[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C0NDP0NHT0C697JPCEG6T1":3,"skill-same:01M7C0NDP0NHT0C697JPCEG6T1":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7C0NDP0NHT0C697JPCEG6T1","autonomous-discovery",null,"Layer 1 intelligence source discovery - auto-detect available sources, search for public information, negotiate with user, produce inventory manifest","zak-keown\u002Fmoe","zak-keown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320717241?v=4","01M7BZFXME0NW6TQX0H7AZM2KS","01M7BZFXN32VR0JN5AATRD53H4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-backstory\u002Fskills\u002Fautonomous-discovery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: autonomous-discovery\ndescription: Layer 1 intelligence source discovery - auto-detect available sources, search for public information, negotiate with user, produce inventory manifest\n---\n\n# Autonomous Discovery\n\nDiscover and inventory every intelligence source available for the target product. Produce a manifest that downstream agents use to plan their analysis.\n\n## The Core Principle\n\n**Find everything. Catalog it. Ask the user what you missed.**\n\nDiscovery is the first thing that runs in Layer 1. Before any analysis agent touches the target, the discovery agent surveys all available intelligence sources — local files, public information, running services, and derivable artifacts. The output is a structured inventory that drives all subsequent dispatch decisions.\n\n## When This Skill Applies\n\nThis skill is loaded by `analyzer` agents dispatched with the `discovery-agent` role. It runs once at the start of Layer 1, before any analysis mode agents are dispatched.\n\n## Four-Phase Discovery\n\n```dot\ndigraph discovery {\n    rankdir=TB;\n\n    \"Start discovery\" [shape=doublecircle];\n    \"Phase 1: Local filesystem scan\" [shape=box];\n    \"Phase 2: Web search\" [shape=box];\n    \"Phase 3: Service detection\" [shape=box];\n    \"Phase 4: Derived source assessment\" [shape=box];\n    \"Write inventory manifest\" [shape=box];\n    \"User negotiation\" [shape=box];\n    \"Write dispatch mapping\" [shape=box];\n    \"Discovery complete\" [shape=doublecircle];\n\n    \"Start discovery\" -> \"Phase 1: Local filesystem scan\";\n    \"Phase 1: Local filesystem scan\" -> \"Phase 2: Web search\";\n    \"Phase 2: Web search\" -> \"Phase 3: Service detection\";\n    \"Phase 3: Service detection\" -> \"Phase 4: Derived source assessment\";\n    \"Phase 4: Derived source assessment\" -> \"Write inventory manifest\";\n    \"Write inventory manifest\" -> \"User negotiation\";\n    \"User negotiation\" -> \"Write dispatch mapping\";\n    \"Write dispatch mapping\" -> \"Discovery complete\";\n}\n```\n\n---\n\n## Phase 1: Local Filesystem Scan\n\nSurvey the target path and its surrounding context. Read directory structures, detect file types, and catalog everything that could feed analysis.\n\n### 1.1 Source Code Detection\n\nDetect source code by file extension. Do not assume a single language — multi-language projects are common.\n\n| Language Family | Extensions |\n|----------------|------------|\n| JavaScript\u002FTypeScript | `.js`, `.jsx`, `.ts`, `.tsx`, `.mjs`, `.cjs`, `.mts`, `.cts` |\n| Python | `.py`, `.pyx`, `.pxd`, `.pyi` |\n| Rust | `.rs` |\n| Go | `.go` |\n| Java\u002FKotlin | `.java`, `.kt`, `.kts` |\n| C\u002FC++ | `.c`, `.h`, `.cpp`, `.hpp`, `.cc`, `.hh`, `.cxx`, `.hxx` |\n| C# | `.cs`, `.csx` |\n| Ruby | `.rb`, `.rake`, `.gemspec` |\n| Swift | `.swift` |\n| PHP | `.php` |\n| Elixir\u002FErlang | `.ex`, `.exs`, `.erl`, `.hrl` |\n| Scala | `.scala`, `.sc` |\n| Dart | `.dart` |\n| Lua | `.lua` |\n| Shell | `.sh`, `.bash`, `.zsh`, `.fish` |\n| Zig | `.zig` |\n\n```bash\n# Count source files by extension\nfind \"$TARGET_PATH\" -type f \\( \\\n  -name \"*.js\" -o -name \"*.ts\" -o -name \"*.jsx\" -o -name \"*.tsx\" \\\n  -o -name \"*.py\" -o -name \"*.rs\" -o -name \"*.go\" \\\n  -o -name \"*.java\" -o -name \"*.kt\" -o -name \"*.c\" -o -name \"*.cpp\" \\\n  -o -name \"*.cs\" -o -name \"*.rb\" -o -name \"*.swift\" -o -name \"*.php\" \\\n  -o -name \"*.ex\" -o -name \"*.scala\" -o -name \"*.dart\" \\\n  -o -name \"*.sh\" -o -name \"*.lua\" -o -name \"*.zig\" \\\n\\) | sed 's\u002F.*\\.\u002F\u002F' | sort | uniq -c | sort -rn\n```\n\nRecord the primary language (most files), secondary languages, and total source file count.\n\n### 1.2 Binary Detection\n\nIdentify compiled artifacts by magic bytes and file extension.\n\n| Binary Type | Detection Method |\n|-------------|-----------------|\n| ELF (Linux native) | `file` output contains \"ELF\" |\n| Mach-O (macOS native) | `file` output contains \"Mach-O\" |\n| PE (Windows native) | `file` output contains \"PE32\" or \"PE32+\" |\n| JVM (`.jar`, `.war`, `.class`) | Extension + `file` confirms \"Java archive\" or \"compiled Java\" |\n| .NET (`.dll`, managed `.exe`) | `file` output contains \"Mono\u002F.Net assembly\" or PE with IL metadata |\n| Python bytecode (`.pyc`, `.pyo`) | Extension + magic number check |\n| WebAssembly (`.wasm`) | Extension + `file` confirms \"WebAssembly\" |\n| Electron\u002FASAR | `.asar` extension |\n\n```bash\n# Find binaries by magic\nfind \"$TARGET_PATH\" -type f \\( \\\n  -name \"*.jar\" -o -name \"*.war\" -o -name \"*.class\" \\\n  -o -name \"*.dll\" -o -name \"*.exe\" -o -name \"*.so\" -o -name \"*.dylib\" \\\n  -o -name \"*.pyc\" -o -name \"*.pyo\" \\\n  -o -name \"*.wasm\" -o -name \"*.asar\" \\\n\\) 2>\u002Fdev\u002Fnull | head -50\n\n# For extensionless binaries, check file type on executables\nfind \"$TARGET_PATH\" -type f -perm +111 ! -name \"*.*\" -exec file {} \\; 2>\u002Fdev\u002Fnull | \\\n  grep -E \"ELF|Mach-O|PE32\" | head -20\n```\n\n### 1.3 Test Suite Detection\n\nDetect test infrastructure by directory conventions and framework markers.\n\n#### Directory Conventions\n\n| Pattern | Likely Framework |\n|---------|-----------------|\n| `__tests__\u002F` | Jest (JavaScript) |\n| `test\u002F`, `tests\u002F` | Generic (any language) |\n| `spec\u002F`, `specs\u002F` | RSpec (Ruby), Jasmine (JS) |\n| `*_test.go` files | Go testing |\n| `test_*.py`, `*_test.py` files | pytest |\n| `cypress\u002F`, `cypress.config.*` | Cypress |\n| `e2e\u002F`, `playwright.config.*` | Playwright |\n| `integration\u002F` | Integration test suite |\n| `fixtures\u002F`, `cassettes\u002F` | Test fixtures \u002F HTTP recordings |\n\n#### Framework Markers\n\nCheck build\u002Fconfig files for test framework dependencies:\n\n```bash\n# JavaScript: package.json\ngrep -l '\"jest\"\\|\"vitest\"\\|\"mocha\"\\|\"ava\"\\|\"tap\"\\|\"playwright\"\\|\"cypress\"\\|\"@testing-library\"' \\\n  \"$TARGET_PATH\"\u002Fpackage.json \"$TARGET_PATH\"\u002F*\u002Fpackage.json 2>\u002Fdev\u002Fnull\n\n# Python: pyproject.toml, setup.cfg, tox.ini, pytest.ini\ngrep -rl \"pytest\\|unittest\\|nose2\\|tox\" \\\n  \"$TARGET_PATH\"\u002Fpyproject.toml \"$TARGET_PATH\"\u002Fsetup.cfg \\\n  \"$TARGET_PATH\"\u002Ftox.ini \"$TARGET_PATH\"\u002Fpytest.ini 2>\u002Fdev\u002Fnull\n\n# Ruby: Gemfile\ngrep -l \"rspec\\|minitest\\|cucumber\" \"$TARGET_PATH\"\u002FGemfile 2>\u002Fdev\u002Fnull\n\n# Java\u002FKotlin: pom.xml, build.gradle\ngrep -l \"junit\\|testng\\|mockito\\|spock\" \\\n  \"$TARGET_PATH\"\u002Fpom.xml \"$TARGET_PATH\"\u002Fbuild.gradle \"$TARGET_PATH\"\u002Fbuild.gradle.kts 2>\u002Fdev\u002Fnull\n\n# Rust: look for #[cfg(test)] or #[test] in source\ngrep -rl '#\\[cfg(test)\\]\\|#\\[test\\]' \"$TARGET_PATH\"\u002Fsrc\u002F 2>\u002Fdev\u002Fnull | head -5\n\n# Go: look for _test.go files\nfind \"$TARGET_PATH\" -name \"*_test.go\" | head -5\n\n# C#: look for test project patterns\nfind \"$TARGET_PATH\" -name \"*.csproj\" -exec grep -l \"Microsoft.NET.Test.Sdk\\|xunit\\|nunit\\|MSTest\" {} \\; 2>\u002Fdev\u002Fnull\n```\n\nRecord: framework name, estimated test count (file count), test types present (unit, integration, e2e).