[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CAS4XASEN59NPYPFA6RZ2P":3,"skill-same:01M6CAS4XASEN59NPYPFA6RZ2P":97},{"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":23,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":64},"01M6CAS4XASEN59NPYPFA6RZ2P","aiwg-language-map",null,"AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs","jmagly\u002Faiwg","jmagly","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1159087?v=4","01M6C10AK8N2WCSQN11FYGTJWN","Joseph Magly","01M6C10AQ8A2RMED1Y1BSVY7NF",229,"MIT","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-language-map\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32],"aiwg language map","language","map","framework","discover","bundle","categories","true","extensions","2026-11-10 10:12:30",false,"---\nname: aiwg-language-map\nnamespace: aiwg\nplatforms: [all]\nkernel: true\ndescription: AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs\n---\n\n# AIWG Language Map — Addons + Extensions\n\nThis is your always-loaded directory for the AIWG **addon and extension** surface. It's the orientation layer for the ~214 skills that live outside the 8 frameworks. Frameworks have their own per-framework quickrefs (`sdlc-quickref`, `forensics-quickref`, etc.); this map covers everything else: addons (utilities, loops, voice, testing, etc.) and ops extensions (sys\u002Fnet\u002Fsec\u002Fdev\u002Fit\u002Fstream).\n\n## How to use this map\n\n1. Identify which **capability domain** below the user's need belongs to\n2. Pick a **curated phrase** from that domain\n3. Run `aiwg discover \"\u003Cphrase>\"` and surface the top match (or top-3) to the user\n4. Fetch the body with `aiwg show skill \u003Cname> --body` — never `find` \u002F `ls` \u002F `Read` on storage paths\n\nIf a phrase doesn't fit the user's exact need, paraphrase. `aiwg discover` is forgiving with natural language.\n\n**The discover→show pattern is mandatory.** See `aiwg-utils-quickref` for the canonical pipeline and `skill-discovery` HIGH rule for enforcement.\n\n## Map layout\n\nThe map has two sections:\n\n- **Addon capability domains** — user-need clusters (memory, loops, voice, etc.) routed to addons\n- **Extension domains** — operational scopes (sys, net, sec, etc.) for `ops-complete`\n\nEach section opens with an explicit `aiwg discover \"\u003Cphrase>\"` example. Table rows underneath show **bare phrases** — pass them straight to `aiwg discover` (the verb is implied by the section header). Phrases have been verified against the index; each surfaces the listed bundle in the top results.\n\n---\n\n## Addon capability domains\n\n### Dataset intelligence, indexing & provenance\n\nWhen a user points AIWG at files, an API, a corpus, or another dataset and asks\nfor search, indexing, traceability, provenance, lineage, synchronization, or\nsafe retirement—even when they do not know those terms.\n\nExample: `aiwg discover \"make this searchable\"`. Phrases below pass straight to\n`aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Start from only a source and outcome | `use this data` | dataset-intelligence |\n| Recommend custom indexing safely | `make this searchable` | dataset-intelligence |\n| Add evidence-bearing traceability | `trace this dataset` | dataset-intelligence |\n| Explain record or field lineage | `where did this record come from` | dataset-intelligence |\n| Verify freshness and provenance | `verify this dataset` | dataset-intelligence |\n| Resume an incremental source | `sync this source` | dataset-intelligence |\n| Retire data and derived artifacts safely | `retire this dataset` | dataset-intelligence |\n\nThe same governed intake and handoff envelopes serve SDLC, research,\nknowledge-base, media, marketing, ops, and project-local bundles. All execution\ndelegates to `aiwg dataset`; the addon does not create a shadow runtime.\n\n### Schemas & data contracts\n\nWhen the user describes a record, configuration file, event, API payload,\nmessage, import\u002Fexport, or other structured data—even when they do not know to\nask for a schema.\n\nExample: `aiwg discover \"define data shape\"`. Phrases below pass straight to\n`aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Decide whether structured data needs a contract | `define data shape` | schema-governance |\n| Explain schemas and continue examples-first | `why do I need a schema` | schema-governance |\n| Author and register a canonical schema | `create a schema` | schema-governance |\n| Evolve an existing contract safely | `change an existing schema` | schema-governance |\n| Review correctness and readiness | `review a data contract` | schema-governance |\n\nThe SDLC discovery track invokes this addon automatically for persistent or\nexchanged data. Users should describe the data need; they need not choose a\ndialect, identifier, lifecycle, or compatibility policy themselves.