[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EP46DF3WMP80Z72Q7VHYJR":3,"skill-same:01M7EP46DF3WMP80Z72Q7VHYJR":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7EP46DF3WMP80Z72Q7VHYJR","observal",null,"Route repository work for Observal, an AI agent registry and observability platform with Python CLI, FastAPI server, harness telemetry, and Vite web UI.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: observal\ndescription: \"Route repository work for Observal, an AI agent registry and\n  observability platform with Python CLI, FastAPI server, harness telemetry, and\n  Vite web UI.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# Observal Repo Skill\n\nUse this skill when working in or reasoning about the Observal repository: the `observal` CLI, registry\u002Fagent component workflows, FastAPI backend, harness adapters and telemetry, session traces, web UI, self-hosting\u002Fdeveloper operations, tests, or contribution policy.\n\nObserval is a monorepo for an agent-centric registry and observability platform. Its primary product surfaces are:\n\n- Python CLI (`observal`) for auth, scan, doctor, registry components, agents, teams, ops\u002Fadmin, server lifecycle, reconciliation, and support bundles.\n- FastAPI server for registry APIs, auth\u002FSSO\u002FSCIM, telemetry ingest, ClickHouse\u002FPostgres storage, insights, admin\u002Freview, teams, inbox, and GraphQL.\n- Vite\u002FReact\u002FTanStack Router web UI for registry browsing, traces, admin dashboards, settings, insights, teams, and account flows.\n- Shared harness registry\u002Fadapters for Claude Code, Kiro, Cursor, Pi, Codex, Copilot, OpenCode, Antigravity, and Goose.\n\n## First read\n\n- For repo freshness and evidence baseline, read [repo provenance](references\u002Frepo-provenance.md).\n- For a compact architecture map, read [overview](references\u002Foverview.md).\n- For install\u002Ftest commands and optional heavy checks, read [quick commands](references\u002Fquick-commands.md).\n- For cross-cutting failure triage, read [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Route by task\n\n| User task | Use |\n| --- | --- |\n| Add, rename, test, or operate a Typer command; keep JSON\u002Ftable\u002Ferror contracts and bundled skills in sync | [cli](sub-skills\u002Fcli\u002FSKILL.md) |\n| Change REST\u002FGraphQL routes, schemas, models, services, auth, insights, jobs, migrations, dynamic settings, or backend tests | [server](sub-skills\u002Fserver\u002FSKILL.md) |\n| Add\u002Fpromote\u002Fdebug a harness, scan\u002Fdoctor\u002Flayer behavior, hook specs, session push\u002Freconcile, session parsers, telemetry ingest, or model catalog coverage | [harness-telemetry](sub-skills\u002Fharness-telemetry\u002FSKILL.md) |\n| Modify Vite\u002FReact routes, pages, components, query hooks, auth storage, UI types, theme tokens, Playwright specs, or screenshots | [web](sub-skills\u002Fweb\u002FSKILL.md) |\n| Choose setup\u002Flint\u002Ftest\u002Frelease\u002Fcompliance scripts, docs\u002Fchangelog obligations, SPDX\u002Fpre-commit policy, AI contribution disclosure, or PR readiness checks | [repo-development](sub-skills\u002Frepo-development\u002FSKILL.md) |\n\nWhen a task crosses layers, start with the implementation owner, then return to `repo-development` for broad tests, docs, changelog, screenshots, and contributor-policy checks.\n\n## Minimal setup and smoke checks\n\nFor CLI users, install the released tool with one of:\n\n```bash\nuv tool install observal-cli\npipx install observal-cli\n```\n\nFor source work inside a checkout, the repo documents Python 3.11+, uv, Node\u002Fpnpm, and Docker for the optional stack. A fast local source smoke is:\n\n```bash\nuv tool install --editable .\nobserval --version\nobserval --help\n```\n\nFor server-aware unit tests, the native pattern runs from the server directory while pointing pytest at root tests. The default Make target wraps this:\n\n```bash\nmake test\nmake lint\n```\n\nDo not run Docker Compose or Playwright E2E by default. Use them only for live stack, browser, or Kiro-specific coverage and state that requirement in the handoff.