\n\n### 1.4 Documentation Detection\n\n```bash\n# README files\nfind \"$TARGET_PATH\" -maxdepth 2 -iname \"readme*\" -type f 2>\u002Fdev\u002Fnull\n\n# Documentation directories\nfind \"$TARGET_PATH\" -maxdepth 2 -type d \\( \\\n  -iname \"docs\" -o -iname \"doc\" -o -iname \"documentation\" \\\n  -o -iname \"wiki\" -o -iname \"guide\" -o -iname \"guides\" \\\n\\) 2>\u002Fdev\u002Fnull\n\n# Generated documentation\nfind \"$TARGET_PATH\" -maxdepth 3 -type d \\( \\\n  -iname \"javadoc\" -o -iname \"typedoc\" -o -iname \"rustdoc\" \\\n  -o -iname \"godoc\" -o -iname \"apidoc\" -o -iname \"_build\" \\\n  -o -iname \"site\" \\\n\\) 2>\u002Fdev\u002Fnull\n\n# Man pages\nfind \"$TARGET_PATH\" -name \"*.1\" -o -name \"*.5\" -o -name \"*.8\" 2>\u002Fdev\u002Fnull | head -10\n\n# Changelog \u002F release notes\nfind \"$TARGET_PATH\" -maxdepth 2 -iname \"changelog*\" -o -iname \"changes*\" \\\n  -o -iname \"release-notes*\" -o -iname \"history*\" 2>\u002Fdev\u002Fnull\n```\n\n### 1.5 Configuration and Build Files\n\n| Category | Files |\n|----------|-------|\n| Package manifests | `package.json`, `Cargo.toml`, `go.mod`, `pyproject.toml`, `setup.py`, `Gemfile`, `pom.xml`, `build.gradle`, `*.csproj`, `Package.swift`, `pubspec.yaml`, `mix.exs`, `composer.json` |\n| Build systems | `Makefile`, `CMakeLists.txt`, `Dockerfile`, `docker-compose.yml`, `Justfile`, `Taskfile.yml`, `Rakefile`, `BUILD`, `WORKSPACE` (Bazel) |\n| CI\u002FCD | `.github\u002Fworkflows\u002F`, `.gitlab-ci.yml`, `.circleci\u002F`, `Jenkinsfile`, `.travis.yml`, `azure-pipelines.yml`, `bitbucket-pipelines.yml` |\n| Linting\u002Fformatting | `.eslintrc*`, `.prettierrc*`, `rustfmt.toml`, `.flake8`, `.rubocop.yml`, `.editorconfig` |\n| Env\u002Fconfig | `.env`, `.env.example`, `*.config.js`, `*.config.ts`, `config\u002F`, `settings\u002F` |\n\n```bash\n# Package manifests\nfind \"$TARGET_PATH\" -maxdepth 2 \\( \\\n  -name \"package.json\" -o -name \"Cargo.toml\" -o -name \"go.mod\" \\\n  -o -name \"pyproject.toml\" -o -name \"setup.py\" -o -name \"Gemfile\" \\\n  -o -name \"pom.xml\" -o -name \"build.gradle\" -o -name \"*.csproj\" \\\n  -o -name \"Package.swift\" -o -name \"pubspec.yaml\" -o -name \"mix.exs\" \\\n  -o -name \"composer.json\" \\\n\\) -type f 2>\u002Fdev\u002Fnull\n\n# Build\u002FCI files\nfind \"$TARGET_PATH\" -maxdepth 3 \\( \\\n  -name \"Makefile\" -o -name \"Dockerfile\" -o -name \"docker-compose.yml\" \\\n  -o -name \"docker-compose.yaml\" -o -name \"Justfile\" \\\n  -o -name \"Jenkinsfile\" -o -name \".gitlab-ci.yml\" \\\n  -o -name \".travis.yml\" \\\n\\) -type f 2>\u002Fdev\u002Fnull\n\nfind \"$TARGET_PATH\" -maxdepth 3 -path \"*\u002F.github\u002Fworkflows\u002F*.yml\" -type f 2>\u002Fdev\u002Fnull\n```\n\n### 1.6 Machine-Readable Contracts\n\n| Contract Type | File Patterns |\n|---------------|--------------|\n| OpenAPI \u002F Swagger | `openapi.json`, `openapi.yaml`, `swagger.json`, `swagger.yaml`, `*.openapi.*` |\n| GraphQL | `schema.graphql`, `*.graphql`, `*.gql`, `schema.gql` |\n| Protocol Buffers | `*.proto` |\n| JSON Schema | `*.schema.json`, files containing `\"$schema\"` |\n| gRPC service definitions | `*.proto` containing `service` keyword |\n| AsyncAPI | `asyncapi.json`, `asyncapi.yaml` |\n| WSDL | `*.wsdl` |\n| TypeScript declarations | `*.d.ts` (especially in `types\u002F` or `@types\u002F`) |\n\n```bash\n# API contracts\nfind \"$TARGET_PATH\" -type f \\( \\\n  -name \"openapi.*\" -o -name \"swagger.*\" \\\n  -o -name \"*.graphql\" -o -name \"*.gql\" \\\n  -o -name \"*.proto\" \\\n  -o -name \"*.schema.json\" \\\n  -o -name \"asyncapi.*\" -o -name \"*.wsdl\" \\\n\\) 2>\u002Fdev\u002Fnull\n\n# TypeScript declarations (type contracts)\nfind \"$TARGET_PATH\" -name \"*.d.ts\" -not -path \"*\u002Fnode_modules\u002F*\" 2>\u002Fdev\u002Fnull | head -20\n```\n\n### 1.7 Version Control\n\n```bash\n# Git repository detection\nif [ -d \"$TARGET_PATH\u002F.git\" ]; then\n  echo \"Git repository detected\"\n\n  # Commit count and history span\n  git -C \"$TARGET_PATH\" rev-list --count HEAD 2>\u002Fdev\u002Fnull\n  git -C \"$TARGET_PATH\" log --format=\"%ai\" --reverse | head -1  # first commit\n  git -C \"$TARGET_PATH\" log --format=\"%ai\" -1                   # latest commit\n\n  # Branch count\n  git -C \"$TARGET_PATH\" branch -a --list 2>\u002Fdev\u002Fnull | wc -l\n\n  # Remote platform detection\n  REMOTE_URL=$(git -C \"$TARGET_PATH\" remote get-url origin 2>\u002Fdev\u002Fnull)\n  echo \"$REMOTE_URL\" | grep -oE \"github\\.com|gitlab\\.com|bitbucket\\.org|codeberg\\.org|sr\\.ht\" || echo \"Unknown platform or no remote\"\n\n  # Contributors\n  git -C \"$TARGET_PATH\" shortlog -sn --no-merges HEAD 2>\u002Fdev\u002Fnull | head -10\n\n  # Tags (releases)\n  git -C \"$TARGET_PATH\" tag --list 2>\u002Fdev\u002Fnull | tail -10\nfi\n```\n\n---\n\n## Phase 2: Web Search\n\nSearch the public internet for information about the target product. This phase requires knowing the product name — extract it from package manifests, README, or the directory name.\n\n### 2.1 Product Identification\n\nBefore searching, determine the product name and any aliases:\n\n```bash\n# From package.json\ngrep '\"name\"' \"$TARGET_PATH\u002Fpackage.json\" 2>\u002Fdev\u002Fnull | head -1\n\n# From Cargo.toml\ngrep '^name\\s*=' \"$TARGET_PATH\u002FCargo.toml\" 2>\u002Fdev\u002Fnull | head -1\n\n# From pyproject.toml or setup.py\ngrep 'name\\s*=' \"$TARGET_PATH\u002Fpyproject.toml\" 2>\u002Fdev\u002Fnull | head -1\n\n# From go.mod\nhead -1 \"$TARGET_PATH\u002Fgo.mod\" 2>\u002Fdev\u002Fnull\n\n# From README title\nhead -5 \"$TARGET_PATH\u002FREADME.md\" 2>\u002Fdev\u002Fnull | grep -E \"^#\"\n\n# Fallback: directory name\nbasename \"$TARGET_PATH\"\n```\n\n### 2.2 Official Documentation\n\nSearch for official documentation and API references using WebSearch:\n\n| # | Search Query | Purpose |\n|---|-------------|---------|\n| 1 | `{product} documentation` | Main docs site |\n| 2 | `{product} API reference` | API surface |\n| 3 | `{product} getting started` | Setup and first use |\n| 4 | `{product} configuration reference` | Config keys, defaults |\n| 5 | `{product} CLI reference` | Commands, flags |\n\nRecord the documentation site URL and whether it appears comprehensive or sparse.\n\n### 2.3 Package Registry Entries\n\nSearch relevant package registries based on the languages detected in Phase 1:\n\n| Registry | URL Pattern |\n|----------|------------|\n| npm | `https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F{name}` |\n| PyPI | `https:\u002F\u002Fpypi.org\u002Fproject\u002F{name}` |\n| crates.io | `https:\u002F\u002Fcrates.io\u002Fcrates\u002F{name}` |\n| Maven Central | `https:\u002F\u002Fsearch.maven.org\u002Fartifact\u002F{group}\u002F{name}` |\n| NuGet | `https:\u002F\u002Fwww.nuget.org\u002Fpackages\u002F{name}` |\n| RubyGems | `https:\u002F\u002Frubygems.org\u002Fgems\u002F{name}` |\n| pkg.go.dev | `https:\u002F\u002Fpkg.go.dev\u002F{module-path}` |\n| Hex.pm | `https:\u002F\u002Fhex.pm\u002Fpackages\u002F{name}` |\n| Packagist | `https:\u002F\u002Fpackagist.org\u002Fpackages\u002F{vendor}\u002F{name}` |\n| pub.dev | `https:\u002F\u002Fpub.dev\u002Fpackages\u002F{name}` |\n\nRecord: registry URL, version, download count, last publish date.