\n\n### Loops & iteration\n\nWhen the user needs an iterative coding loop, recursive context decomposition, eval gates, or guided autonomous implementation.\n\nExample: `aiwg discover \"ralph loop\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Iterative AI coding loop (Ralph) | `ralph loop` | agent-loop |\n| Loop status \u002F abort \u002F resume \u002F attach | `ralph attach` (or `ralph abort` \u002F `ralph resume` \u002F `ralph status`) | agent-loop |\n| External crash-resilient loop variant | `ralph external loop` | agent-loop |\n| Recursive decomposition of a huge corpus | `rlm query` | rlm |\n| RLM batch processing with parallel sub-agents | `rlm batch fan-out` | rlm |\n| Bounded autonomous issue-to-code | `guided implementation` | guided-implementation |\n| Inner generator\u002Fcritic eval loop in a pipeline | `eval loop` | nlp-prod |\n| KAMI-based agent quality eval framework | `agent quality eval` | aiwg-evals |\n\n### Session history and exploration\n\nUse `aiwg discover \"spelunk session data\"` to find catalog exploration. Useful\nphrases include `search past conversations`, `trace session tool calls`,\n`compare provider sessions`, and `harvest session decisions`. `session-explore`\nhandles search, timelines, analytics, citations and coverage; `session-harvest`\nhandles candidate review and promotion. `session-analyst` and the\n`session-investigation` flow compose bounded evidence collection and synthesis.\nThe singular `session` launcher and cost-history telemetry serve different needs.\n\n### Memory & state\n\nWhen the user needs persistent agent memory, semantic ingestion, or context curation.\n\nExample: `aiwg discover \"memory ingest\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Semantic memory ingest | `memory ingest` | semantic-memory |\n| Lint memory entries | `semantic memory lint` | semantic-memory |\n| Capture \u002F query memory | `memory query` | semantic-memory |\n| Filter context to remove distractors | `filter distractors from context` | context-curator |\n\n> `llm-wiki` has a first-class discoverable driver for profile selection and\n> activation; its topology composes with the knowledge-base framework and\n> semantic-memory drivers. `auto-memory` remains a template bundle pending its\n> own operational driver.\n\n### Voice & writing quality\n\nWhen the user is producing or reviewing prose and needs voice consistency, AI-pattern detection, or related text quality work.\n\nExample: `aiwg discover \"apply voice profile\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Apply a voice profile to existing content | `apply voice profile` | voice-framework |\n| Create a new voice profile | `create voice profile` | voice-framework |\n| Blend two voices | `blend voice profiles` | voice-framework |\n| Analyze content's current voice | `analyze voice` | voice-framework |\n| Detect AI-pattern artifacts in writing | `ai pattern detection` | writing-quality |\n| Improve output diversity (verbalized sampling) | `verbalized sampling` | verbalized-sampling |\n\n### NLP & inference pipelines\n\nWhen the user is building or optimizing LLM inference systems.\n\nExample: `aiwg discover \"pipeline architect\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| LLM inference pipeline architecture | `pipeline architect` | nlp-prod |\n| Pipeline pattern selection | `pipeline pattern` | nlp-prod |\n| Cost optimizer for LLM workloads | `llm cost optimizer` | nlp-prod |\n| Eval-loop generator\u002Fcritic | `eval loop` | nlp-prod |\n| Productionize an inference pipeline | `pipeline productionize` | nlp-prod |\n| Prompt engineering | `prompt engineer` | nlp-prod |\n| Agentic or bounded classification | `agentic classification` | decision-engine (opt-in) |\n| Jev decision engine | `Jev decision engine` | decision-engine (opt-in) |\n| Reduce frontier tokens with bounded decisions | `classify to reduce frontier tokens` | decision-engine (opt-in) |\n| Offload a yes\u002Fno, pick-one, or 1-N decision to Jev | `offload decisions to jev` | decision-engine (opt-in) |\n| Set up Jev with a token | `set up jev` | decision-engine (opt-in) |\n| Questions sharing authorized state | `shared-state batching` | decision-engine (opt-in) |\n| Offline decision fixtures and readiness plans | `decision playground` | decision-engine (opt-in) |\n\n`decision-engine` requires explicit installation: `aiwg use decision-engine`.