\n\n## Bundled helper checks\n\nThese helpers are copied into the skill so future agents can check contracts without reopening the source docs:\n\n```bash\npython scripts\u002Fcheck_observal_skill_tree.py --skill-root skills\u002Fdisco\u002Fobserval --pretty\npython sub-skills\u002Fcli\u002Fscripts\u002Fcheck_cli_contract.py --repo-root . --pretty\npython sub-skills\u002Fserver\u002Fscripts\u002Fcheck_server_routes.py --server-path . --pretty\npython sub-skills\u002Fharness-telemetry\u002Fscripts\u002Fcheck_harness_registry.py --repo-root . --pretty\npython sub-skills\u002Fweb\u002Fscripts\u002Fcheck_web_contract.py --repo-root .\npython sub-skills\u002Frepo-development\u002Fscripts\u002Finspect_observal_repo.py --repo-root . --pretty\n```\n\nExpected signals: valid skill frontmatter, known CLI groups, server route registry import, ten registered harnesses with parser coverage, frontend contract markers, and repository markers\u002Ftest counts.\n\n## Operating invariants\n\n- No telemetry wrappers or OTLP environment variables: harness telemetry flows through session push hooks and reconciliation.\n- Harness-specific behavior belongs in adapters and shared registry entries, not orchestrator if\u002Felif chains.\n- CLI command changes must update CLI docs and bundled skills; run the sync command before handoff.\n- ClickHouse schema changes live in ClickHouse SQL migrations; Alembic is for Postgres only.\n- Frontend harness data comes from the server; do not hardcode harness lists in React.\n- Log with Loguru positional placeholders and never log secrets, tokens, JWT payloads, keys, or credential values.\n- Tests mock external services by default; E2E specs are the exception and require a running stack.\n- Keep AI-assisted contribution claims explainable and human-reviewed; autonomous PR submission is out of scope.\n","# Observal Repo Skill\n\nUse this skill when working in or reasoning about the Observal repository: the `observal` CLI, registry\u002Fagent component workflows, FastAPI backend, harness adapters and telemetry, session traces, web UI, self-hosting\u002Fdeveloper operations, tests, or contribution policy.\n\nObserval is a monorepo for an agent-centric registry and observability platform. Its primary product surfaces are:\n\n- Python CLI (`observal`) for auth, scan, doctor, registry components, agents, teams, ops\u002Fadmin, server lifecycle, reconciliation, and support bundles.\n- FastAPI server for registry APIs, auth\u002FSSO\u002FSCIM, telemetry ingest, ClickHouse\u002FPostgres storage, insights, admin\u002Freview, teams, inbox, and GraphQL.\n- Vite\u002FReact\u002FTanStack Router web UI for registry browsing, traces, admin dashboards, settings, insights, teams, and account flows.\n- Shared harness registry\u002Fadapters for Claude Code, Kiro, Cursor, Pi, Codex, Copilot, OpenCode, Antigravity, and Goose.\n\n## First read\n\n- For repo freshness and evidence baseline, read [repo provenance](references\u002Frepo-provenance.md).\n- For a compact architecture map, read [overview](references\u002Foverview.md).\n- For install\u002Ftest commands and optional heavy checks, read [quick commands](references\u002Fquick-commands.md).\n- For cross-cutting failure triage, read [troubleshooting](references\u002Ftroubleshooting.md).\n\n## Route by task\n\n| User task | Use |\n| --- | --- |\n| Add, rename, test, or operate a Typer command; keep JSON\u002Ftable\u002Ferror contracts and bundled skills in sync | [cli](sub-skills\u002Fcli\u002FSKILL.md) |\n| Change REST\u002FGraphQL routes, schemas, models, services, auth, insights, jobs, migrations, dynamic settings, or backend tests | [server](sub-skills\u002Fserver\u002FSKILL.md) |\n| Add\u002Fpromote\u002Fdebug a harness, scan\u002Fdoctor\u002Flayer behavior, hook specs, session push\u002Freconcile, session parsers, telemetry ingest, or model catalog coverage | [harness-telemetry](sub-skills\u002Fharness-telemetry\u002FSKILL.md) |\n| Modify Vite\u002FReact routes, pages, components, query hooks, auth storage, UI types, theme tokens, Playwright specs, or screenshots | [web](sub-skills\u002Fweb\u002FSKILL.md) |\n| Choose setup\u002Flint\u002Ftest\u002Frelease\u002Fcompliance scripts, docs\u002Fchangelog obligations, SPDX\u002Fpre-commit policy, AI contribution disclosure, or PR readiness checks | [repo-development](sub-skills\u002Frepo-development\u002FSKILL.md) |\n\nWhen a task crosses layers, start with the implementation owner, then return to `repo-development` for broad tests, docs, changelog, screenshots, and contributor-policy checks.