\n\n### 2.4 Community Content\n\n| # | Search Query | Purpose |\n|---|-------------|---------|\n| 1 | `{product} site:stackoverflow.com` | Community Q&A |\n| 2 | `{product} site:github.com issues` | Issue tracker |\n| 3 | `{product} tutorial` | Community tutorials |\n| 4 | `{product} blog` | Blog posts |\n\nFor discovery purposes, you do not need to deeply analyze this content. Record whether each category has substantial results (many hits) or sparse results (few or none). The `doc-researcher` and `community-analyst` agents will do deep extraction later.\n\n### 2.5 Third-Party Libraries and Plugins\n\n| # | Search Query | Purpose |\n|---|-------------|---------|\n| 1 | `{product} SDK` or `{product} client library` | Official\u002Fcommunity SDKs |\n| 2 | `{product} plugin` or `{product} extension` | Plugin ecosystem |\n| 3 | `{product} integration` | Third-party integrations |\n\nRecord: whether an SDK ecosystem exists, approximate size, which languages are covered.\n\n---\n\n## Phase 3: Service Detection\n\nDetermine whether the target is a running service or can be started as one.\n\n### 3.1 Port Scanning\n\nIf the target appears to be a server (presence of `server`, `listen`, `bind`, `port` in source or config):\n\n```bash\n# Check common development ports\nfor port in 80 443 3000 3001 4000 5000 5173 5432 6379 8000 8080 8443 8888 9090 27017; do\n  (echo >\u002Fdev\u002Ftcp\u002Flocalhost\u002F$port) 2>\u002Fdev\u002Fnull && echo \"Port $port: OPEN\"\ndone\n```\n\n### 3.2 Health Endpoints\n\nFor any open ports found, probe standard health endpoints:\n\n```bash\nfor port in $OPEN_PORTS; do\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002Fhealth\" 2>\u002Fdev\u002Fnull\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002Fhealthz\" 2>\u002Fdev\u002Fnull\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002Fapi\u002Fhealth\" 2>\u002Fdev\u002Fnull\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002F\" 2>\u002Fdev\u002Fnull\ndone\n```\n\n### 3.3 Process Detection\n\n```bash\n# Check if the target is already running\nps aux | grep -i \"$(basename \"$TARGET_PATH\")\" | grep -v grep\n\n# Check for known server processes\nps aux | grep -E \"node|python|ruby|java|dotnet|go \" | grep -v grep | head -10\n```\n\n### 3.4 Container Runtime Availability\n\n```bash\n# Docker\ndocker info >\u002Fdev\u002Fnull 2>&1 && echo \"Docker: available\" || echo \"Docker: not available\"\ndocker ps 2>\u002Fdev\u002Fnull | grep -i \"$(basename \"$TARGET_PATH\")\" | head -5\n\n# Podman\npodman info >\u002Fdev\u002Fnull 2>&1 && echo \"Podman: available\" || echo \"Podman: not available\"\n\n# Docker Compose\ndocker compose version >\u002Fdev\u002Fnull 2>&1 && echo \"Docker Compose: available\" || echo \"Docker Compose: not available\"\n```\n\nRecord: container runtime available (docker\u002Fpodman\u002Fnone), existing containers related to the target, whether docker-compose.yml or similar exists.\n\n---\n\n## Phase 4: Derived Source Assessment\n\nAssess what additional intelligence sources can be created from what already exists.\n\n### 4.1 Minified Code Recovery\n\nIf Phase 1 found minified JavaScript bundles (few lines, many bytes per file):\n\n| Source | Derived Artifact | Method | Quality |\n|--------|-----------------|--------|---------|\n| Minified `.js` | Beautified source | `js-beautify` | Lossless formatting recovery |\n| `.js.map` source maps | Original source | Source map extraction | Near-original if maps are present |\n| Minified CSS | Beautified CSS | `css-beautify` | Lossless formatting recovery |\n\n```bash\n# Check for source maps\nfind \"$TARGET_PATH\" -name \"*.js.map\" -o -name \"*.css.map\" 2>\u002Fdev\u002Fnull | head -10\n\n# Check if JS files reference source maps\ngrep -rl \"sourceMappingURL\" \"$TARGET_PATH\" --include=\"*.js\" 2>\u002Fdev\u002Fnull | head -10\n```\n\n### 4.2 Binary Decompilation Potential\n\nBased on binaries found in Phase 1, assess decompilation feasibility:\n\n| Binary Type | Decompilation Quality | Tool Required |\n|-------------|----------------------|---------------|\n| JVM (`.jar`, `.class`) | Very high (near-source) | CFR, Procyon, FernFlower |\n| .NET (managed `.dll`) | Very high (near-source) | ILSpy (`ilspycmd`) |\n| Python (`.pyc`) | Very high (near-source) | uncompyle6, decompyle3 |\n| Electron (`.asar`) | Lossless (bundled source) | `npx asar extract` |\n| WebAssembly (`.wasm`) | Limited (WAT text format) | `wasm2wat` |\n| Native ELF\u002FMach-O\u002FPE | Low (disassembly only) | Ghidra, radare2 |\n\n### 4.3 Bundle Splitting Potential\n\nIf webpack, esbuild, rollup, or parcel bundles are detected:\n\n```bash\n# Detect bundler\nhead -50 \"$TARGET_PATH\"\u002Fdist\u002F*.js 2>\u002Fdev\u002Fnull | grep -oE \"webpack|esbuild|rollup|parcel\" | head -1\n\n# Check for multiple entry points\nfind \"$TARGET_PATH\" -path \"*\u002Fdist\u002F*\" -name \"*.js\" -not -name \"*.min.js\" 2>\u002Fdev\u002Fnull | wc -l\n```\n\n### 4.4 Database Schema Extraction\n\nIf database files or migration directories exist:\n\n```bash\n# SQL migrations\nfind \"$TARGET_PATH\" -type d -name \"migrations\" -o -name \"migrate\" 2>\u002Fdev\u002Fnull\nfind \"$TARGET_PATH\" -name \"*.sql\" 2>\u002Fdev\u002Fnull | head -10\n\n# ORM schema files\nfind \"$TARGET_PATH\" -name \"schema.prisma\" -o -name \"schema.rb\" 2>\u002Fdev\u002Fnull\nfind \"$TARGET_PATH\" -path \"*\u002Fmodels\u002F*.py\" -o -path \"*\u002Fentities\u002F*.ts\" 2>\u002Fdev\u002Fnull | head -10\n\n# SQLite databases\nfind \"$TARGET_PATH\" -name \"*.db\" -o -name \"*.sqlite\" -o -name \"*.sqlite3\" 2>\u002Fdev\u002Fnull | head -5\n```\n\n---\n\n## Inventory Manifest\n\nAfter all four phases complete, write the inventory to `workspace\u002Finventory.md`.\n\n### Format\n\n```markdown\n# Intelligence Source Inventory\n\n## Metadata\n- **Target:** {product name}\n- **Target path:** {absolute path}\n- **Discovery agent:** discovery-agent\n- **Date:** {ISO 8601}\n- **Phases completed:** 1, 2, 3, 4\n\n---\n\n## Source Code\n\n| Language | File Count | Location | Analytical Value |\n|----------|-----------|----------|-----------------|\n| TypeScript | 247 | src\u002F | PRIMARY — main application logic |\n| JavaScript | 34 | scripts\u002F, config\u002F | SUPPORTING — build and config |\n| ... | ... | ... | ... |\n\n## Binaries\n\n| Type | Count | Location | Decompilation Potential |\n|------|-------|----------|------------------------|\n| ... | ... | ... | ... |\n\n## Test Suites\n\n| Framework | Type | File Count | Location |\n|-----------|------|-----------|----------|\n| Jest | unit | 89 | __tests__\u002F |\n| Playwright | e2e | 12 | e2e\u002F |\n| ... | ... | ... | ... |\n\n## Documentation\n\n| Type | Location | Notes |\n|------|----------|-------|\n| README | .