\nIt is excluded from bulk installs. Discover `decision-offload` for\nsingle-question offload via `aiwg decision ask` (enabled by\n`aiwg decision setup jev`); discover `decision-evaluate` for pinned\nclassification requests; evaluation requires `AIWG_DECISION_ENABLED=1` plus\nan explicit backend binding and approved projection for live egress. Library\nbatching also needs host policies; discovering the skill does not enable it.\nDiscover `decision-playground` to list and run offline recorded fixtures without\ncredentials or inference. Its `live-plan` command only reports readiness; live\nevaluation requires the separate explicit opt-in and host configuration.\nThese phrases use deterministic discovery and require no model inference.\n\n### Documentation intelligence\n\nWhen the user is scraping, extracting, or analyzing documentation as a corpus.\n\nExample: `aiwg discover \"doc analyst\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Coordinate doc analysis (master orchestrator) | `doc analyst` | doc-intelligence |\n| Scrape documentation sites | `doc scraper` | doc-intelligence |\n| Extract from PDFs | `pdf extractor` | doc-intelligence |\n| Run an OpenProse program | `prose run` | prose-integration |\n| Validate \u002F parse a Prose program | `prose validate` | prose-integration |\n\n### Testing & quality\n\nWhen the user needs test enforcement, UAT, or quality automation.\n\nExample: `aiwg discover \"tdd enforce\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| TDD enforcement \u002F test gates | `tdd enforce` | testing-quality |\n| Mutation testing analyst | `mutation analyst` | sdlc-complete (agent) |\n| Mutation test runner | `mutation test` | testing-quality |\n| UAT plan generation via MCP | `uat plan` | uat-mcp |\n| UAT execution via MCP | `uat execute` | uat-mcp |\n\n### Skill \u002F extension authoring\n\nWhen the user is building new AIWG content (skills, addons, framework changes).\n\nExample: `aiwg discover \"skill architect\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| End-to-end skill creation orchestrator | `skill architect` | skill-factory |\n| Build a skill | `skill builder` | skill-factory |\n| Enhance \u002F validate \u002F package a skill | `skill packager` | skill-factory |\n| Validate an AIWG addon | `validate addon` | aiwg-dev |\n| Validate a framework component | `validate component` | aiwg-dev |\n| AIWG devkit build helpers | `devkit build` | aiwg-dev |\n| Link-check across docs | `link check` | aiwg-dev |\n\n### Color & UX\n\nWhen the user needs color theory or palette tooling.\n\nExample: `aiwg discover \"color palette\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Generate or review a color palette | `color palette` | color-palette |\n| Color theory fundamentals reference | `color theory` | color-palette |\n| Accessibility \u002F contrast review | `color accessibility` | color-palette |\n\n### Daemon & background work\n\nWhen the user needs persistent sessions or background orchestration.\n\nExample: `aiwg discover \"daemon init\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Concierge daemon entry \u002F init | `daemon init` | aiwg-utils |\n| Concierge agent (front-of-house) | `concierge daemon` | daemon |\n| Mission Control (background mission orchestrator) | `mc dispatch` | agent-loop |\n| Star-prompt for repo recommendations | `star prompt` | star-prompt |\n\n### Setup & installer\n\nWhen the user is bootstrapping a project or installing AIWG itself.\n\nExample: `aiwg discover \"setup manifest generate\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Generate a reproducible installer manifest | `setup manifest generate` | agentic-installer |\n| Validate \u002F run a setup manifest | `setup manifest validate run` | agentic-installer |\n\n### Hooks & integration\n\nWhen the user needs platform-level lifecycle hooks, HITL gates, or external bridges.\n\nExample: `aiwg discover \"hitl patterns\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| HITL gate patterns (rule) | `hitl patterns` | sdlc-complete (rule) |\n| HITL gates (rule, ensemble review) | `hitl gates` | sdlc-complete (rule) |\n| Factory AI compat agent | `factory compat` | sdlc-complete (agent) |\n\n> `aiwg-hooks`, `agent-persistence`, and `droid-bridge` now expose\n> discoverable activation drivers. Their low-level hooks, HITL gates, and MCP\n> server remain implementation artifacts reached through those drivers.