\n\n## Minimal setup and smoke checks\n\nFor CLI users, install the released tool with one of:\n\n```bash\nuv tool install observal-cli\npipx install observal-cli\n```\n\nFor source work inside a checkout, the repo documents Python 3.11+, uv, Node\u002Fpnpm, and Docker for the optional stack. A fast local source smoke is:\n\n```bash\nuv tool install --editable .\nobserval --version\nobserval --help\n```\n\nFor server-aware unit tests, the native pattern runs from the server directory while pointing pytest at root tests. The default Make target wraps this:\n\n```bash\nmake test\nmake lint\n```\n\nDo not run Docker Compose or Playwright E2E by default. Use them only for live stack, browser, or Kiro-specific coverage and state that requirement in the handoff.\n\n## Bundled helper checks\n\nThese helpers are copied into the skill so future agents can check contracts without reopening the source docs:\n\n```bash\npython scripts\u002Fcheck_observal_skill_tree.py --skill-root skills\u002Fdisco\u002Fobserval --pretty\npython sub-skills\u002Fcli\u002Fscripts\u002Fcheck_cli_contract.py --repo-root . --pretty\npython sub-skills\u002Fserver\u002Fscripts\u002Fcheck_server_routes.py --server-path . --pretty\npython sub-skills\u002Fharness-telemetry\u002Fscripts\u002Fcheck_harness_registry.py --repo-root . --pretty\npython sub-skills\u002Fweb\u002Fscripts\u002Fcheck_web_contract.py --repo-root .\npython sub-skills\u002Frepo-development\u002Fscripts\u002Finspect_observal_repo.py --repo-root . --pretty\n```\n\nExpected signals: valid skill frontmatter, known CLI groups, server route registry import, ten registered harnesses with parser coverage, frontend contract markers, and repository markers\u002Ftest counts.\n\n## Operating invariants\n\n- No telemetry wrappers or OTLP environment variables: harness telemetry flows through session push hooks and reconciliation.\n- Harness-specific behavior belongs in adapters and shared registry entries, not orchestrator if\u002Felif chains.\n- CLI command changes must update CLI docs and bundled skills; run the sync command before handoff.\n- ClickHouse schema changes live in ClickHouse SQL migrations; Alembic is for Postgres only.\n- Frontend harness data comes from the server; do not hardcode harness lists in React.\n- Log with Loguru positional placeholders and never log secrets, tokens, JWT payloads, keys, or credential values.\n- Tests mock external services by default; E2E specs are the exception and require a running stack.\n- Keep AI-assisted contribution claims explainable and human-reviewed; autonomous PR submission is out of scope.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fobserval",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill observal",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill observal",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill observal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002FSKILL.md",[49,55,59,63,67],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Foverview.md","REFERENCE","参考文档",4008,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Freferences\u002Foverview.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fquick-commands.md",3271,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Freferences\u002Fquick-commands.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Frepo-provenance.md",2398,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Freferences\u002Frepo-provenance.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Frepo-routing-metadata.json",488,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Freferences\u002Frepo-routing-metadata.json",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Ftroubleshooting.md",4945,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fobserval\u002Freferences\u002Ftroubleshooting.md",[72,81,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":82,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":80},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":80},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":80},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":80},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":80},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]