\u002FREADME.md | 450 lines, comprehensive |\n| API docs | docs\u002Fapi\u002F | Generated TypeDoc |\n| ... | ... | ... |\n\n## Configuration and Build\n\n| File | Purpose |\n|------|---------|\n| package.json | Node.js manifest, scripts, dependencies |\n| Dockerfile | Container build definition |\n| ... | ... |\n\n## Machine-Readable Contracts\n\n| Type | File | Notes |\n|------|------|-------|\n| OpenAPI 3.0 | api\u002Fopenapi.yaml | 2400 lines, comprehensive |\n| GraphQL schema | schema.graphql | 180 types |\n| ... | ... | ... |\n\n## Version Control\n\n| Property | Value |\n|----------|-------|\n| VCS | git |\n| Commits | 1,847 |\n| Branches | 12 |\n| Tags\u002Freleases | 34 |\n| Remote platform | GitHub |\n| Contributors | 8 |\n| History span | 2021-03-15 to 2024-11-20 |\n\n## Public Information (Web Search)\n\n| Category | Availability | Notes |\n|----------|-------------|-------|\n| Official docs | Yes — docs.example.com | Comprehensive API reference |\n| Package registry | npm — 45k weekly downloads | Active maintenance |\n| Community Q&A | ~120 Stack Overflow questions | Moderate community |\n| Tutorials | 8+ blog posts found | Several recent |\n| Third-party SDKs | 3 community libraries (Python, Go, Ruby) | Active ecosystem |\n| Plugins\u002Fextensions | VS Code extension, 2 CLI plugins | Small plugin ecosystem |\n\n## Running Services\n\n| Port | Service | Health |\n|------|---------|--------|\n| 3000 | Dev server | 200 OK at \u002Fhealth |\n| 5432 | PostgreSQL | Accepting connections |\n\n## Container Runtime\n\n| Runtime | Available | Target Containers |\n|---------|-----------|-------------------|\n| Docker | Yes | app (running), db (running) |\n| Docker Compose | Yes | docker-compose.yml with 3 services |\n\n## Derived Sources (Can Be Created)\n\n| Source | Method | Expected Quality |\n|--------|--------|-----------------|\n| Beautified dist\u002Fmain.js | js-beautify | Lossless formatting |\n| Source maps → original source | source map extraction | Near-original |\n| JVM class files → Java source | CFR decompiler | Very high |\n| SQL schema from migrations | Migration replay | Definitive |\n\n---\n\n## Summary\n\n- **Primary intelligence sources:** {list the most valuable sources}\n- **Secondary sources:** {supporting sources}\n- **Gaps:** {what is missing or unavailable}\n- **Recommended analysis modes:** {which modes should run based on what was found}\n```\n\nAdapt the tables to match what was actually found. Omit sections that have no entries (e.g., if there are no binaries, omit the Binaries table). Do not fabricate entries.\n\n---\n\n## User Negotiation\n\nAfter writing the inventory manifest, present it to the user and ask:\n\n> Here is what I found. The inventory is at `workspace\u002Finventory.md`.\n>\n> **Key findings:**\n> - {summary of most significant sources}\n> - {notable gaps or surprises}\n>\n> **Recommended analysis modes:** {modes}\n>\n> Two questions:\n> 1. **Is there anything else I should look at?** Other repositories, deployed instances, internal documentation, API keys for authenticated endpoints, etc.\n> 2. **Is anything off-limits?** Files, directories, or services I should NOT analyze (proprietary dependencies, third-party code you don't own, production databases, etc.).\n\nWait for the user's response. Update `workspace\u002Finventory.md` with any additions or exclusions they provide. Mark excluded items clearly:\n\n```markdown\n## Exclusions (User-Specified)\n\n| Item | Reason |\n|------|--------|\n| vendor\u002F | Third-party code, not owned |\n| .env | Contains production secrets |\n```\n\n---\n\n## Dispatch Mapping\n\nAfter the inventory is finalized (including user feedback), write a dispatch mapping table to the end of `workspace\u002Finventory.md`. This table tells the orchestrator which agent roles and skills to assign to each source type.\n\n```markdown\n## Dispatch Mapping\n\n| Source Type | Agent Role | Skill | Priority | Input Path |\n|-------------|-----------|-------|----------|------------|\n| Source code (structured) | chunk-analyzer, function-analyzer | source-analysis | P0 | src\u002F |\n| Source code (bundled\u002Fminified) | bundle-splitter → chunk-analyzer → function-analyzer | source-analysis | P0 | dist\u002F |\n| Official documentation | doc-researcher | doc-research | P0 | (web) docs.example.com |\n| Community content | community-analyst | community-intelligence | P1 | (web) search results |\n| SDK ecosystem | sdk-analyzer, integration-test-miner | ecosystem-analysis | P1 | (web) npm\u002FPyPI\u002FGitHub |\n| Test suites | chunk-analyzer | source-analysis | P0 | __tests__\u002F, e2e\u002F |\n| Runtime (CLI) | cli-explorer | runtime-observation | P1 | container |\n| Runtime (Web UI) | web-ui-explorer | runtime-observation | P1 | container |\n| Runtime (Behavior) | behavior-observer | runtime-observation | P2 | container |\n| Binaries (managed) | binary-surveyor → source-analysis handoff | binary-analysis | P2 | lib\u002F*.jar |\n| Binaries (native) | binary-surveyor, binary-deep-analyzer | binary-analysis | P3 | bin\u002F |\n| OpenAPI spec | doc-researcher | doc-research | P0 | api\u002Fopenapi.yaml |\n| GraphQL schema | doc-researcher | doc-research | P0 | schema.graphql |\n| Protobuf definitions | doc-researcher | doc-research | P1 | proto\u002F |\n| Derived: beautified bundles | bundle-splitter | source-analysis | P0 | (created from dist\u002F) |\n| Derived: decompiled binaries | binary-surveyor → source-analysis | binary-analysis | P2 | (created from binaries) |\n```\n\nAdapt this table to the actual sources found. Only include rows for source types that exist in the inventory. Priority levels:\n\n- **P0** — Primary intelligence sources. Analysis cannot proceed without these.\n- **P1** — High-value supplementary sources. Significantly improve coverage and confidence.\n- **P2** — Useful corroborating sources. Fill gaps and confirm claims from P0\u002FP1 sources.\n- **P3** — Low-yield sources. Only analyze if time permits and other sources leave gaps.\n\n---\n\n## Output Structure\n\n```\nworkspace\u002F\n└── inventory.md          # Complete inventory manifest with dispatch mapping\n```\n\nThe inventory is a single file. It is the first artifact written to the workspace and drives all subsequent agent dispatch decisions.\n\n## Rules\n\n1. **Scan before you search.** Phase 1 (local filesystem) always runs before Phase 2 (web search). Local files are the ground truth about what exists.\n2. **Do not analyze, only catalog.** Discovery identifies sources; it does not read or interpret them. That is the job of downstream analysis agents.\n3. **Record absence as well as presence.** If there are no tests, no docs, no binaries — say so explicitly. Gaps in the inventory are as important as entries.\n4. **Respect user boundaries.** If the user marks something off-limits, exclude it from the inventory and ensure no downstream agent touches it.\n5. **Be concrete.** File counts, directory paths, port numbers, URLs. Vague inventories produce vague analysis plans.\n6. **One pass, not exhaustive.** Discovery is a survey, not a deep audit. Spend minutes, not hours. Downstream agents will do the exhaustive reading.\n","# Autonomous Discovery\n\nDiscover and inventory every intelligence source available for the target product. Produce a manifest that downstream agents use to plan their analysis.\n\n## The Core Principle\n\n**Find everything. Catalog it. Ask the user what you missed.**\n\nDiscovery is the first thing that runs in Layer 1. Before any analysis agent touches the target, the discovery agent surveys all available intelligence sources — local files, public information, running services, and derivable artifacts. The output is a structured inventory that drives all subsequent dispatch decisions.\n\n## When This Skill Applies\n\nThis skill is loaded by `analyzer` agents dispatched with the `discovery-agent` role. It runs once at the start of Layer 1, before any analysis mode agents are dispatched.\n\n## Four-Phase Discovery\n\n```dot\ndigraph discovery {\n    rankdir=TB;\n\n    \"Start discovery\" [shape=doublecircle];\n    \"Phase 1: Local filesystem scan\" [shape=box];\n    \"Phase 2: Web search\" [shape=box];\n    \"Phase 3: Service detection\" [shape=box];\n    \"Phase 4: Derived source assessment\" [shape=box];\n    \"Write inventory manifest\" [shape=box];\n    \"User negotiation\" [shape=box];\n    \"Write dispatch mapping\" [shape=box];\n    \"Discovery complete\" [shape=doublecircle];\n\n    \"Start discovery\" -> \"Phase 1: Local filesystem scan\";\n    \"Phase 1: Local filesystem scan\" -> \"Phase 2: Web search\";\n    \"Phase 2: Web search\" -> \"Phase 3: Service detection\";\n    \"Phase 3: Service detection\" -> \"Phase 4: Derived source assessment\";\n    \"Phase 4: Derived source assessment\" -> \"Write inventory manifest\";\n    \"Write inventory manifest\" -> \"User negotiation\";\n    \"User negotiation\" -> \"Write dispatch mapping\";\n    \"Write dispatch mapping\" -> \"Discovery complete\";\n}\n```\n\n---\n\n## Phase 1: Local Filesystem Scan\n\nSurvey the target path and its surrounding context. Read directory structures, detect file types, and catalog everything that could feed analysis.\n\n### 1.1 Source Code Detection\n\nDetect source code by file extension. Do not assume a single language — multi-language projects are common.\n\n| Language Family | Extensions |\n|----------------|------------|\n| JavaScript\u002FTypeScript | `.js`, `.jsx`, `.ts`, `.tsx`, `.mjs`, `.cjs`, `.mts`, `.cts` |\n| Python | `.py`, `.pyx`, `.pxd`, `.pyi` |\n| Rust | `.rs` |\n| Go | `.go` |\n| Java\u002FKotlin | `.java`, `.kt`, `.kts` |\n| C\u002FC++ | `.c`, `.h`, `.cpp`, `.hpp`, `.cc`, `.hh`, `.cxx`, `.hxx` |\n| C# | `.cs`, `.csx` |\n| Ruby | `.rb`, `.rake`, `.gemspec` |\n| Swift | `.swift` |\n| PHP | `.php` |\n| Elixir\u002FErlang | `.ex`, `.exs`, `.erl`, `.hrl` |\n| Scala | `.scala`, `.sc` |\n| Dart | `.dart` |\n| Lua | `.lua` |\n| Shell | `.sh`, `.bash`, `.zsh`, `.fish` |\n| Zig | `.zig` |\n\n```bash\n# Count source files by extension\nfind \"$TARGET_PATH\" -type f \\( \\\n  -name \"*.js\" -o -name \"*.ts\" -o -name \"*.jsx\" -o -name \"*.tsx\" \\\n  -o -name \"*.py\" -o -name \"*.rs\" -o -name \"*.go\" \\\n  -o -name \"*.java\" -o -name \"*.kt\" -o -name \"*.c\" -o -name \"*.cpp\" \\\n  -o -name \"*.cs\" -o -name \"*.rb\" -o -name \"*.swift\" -o -name \"*.php\" \\\n  -o -name \"*.ex\" -o -name \"*.scala\" -o -name \"*.dart\" \\\n  -o -name \"*.sh\" -o -name \"*.lua\" -o -name \"*.zig\" \\\n\\) | sed 's\u002F.*\\.\u002F\u002F' | sort | uniq -c | sort -rn\n```\n\nRecord the primary language (most files), secondary languages, and total source file count.\n\n### 1.2 Binary Detection\n\nIdentify compiled artifacts by magic bytes and file extension.\n\n| Binary Type | Detection Method |\n|-------------|-----------------|\n| ELF (Linux native) | `file` output contains \"ELF\" |\n| Mach-O (macOS native) | `file` output contains \"Mach-O\" |\n| PE (Windows native) | `file` output contains \"PE32\" or \"PE32+\" |\n| JVM (`.jar`, `.war`, `.class`) | Extension + `file` confirms \"Java archive\" or \"compiled Java\" |\n| .NET (`.dll`, managed `.exe`) | `file` output contains \"Mono\u002F.Net assembly\" or PE with IL metadata |\n| Python bytecode (`.pyc`, `.pyo`) | Extension + magic number check |\n| WebAssembly (`.wasm`) | Extension + `file` confirms \"WebAssembly\" |\n| Electron\u002FASAR | `.asar` extension |\n\n```bash\n# Find binaries by magic\nfind \"$TARGET_PATH\" -type f \\( \\\n  -name \"*.jar\" -o -name \"*.war\" -o -name \"*.class\" \\\n  -o -name \"*.dll\" -o -name \"*.exe\" -o -name \"*.so\" -o -name \"*.dylib\" \\\n  -o -name \"*.pyc\" -o -name \"*.pyo\" \\\n  -o -name \"*.wasm\" -o -name \"*.asar\" \\\n\\) 2>\u002Fdev\u002Fnull | head -50\n\n# For extensionless binaries, check file type on executables\nfind \"$TARGET_PATH\" -type f -perm +111 ! -name \"*.*\" -exec file {} \\; 2>\u002Fdev\u002Fnull | \\\n  grep -E \"ELF|Mach-O|PE32\" | head -20\n```\n\n### 1.3 Test Suite Detection\n\nDetect test infrastructure by directory conventions and framework markers.\n\n#### Directory Conventions\n\n| Pattern | Likely Framework |\n|---------|-----------------|\n| `__tests__\u002F` | Jest (JavaScript) |\n| `test\u002F`, `tests\u002F` | Generic (any language) |\n| `spec\u002F`, `specs\u002F` | RSpec (Ruby), Jasmine (JS) |\n| `*_test.go` files | Go testing |\n| `test_*.py`, `*_test.py` files | pytest |\n| `cypress\u002F`, `cypress.config.*` | Cypress |\n| `e2e\u002F`, `playwright.config.*` | Playwright |\n| `integration\u002F` | Integration test suite |\n| `fixtures\u002F`, `cassettes\u002F` | Test fixtures \u002F HTTP recordings |\n\n#### Framework Markers\n\nCheck build\u002Fconfig files for test framework dependencies:\n\n```bash\n# JavaScript: package.json\ngrep -l '\"jest\"\\|\"vitest\"\\|\"mocha\"\\|\"ava\"\\|\"tap\"\\|\"playwright\"\\|\"cypress\"\\|\"@testing-library\"' \\\n  \"$TARGET_PATH\"\u002Fpackage.json \"$TARGET_PATH\"\u002F*\u002Fpackage.json 2>\u002Fdev\u002Fnull\n\n# Python: pyproject.toml, setup.cfg, tox.ini, pytest.ini\ngrep -rl \"pytest\\|unittest\\|nose2\\|tox\" \\\n  \"$TARGET_PATH\"\u002Fpyproject.toml \"$TARGET_PATH\"\u002Fsetup.cfg \\\n  \"$TARGET_PATH\"\u002Ftox.ini \"$TARGET_PATH\"\u002Fpytest.ini 2>\u002Fdev\u002Fnull\n\n# Ruby: Gemfile\ngrep -l \"rspec\\|minitest\\|cucumber\" \"$TARGET_PATH\"\u002FGemfile 2>\u002Fdev\u002Fnull\n\n# Java\u002FKotlin: pom.xml, build.gradle\ngrep -l \"junit\\|testng\\|mockito\\|spock\" \\\n  \"$TARGET_PATH\"\u002Fpom.xml \"$TARGET_PATH\"\u002Fbuild.gradle \"$TARGET_PATH\"\u002Fbuild.gradle.kts 2>\u002Fdev\u002Fnull\n\n# Rust: look for #[cfg(test)] or #[test] in source\ngrep -rl '#\\[cfg(test)\\]\\|#\\[test\\]' \"$TARGET_PATH\"\u002Fsrc\u002F 2>\u002Fdev\u002Fnull | head -5\n\n# Go: look for _test.go files\nfind \"$TARGET_PATH\" -name \"*_test.go\" | head -5\n\n# C#: look for test project patterns\nfind \"$TARGET_PATH\" -name \"*.csproj\" -exec grep -l \"Microsoft.NET.Test.Sdk\\|xunit\\|nunit\\|MSTest\" {} \\; 2>\u002Fdev\u002Fnull\n```\n\nRecord: framework name, estimated test count (file count), test types present (unit, integration, e2e).\n\n### 1.4 Documentation Detection\n\n```bash\n# README files\nfind \"$TARGET_PATH\" -maxdepth 2 -iname \"readme*\" -type f 2>\u002Fdev\u002Fnull\n\n# Documentation directories\nfind \"$TARGET_PATH\" -maxdepth 2 -type d \\( \\\n  -iname \"docs\" -o -iname \"doc\" -o -iname \"documentation\" \\\n  -o -iname \"wiki\" -o -iname \"guide\" -o -iname \"guides\" \\\n\\) 2>\u002Fdev\u002Fnull\n\n# Generated documentation\nfind \"$TARGET_PATH\" -maxdepth 3 -type d \\( \\\n  -iname \"javadoc\" -o -iname \"typedoc\" -o -iname \"rustdoc\" \\\n  -o -iname \"godoc\" -o -iname \"apidoc\" -o -iname \"_build\" \\\n  -o -iname \"site\" \\\n\\) 2>\u002Fdev\u002Fnull\n\n# Man pages\nfind \"$TARGET_PATH\" -name \"*.1\" -o -name \"*.5\" -o -name \"*.8\" 2>\u002Fdev\u002Fnull | head -10\n\n# Changelog \u002F release notes\nfind \"$TARGET_PATH\" -maxdepth 2 -iname \"changelog*\" -o -iname \"changes*\" \\\n  -o -iname \"release-notes*\" -o -iname \"history*\" 2>\u002Fdev\u002Fnull\n```\n\n### 1.5 Configuration and Build Files\n\n| Category | Files |\n|----------|-------|\n| Package manifests | `package.json`, `Cargo.toml`, `go.mod`, `pyproject.toml`, `setup.py`, `Gemfile`, `pom.xml`, `build.gradle`, `*.csproj`, `Package.swift`, `pubspec.yaml`, `mix.exs`, `composer.json` |\n| Build systems | `Makefile`, `CMakeLists.txt`, `Dockerfile`, `docker-compose.yml`, `Justfile`, `Taskfile.yml`, `Rakefile`, `BUILD`, `WORKSPACE` (Bazel) |\n| CI\u002FCD | `.github\u002Fworkflows\u002F`, `.gitlab-ci.yml`, `.circleci\u002F`, `Jenkinsfile`, `.travis.yml`, `azure-pipelines.yml`, `bitbucket-pipelines.yml` |\n| Linting\u002Fformatting | `.eslintrc*`, `.prettierrc*`, `rustfmt.toml`, `.flake8`, `.rubocop.yml`, `.editorconfig` |\n| Env\u002Fconfig | `.env`, `.env.example`, `*.config.js`, `*.config.ts`, `config\u002F`, `settings\u002F` |\n\n```bash\n# Package manifests\nfind \"$TARGET_PATH\" -maxdepth 2 \\( \\\n  -name \"package.json\" -o -name \"Cargo.toml\" -o -name \"go.mod\" \\\n  -o -name \"pyproject.toml\" -o -name \"setup.py\" -o -name \"Gemfile\" \\\n  -o -name \"pom.xml\" -o -name \"build.gradle\" -o -name \"*.csproj\" \\\n  -o -name \"Package.swift\" -o -name \"pubspec.yaml\" -o -name \"mix.exs\" \\\n  -o -name \"composer.json\" \\\n\\) -type f 2>\u002Fdev\u002Fnull\n\n# Build\u002FCI files\nfind \"$TARGET_PATH\" -maxdepth 3 \\( \\\n  -name \"Makefile\" -o -name \"Dockerfile\" -o -name \"docker-compose.yml\" \\\n  -o -name \"docker-compose.yaml\" -o -name \"Justfile\" \\\n  -o -name \"Jenkinsfile\" -o -name \".gitlab-ci.yml\" \\\n  -o -name \".travis.yml\" \\\n\\) -type f 2>\u002Fdev\u002Fnull\n\nfind \"$TARGET_PATH\" -maxdepth 3 -path \"*\u002F.github\u002Fworkflows\u002F*.yml\" -type f 2>\u002Fdev\u002Fnull\n```\n\n### 1.6 Machine-Readable Contracts\n\n| Contract Type | File Patterns |\n|---------------|--------------|\n| OpenAPI \u002F Swagger | `openapi.json`, `openapi.yaml`, `swagger.json`, `swagger.yaml`, `*.openapi.*` |\n| GraphQL | `schema.graphql`, `*.graphql`, `*.gql`, `schema.gql` |\n| Protocol Buffers | `*.proto` |\n| JSON Schema | `*.schema.json`, files containing `\"$schema\"` |\n| gRPC service definitions | `*.proto` containing `service` keyword |\n| AsyncAPI | `asyncapi.json`, `asyncapi.yaml` |\n| WSDL | `*.wsdl` |\n| TypeScript declarations | `*.d.ts` (especially in `types\u002F` or `@types\u002F`) |\n\n```bash\n# API contracts\nfind \"$TARGET_PATH\" -type f \\( \\\n  -name \"openapi.*\" -o -name \"swagger.*\" \\\n  -o -name \"*.graphql\" -o -name \"*.gql\" \\\n  -o -name \"*.proto\" \\\n  -o -name \"*.schema.json\" \\\n  -o -name \"asyncapi.*\" -o -name \"*.wsdl\" \\\n\\) 2>\u002Fdev\u002Fnull\n\n# TypeScript declarations (type contracts)\nfind \"$TARGET_PATH\" -name \"*.d.ts\" -not -path \"*\u002Fnode_modules\u002F*\" 2>\u002Fdev\u002Fnull | head -20\n```\n\n### 1.7 Version Control\n\n```bash\n# Git repository detection\nif [ -d \"$TARGET_PATH\u002F.git\" ]; then\n  echo \"Git repository detected\"\n\n  # Commit count and history span\n  git -C \"$TARGET_PATH\" rev-list --count HEAD 2>\u002Fdev\u002Fnull\n  git -C \"$TARGET_PATH\" log --format=\"%ai\" --reverse | head -1  # first commit\n  git -C \"$TARGET_PATH\" log --format=\"%ai\" -1                   # latest commit\n\n  # Branch count\n  git -C \"$TARGET_PATH\" branch -a --list 2>\u002Fdev\u002Fnull | wc -l\n\n  # Remote platform detection\n  REMOTE_URL=$(git -C \"$TARGET_PATH\" remote get-url origin 2>\u002Fdev\u002Fnull)\n  echo \"$REMOTE_URL\" | grep -oE \"github\\.com|gitlab\\.com|bitbucket\\.org|codeberg\\.org|sr\\.ht\" || echo \"Unknown platform or no remote\"\n\n  # Contributors\n  git -C \"$TARGET_PATH\" shortlog -sn --no-merges HEAD 2>\u002Fdev\u002Fnull | head -10\n\n  # Tags (releases)\n  git -C \"$TARGET_PATH\" tag --list 2>\u002Fdev\u002Fnull | tail -10\nfi\n```\n\n---\n\n## Phase 2: Web Search\n\nSearch the public internet for information about the target product. This phase requires knowing the product name — extract it from package manifests, README, or the directory name.\n\n### 2.1 Product Identification\n\nBefore searching, determine the product name and any aliases:\n\n```bash\n# From package.json\ngrep '\"name\"' \"$TARGET_PATH\u002Fpackage.json\" 2>\u002Fdev\u002Fnull | head -1\n\n# From Cargo.toml\ngrep '^name\\s*=' \"$TARGET_PATH\u002FCargo.toml\" 2>\u002Fdev\u002Fnull | head -1\n\n# From pyproject.toml or setup.py\ngrep 'name\\s*=' \"$TARGET_PATH\u002Fpyproject.toml\" 2>\u002Fdev\u002Fnull | head -1\n\n# From go.mod\nhead -1 \"$TARGET_PATH\u002Fgo.mod\" 2>\u002Fdev\u002Fnull\n\n# From README title\nhead -5 \"$TARGET_PATH\u002FREADME.md\" 2>\u002Fdev\u002Fnull | grep -E \"^#\"\n\n# Fallback: directory name\nbasename \"$TARGET_PATH\"\n```\n\n### 2.2 Official Documentation\n\nSearch for official documentation and API references using WebSearch:\n\n| # | Search Query | Purpose |\n|---|-------------|---------|\n| 1 | `{product} documentation` | Main docs site |\n| 2 | `{product} API reference` | API surface |\n| 3 | `{product} getting started` | Setup and first use |\n| 4 | `{product} configuration reference` | Config keys, defaults |\n| 5 | `{product} CLI reference` | Commands, flags |\n\nRecord the documentation site URL and whether it appears comprehensive or sparse.\n\n### 2.3 Package Registry Entries\n\nSearch relevant package registries based on the languages detected in Phase 1:\n\n| Registry | URL Pattern |\n|----------|------------|\n| npm | `https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F{name}` |\n| PyPI | `https:\u002F\u002Fpypi.org\u002Fproject\u002F{name}` |\n| crates.io | `https:\u002F\u002Fcrates.io\u002Fcrates\u002F{name}` |\n| Maven Central | `https:\u002F\u002Fsearch.maven.org\u002Fartifact\u002F{group}\u002F{name}` |\n| NuGet | `https:\u002F\u002Fwww.nuget.org\u002Fpackages\u002F{name}` |\n| RubyGems | `https:\u002F\u002Frubygems.org\u002Fgems\u002F{name}` |\n| pkg.go.dev | `https:\u002F\u002Fpkg.go.dev\u002F{module-path}` |\n| Hex.pm | `https:\u002F\u002Fhex.pm\u002Fpackages\u002F{name}` |\n| Packagist | `https:\u002F\u002Fpackagist.org\u002Fpackages\u002F{vendor}\u002F{name}` |\n| pub.dev | `https:\u002F\u002Fpub.dev\u002Fpackages\u002F{name}` |\n\nRecord: registry URL, version, download count, last publish date.\n\n### 2.4 Community Content\n\n| # | Search Query | Purpose |\n|---|-------------|---------|\n| 1 | `{product} site:stackoverflow.com` | Community Q&A |\n| 2 | `{product} site:github.com issues` | Issue tracker |\n| 3 | `{product} tutorial` | Community tutorials |\n| 4 | `{product} blog` | Blog posts |\n\nFor discovery purposes, you do not need to deeply analyze this content. Record whether each category has substantial results (many hits) or sparse results (few or none). The `doc-researcher` and `community-analyst` agents will do deep extraction later.\n\n### 2.5 Third-Party Libraries and Plugins\n\n| # | Search Query | Purpose |\n|---|-------------|---------|\n| 1 | `{product} SDK` or `{product} client library` | Official\u002Fcommunity SDKs |\n| 2 | `{product} plugin` or `{product} extension` | Plugin ecosystem |\n| 3 | `{product} integration` | Third-party integrations |\n\nRecord: whether an SDK ecosystem exists, approximate size, which languages are covered.\n\n---\n\n## Phase 3: Service Detection\n\nDetermine whether the target is a running service or can be started as one.\n\n### 3.1 Port Scanning\n\nIf the target appears to be a server (presence of `server`, `listen`, `bind`, `port` in source or config):\n\n```bash\n# Check common development ports\nfor port in 80 443 3000 3001 4000 5000 5173 5432 6379 8000 8080 8443 8888 9090 27017; do\n  (echo >\u002Fdev\u002Ftcp\u002Flocalhost\u002F$port) 2>\u002Fdev\u002Fnull && echo \"Port $port: OPEN\"\ndone\n```\n\n### 3.2 Health Endpoints\n\nFor any open ports found, probe standard health endpoints:\n\n```bash\nfor port in $OPEN_PORTS; do\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002Fhealth\" 2>\u002Fdev\u002Fnull\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002Fhealthz\" 2>\u002Fdev\u002Fnull\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002Fapi\u002Fhealth\" 2>\u002Fdev\u002Fnull\n  curl -s -o \u002Fdev\u002Fnull -w \"%{http_code}\" \"http:\u002F\u002Flocalhost:$port\u002F\" 2>\u002Fdev\u002Fnull\ndone\n```\n\n### 3.3 Process Detection\n\n```bash\n# Check if the target is already running\nps aux | grep -i \"$(basename \"$TARGET_PATH\")\" | grep -v grep\n\n# Check for known server processes\nps aux | grep -E \"node|python|ruby|java|dotnet|go \" | grep -v grep | head -10\n```\n\n### 3.4 Container Runtime Availability\n\n```bash\n# Docker\ndocker info >\u002Fdev\u002Fnull 2>&1 && echo \"Docker: available\" || echo \"Docker: not available\"\ndocker ps 2>\u002Fdev\u002Fnull | grep -i \"$(basename \"$TARGET_PATH\")\" | head -5\n\n# Podman\npodman info >\u002Fdev\u002Fnull 2>&1 && echo \"Podman: available\" || echo \"Podman: not available\"\n\n# Docker Compose\ndocker compose version >\u002Fdev\u002Fnull 2>&1 && echo \"Docker Compose: available\" || echo \"Docker Compose: not available\"\n```\n\nRecord: container runtime available (docker\u002Fpodman\u002Fnone), existing containers related to the target, whether docker-compose.yml or similar exists.\n\n---\n\n## Phase 4: Derived Source Assessment\n\nAssess what additional intelligence sources can be created from what already exists.\n\n### 4.1 Minified Code Recovery\n\nIf Phase 1 found minified JavaScript bundles (few lines, many bytes per file):\n\n| Source | Derived Artifact | Method | Quality |\n|--------|-----------------|--------|---------|\n| Minified `.js` | Beautified source | `js-beautify` | Lossless formatting recovery |\n| `.js.map` source maps | Original source | Source map extraction | Near-original if maps are present |\n| Minified CSS | Beautified CSS | `css-beautify` | Lossless formatting recovery |\n\n```bash\n# Check for source maps\nfind \"$TARGET_PATH\" -name \"*.js.map\" -o -name \"*.css.map\" 2>\u002Fdev\u002Fnull | head -10\n\n# Check if JS files reference source maps\ngrep -rl \"sourceMappingURL\" \"$TARGET_PATH\" --include=\"*.js\" 2>\u002Fdev\u002Fnull | head -10\n```\n\n### 4.2 Binary Decompilation Potential\n\nBased on binaries found in Phase 1, assess decompilation feasibility:\n\n| Binary Type | Decompilation Quality | Tool Required |\n|-------------|----------------------|---------------|\n| JVM (`.jar`, `.class`) | Very high (near-source) | CFR, Procyon, FernFlower |\n| .NET (managed `.dll`) | Very high (near-source) | ILSpy (`ilspycmd`) |\n| Python (`.pyc`) | Very high (near-source) | uncompyle6, decompyle3 |\n| Electron (`.asar`) | Lossless (bundled source) | `npx asar extract` |\n| WebAssembly (`.wasm`) | Limited (WAT text format) | `wasm2wat` |\n| Native ELF\u002FMach-O\u002FPE | Low (disassembly only) | Ghidra, radare2 |\n\n### 4.3 Bundle Splitting Potential\n\nIf webpack, esbuild, rollup, or parcel bundles are detected:\n\n```bash\n# Detect bundler\nhead -50 \"$TARGET_PATH\"\u002Fdist\u002F*.js 2>\u002Fdev\u002Fnull | grep -oE \"webpack|esbuild|rollup|parcel\" | head -1\n\n# Check for multiple entry points\nfind \"$TARGET_PATH\" -path \"*\u002Fdist\u002F*\" -name \"*.js\" -not -name \"*.min.js\" 2>\u002Fdev\u002Fnull | wc -l\n```\n\n### 4.4 Database Schema Extraction\n\nIf database files or migration directories exist:\n\n```bash\n# SQL migrations\nfind \"$TARGET_PATH\" -type d -name \"migrations\" -o -name \"migrate\" 2>\u002Fdev\u002Fnull\nfind \"$TARGET_PATH\" -name \"*.sql\" 2>\u002Fdev\u002Fnull | head -10\n\n# ORM schema files\nfind \"$TARGET_PATH\" -name \"schema.prisma\" -o -name \"schema.rb\" 2>\u002Fdev\u002Fnull\nfind \"$TARGET_PATH\" -path \"*\u002Fmodels\u002F*.py\" -o -path \"*\u002Fentities\u002F*.ts\" 2>\u002Fdev\u002Fnull | head -10\n\n# SQLite databases\nfind \"$TARGET_PATH\" -name \"*.db\" -o -name \"*.sqlite\" -o -name \"*.sqlite3\" 2>\u002Fdev\u002Fnull | head -5\n```\n\n---\n\n## Inventory Manifest\n\nAfter all four phases complete, write the inventory to `workspace\u002Finventory.md`.\n\n### Format\n\n```markdown\n# Intelligence Source Inventory\n\n## Metadata\n- **Target:** {product name}\n- **Target path:** {absolute path}\n- **Discovery agent:** discovery-agent\n- **Date:** {ISO 8601}\n- **Phases completed:** 1, 2, 3, 4\n\n---\n\n## Source Code\n\n| Language | File Count | Location | Analytical Value |\n|----------|-----------|----------|-----------------|\n| TypeScript | 247 | src\u002F | PRIMARY — main application logic |\n| JavaScript | 34 | scripts\u002F, config\u002F | SUPPORTING — build and config |\n| ... | ... | ... | ... |\n\n## Binaries\n\n| Type | Count | Location | Decompilation Potential |\n|------|-------|----------|------------------------|\n| ... | ... | ... | ... |\n\n## Test Suites\n\n| Framework | Type | File Count | Location |\n|-----------|------|-----------|----------|\n| Jest | unit | 89 | __tests__\u002F |\n| Playwright | e2e | 12 | e2e\u002F |\n| ... | ... | ... | ... |\n\n## Documentation\n\n| Type | Location | Notes |\n|------|----------|-------|\n| README | .\u002FREADME.md | 450 lines, comprehensive |\n| API docs | docs\u002Fapi\u002F | Generated TypeDoc |\n| ... | ... | ... |\n\n## Configuration and Build\n\n| File | Purpose |\n|------|---------|\n| package.json | Node.js manifest, scripts, dependencies |\n| Dockerfile | Container build definition |\n| ... | ... |\n\n## Machine-Readable Contracts\n\n| Type | File | Notes |\n|------|------|-------|\n| OpenAPI 3.0 | api\u002Fopenapi.yaml | 2400 lines, comprehensive |\n| GraphQL schema | schema.graphql | 180 types |\n| ... | ... | ... |\n\n## Version Control\n\n| Property | Value |\n|----------|-------|\n| VCS | git |\n| Commits | 1,847 |\n| Branches | 12 |\n| Tags\u002Freleases | 34 |\n| Remote platform | GitHub |\n| Contributors | 8 |\n| History span | 2021-03-15 to 2024-11-20 |\n\n## Public Information (Web Search)\n\n| Category | Availability | Notes |\n|----------|-------------|-------|\n| Official docs | Yes — docs.example.com | Comprehensive API reference |\n| Package registry | npm — 45k weekly downloads | Active maintenance |\n| Community Q&A | ~120 Stack Overflow questions | Moderate community |\n| Tutorials | 8+ blog posts found | Several recent |\n| Third-party SDKs | 3 community libraries (Python, Go, Ruby) | Active ecosystem |\n| Plugins\u002Fextensions | VS Code extension, 2 CLI plugins | Small plugin ecosystem |\n\n## Running Services\n\n| Port | Service | Health |\n|------|---------|--------|\n| 3000 | Dev server | 200 OK at \u002Fhealth |\n| 5432 | PostgreSQL | Accepting connections |\n\n## Container Runtime\n\n| Runtime | Available | Target Containers |\n|---------|-----------|-------------------|\n| Docker | Yes | app (running), db (running) |\n| Docker Compose | Yes | docker-compose.yml with 3 services |\n\n## Derived Sources (Can Be Created)\n\n| Source | Method | Expected Quality |\n|--------|--------|-----------------|\n| Beautified dist\u002Fmain.js | js-beautify | Lossless formatting |\n| Source maps → original source | source map extraction | Near-original |\n| JVM class files → Java source | CFR decompiler | Very high |\n| SQL schema from migrations | Migration replay | Definitive |\n\n---\n\n## Summary\n\n- **Primary intelligence sources:** {list the most valuable sources}\n- **Secondary sources:** {supporting sources}\n- **Gaps:** {what is missing or unavailable}\n- **Recommended analysis modes:** {which modes should run based on what was found}\n```\n\nAdapt the tables to match what was actually found. Omit sections that have no entries (e.g., if there are no binaries, omit the Binaries table). Do not fabricate entries.\n\n---\n\n## User Negotiation\n\nAfter writing the inventory manifest, present it to the user and ask:\n\n> Here is what I found. The inventory is at `workspace\u002Finventory.md`.\n>\n> **Key findings:**\n> - {summary of most significant sources}\n> - {notable gaps or surprises}\n>\n> **Recommended analysis modes:** {modes}\n>\n> Two questions:\n> 1. **Is there anything else I should look at?** Other repositories, deployed instances, internal documentation, API keys for authenticated endpoints, etc.\n> 2. **Is anything off-limits?** Files, directories, or services I should NOT analyze (proprietary dependencies, third-party code you don't own, production databases, etc.).\n\nWait for the user's response. Update `workspace\u002Finventory.md` with any additions or exclusions they provide. Mark excluded items clearly:\n\n```markdown\n## Exclusions (User-Specified)\n\n| Item | Reason |\n|------|--------|\n| vendor\u002F | Third-party code, not owned |\n| .env | Contains production secrets |\n```\n\n---\n\n## Dispatch Mapping\n\nAfter the inventory is finalized (including user feedback), write a dispatch mapping table to the end of `workspace\u002Finventory.md`. This table tells the orchestrator which agent roles and skills to assign to each source type.\n\n```markdown\n## Dispatch Mapping\n\n| Source Type | Agent Role | Skill | Priority | Input Path |\n|-------------|-----------|-------|----------|------------|\n| Source code (structured) | chunk-analyzer, function-analyzer | source-analysis | P0 | src\u002F |\n| Source code (bundled\u002Fminified) | bundle-splitter → chunk-analyzer → function-analyzer | source-analysis | P0 | dist\u002F |\n| Official documentation | doc-researcher | doc-research | P0 | (web) docs.example.com |\n| Community content | community-analyst | community-intelligence | P1 | (web) search results |\n| SDK ecosystem | sdk-analyzer, integration-test-miner | ecosystem-analysis | P1 | (web) npm\u002FPyPI\u002FGitHub |\n| Test suites | chunk-analyzer | source-analysis | P0 | __tests__\u002F, e2e\u002F |\n| Runtime (CLI) | cli-explorer | runtime-observation | P1 | container |\n| Runtime (Web UI) | web-ui-explorer | runtime-observation | P1 | container |\n| Runtime (Behavior) | behavior-observer | runtime-observation | P2 | container |\n| Binaries (managed) | binary-surveyor → source-analysis handoff | binary-analysis | P2 | lib\u002F*.jar |\n| Binaries (native) | binary-surveyor, binary-deep-analyzer | binary-analysis | P3 | bin\u002F |\n| OpenAPI spec | doc-researcher | doc-research | P0 | api\u002Fopenapi.yaml |\n| GraphQL schema | doc-researcher | doc-research | P0 | schema.graphql |\n| Protobuf definitions | doc-researcher | doc-research | P1 | proto\u002F |\n| Derived: beautified bundles | bundle-splitter | source-analysis | P0 | (created from dist\u002F) |\n| Derived: decompiled binaries | binary-surveyor → source-analysis | binary-analysis | P2 | (created from binaries) |\n```\n\nAdapt this table to the actual sources found. Only include rows for source types that exist in the inventory. Priority levels:\n\n- **P0** — Primary intelligence sources. Analysis cannot proceed without these.\n- **P1** — High-value supplementary sources. Significantly improve coverage and confidence.\n- **P2** — Useful corroborating sources. Fill gaps and confirm claims from P0\u002FP1 sources.\n- **P3** — Low-yield sources. Only analyze if time permits and other sources leave gaps.\n\n---\n\n## Output Structure\n\n```\nworkspace\u002F\n└── inventory.md          # Complete inventory manifest with dispatch mapping\n```\n\nThe inventory is a single file. It is the first artifact written to the workspace and drives all subsequent agent dispatch decisions.\n\n## Rules\n\n1. **Scan before you search.** Phase 1 (local filesystem) always runs before Phase 2 (web search). Local files are the ground truth about what exists.\n2. **Do not analyze, only catalog.** Discovery identifies sources; it does not read or interpret them. That is the job of downstream analysis agents.\n3. **Record absence as well as presence.** If there are no tests, no docs, no binaries — say so explicitly. Gaps in the inventory are as important as entries.\n4. **Respect user boundaries.** If the user marks something off-limits, exclude it from the inventory and ensure no downstream agent touches it.\n5. **Be concrete.** File counts, directory paths, port numbers, URLs. Vague inventories produce vague analysis plans.\n6. **One pass, not exhaustive.** Discovery is a survey, not a deep audit. Spend minutes, not hours. Downstream agents will do the exhaustive reading.\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe-backstory\u002Fskills\u002Fautonomous-discovery",1,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe","https:\u002F\u002Fgithub.com\u002Fzak-keown","2026-09-05 06:29:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zak-keown\u002Fmoe --skill autonomous-discovery",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill autonomous-discovery",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill autonomous-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-backstory\u002Fskills\u002Fautonomous-discovery\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M7C1Z5362Y8NVRZ69HWP0ZD0","write-skill","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7C1YZ9966WK9R6ZRPCGWF3G","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7C1YMR4SJD7BPBBPXZCVGVH","write-clearly","Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-clearly\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7C1YH9805YSM0N20VQAVSXF","windows-vm","Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwindows-vm\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7C1YD87SCNEJ2C9B8HFR2NQ","verify-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7C1YARDEHT0TJ9BRG30ZCF4","using-moe","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fusing-moe\u002FSKILL.md",[],[]]