\n\n### Core meta-utilities\n\nFor everything else AIWG-internal — context regeneration, workspace management, index\u002Fquery, validation, and project-status surfaces — see `aiwg-utils-quickref`. It's already loaded; this map points back at it.\n\n---\n\n## Extension domains (ops-complete)\n\nOperational extensions live under `agentic\u002Fcode\u002Fextensions\u002F\u003Cdomain>\u002F` and extend `ops-complete`. They carry both skills AND rules. The framework-level `ops-quickref` lists the high-level extension model; this section gives you direct phrases.\n\nEach block opens with one explicit `aiwg discover` example; remaining phrases are bare — pass straight to `aiwg discover`.\n\n### sys — per-host operations\n\nHardware, OS, boot chains, fleet host documentation, immutable bases, hardware safety procedures.\n\n```\naiwg discover \"sys host profile\"   # → sys-host-profiler agent (1.00)\nsys host audit                     # → sys-host-audit skill\nluks tpm dual phase                # → sec-luks-dual-phase rule (sys+sec border)\nsys host independence              # → sys-host-independence rule\n```\n\n### net — network operations\n\nVLANs, DNS, firewalls, Cloudflare tunnels, UniFi config, network state authority, cert expiry gates, tunnel safety.\n\n```\naiwg discover \"vlan audit\"   # → net-vlan-audit (1.00)\nnet dns check                # → net-dns-check skill\nnet change blast radius      # → net-change-blast-radius rule\ntunnel safety                # → net-tunnel-safety rule\nnet state authority          # → net-state-authority rule\n```\n\n### sec — security operations\n\nPKI, LUKS, TPM2, YubiKey, SSH CA, access auditing, cert expiry gates, key material handling.\n\n```\naiwg discover \"sec cert scan\"   # → sec-cert-scan\nsec access snapshot             # → sec-access-snapshot\nsec access audit frequency      # → sec-access-audit-frequency rule\nsec cert expiry gate            # → sec-cert-expiry-gates rule\nkey material handling           # → sec-key-material-handling rule\nsec luks dual phase             # → sec-luks-dual-phase rule\n```\n\n### dev — CI\u002FCD and build automation\n\nPipeline safety, idempotent builds, secret hygiene, self-contained CI builders.\n\n```\naiwg discover \"pipeline safety ci\"   # → dev-pipeline-safety rule\nidempotent build                     # → dev-idempotent-builds rule\nci secret hygiene                    # → dev-secret-hygiene rule\nself contained ci builder            # → dev-ci-self-contained rule\n```\n\n### it — IT ops, CMDB, asset management\n\nAsset registry, service deployments, disaster recovery, change control, asset authority, DR validation.\n\n```\naiwg discover \"it asset sync\"   # → it-asset-sync skill (0.81)\nit asset authority              # → it-asset-authority rule\nit service health               # → it-service-health rule\nit dr validation                # → it-dr-validation rule\nit change control               # → it-change-control rule\n```\n\n### stream — streaming media operations\n\nTranscoders, restreaming, platform integrations, stream pipeline gates.\n\n```\naiwg discover \"stream deploy\"   # → stream-deploy skill\nstream pipeline gates           # → stream-pipeline-gates rule\nstream safety                   # → stream-safety rule\n```\n\n### api-adapter — external API integrations\n\nReserved for external API adapter scaffolding. Currently a placeholder bundle with no skills or rules; phrases will appear as adapters are added.\n\n---\n\n## Categories at a glance (cheat sheet)\n\nWhen you don't know which domain a need falls into:\n\n| If the user mentions... | Look in... |\n|---|---|\n| \"loop\", \"iterate\", \"ralph\", \"recursive\", \"decompose huge file\" | Loops & iteration |\n| \"remember\", \"memory\", \"context\", \"wiki\", \"ingest\" | Memory & state |\n| \"voice\", \"writing style\", \"AI pattern\", \"diversity\", \"samples\" | Voice & writing quality |\n| \"inference\", \"pipeline cost\", \"model selection\" | NLP & inference pipelines |\n| \"documentation scrape\", \"extract from PDF\", \"Prose program\" | Documentation intelligence |\n| \"test enforcement\", \"TDD\", \"UAT\", \"MCP test\" | Testing & quality |\n| \"build a skill\", \"scaffold addon\", \"framework dev\" | Skill \u002F extension authoring |\n| \"color\", \"palette\", \"contrast\", \"WCAG\" | Color & UX |\n| \"daemon\", \"background mission\", \"mission control\" | Daemon & background work |\n| \"installer\", \"setup manifest\", \"bootstrap\" | Setup & installer |\n| \"hooks\", \"permissions\", \"session\", \"droid\", \"HITL\" | Hooks & integration |\n| \"host\", \"BIOS\", \"boot chain\", \"OS install\" | Extensions \u002F sys |\n| \"VLAN\", \"DNS\", \"firewall\", \"tunnel\" | Extensions \u002F net |\n| \"cert\", \"LUKS\", \"YubiKey\", \"PKI\", \"access audit\" | Extensions \u002F sec |\n| \"CI\", \"pipeline\", \"build\", \"secret in workflow\" | Extensions \u002F dev |\n| \"CMDB\", \"asset\", \"DR\", \"service deploy\", \"change control\" | Extensions \u002F it |\n| \"transcoder\", \"restream\", \"live broadcast\" | Extensions \u002F stream |\n\n---\n\n## Project-local extensions (pilot → promote)\n\nAddons, extensions, and frameworks don't all have to come from upstream. Users can pilot content bundles per-project under `.aiwg\u002F{extensions,addons,frameworks}\u002F\u003Cname>\u002F`, validate them, then promote to upstream when mature. Use `.aiwg\u002Fplugins\u002F\u003Cname>\u002F` only when wrapping a bundle for marketplace delivery. Curated phrases:\n\n```bash\naiwg new-bundle \u003Cname>                         # scaffold; auto-builds project graph\naiwg new-extension \u003Cname> --starter rule       # extension with starter rule\naiwg new-addon \u003Cname>                          # addon\naiwg new-framework \u003Cname>                      # framework\naiwg new-plugin \u003Cname>                         # marketplace delivery wrapper\naiwg new-bundle \u003Cname> --dry-run               # preview without writing\naiwg list --project-local                      # inventory + validation status\naiwg doctor --project-local                    # health check (counts, drift, shadows)\naiwg use \u003Cname>                                # deploy single project-local bundle\naiwg promote \u003Cname>                            # graduate to upstream (hash-verified)\naiwg promote \u003Cname> --to corpus \u003Cpath>         # promote to private corpus instead\naiwg promote \u003Cname> --dry-run                  # preview promotion\n```\n\nAfter scaffolding, the bundle is immediately discoverable via `aiwg discover \"\u003Cname>\"` — the project graph is rebuilt automatically. No manual `aiwg index build --graph project` step needed.\n\n## When this map doesn't have a phrase that fits\n\n**Don't enumerate from memory.** Run `aiwg discover` with the user's natural-language phrasing — the index is forgiving. If you get zero results, try:\n\n1. A broader phrase (e.g., drop a noun)\n2. A different vocabulary (e.g., \"deploy\" vs \"publish\" vs \"release\")\n3. `aiwg index stats --graph framework` to confirm the index is built and populated\n4. Check whether the bundle is even installed via `aiwg list`\n5. If the workspace has project-local bundles, also check `aiwg index stats --graph project`\n\nIf after that the capability genuinely doesn't exist, you can tell the user honestly — but only after the search ran and came up empty. The `skill-discovery` HIGH rule mandates the search before declining.\n\n## See also\n\n- `aiwg-utils-quickref` — core meta-utility surface and the canonical discover→show pipeline\n- Per-framework quickrefs: `sdlc-quickref`, `forensics-quickref`, `research-quickref`, `media-curator-quickref`, `marketing-quickref`, `ops-quickref`, `security-engineering-quickref`, `knowledge-base-quickref`\n- `skill-discovery` HIGH rule — discovery is mandatory before declining or improvising\n","# AIWG Language Map — Addons + Extensions\n\nThis is your always-loaded directory for the AIWG **addon and extension** surface. It's the orientation layer for the ~214 skills that live outside the 8 frameworks. Frameworks have their own per-framework quickrefs (`sdlc-quickref`, `forensics-quickref`, etc.); this map covers everything else: addons (utilities, loops, voice, testing, etc.) and ops extensions (sys\u002Fnet\u002Fsec\u002Fdev\u002Fit\u002Fstream).\n\n## How to use this map\n\n1. Identify which **capability domain** below the user's need belongs to\n2. Pick a **curated phrase** from that domain\n3. Run `aiwg discover \"\u003Cphrase>\"` and surface the top match (or top-3) to the user\n4. Fetch the body with `aiwg show skill \u003Cname> --body` — never `find` \u002F `ls` \u002F `Read` on storage paths\n\nIf a phrase doesn't fit the user's exact need, paraphrase. `aiwg discover` is forgiving with natural language.\n\n**The discover→show pattern is mandatory.** See `aiwg-utils-quickref` for the canonical pipeline and `skill-discovery` HIGH rule for enforcement.\n\n## Map layout\n\nThe map has two sections:\n\n- **Addon capability domains** — user-need clusters (memory, loops, voice, etc.) routed to addons\n- **Extension domains** — operational scopes (sys, net, sec, etc.) for `ops-complete`\n\nEach section opens with an explicit `aiwg discover \"\u003Cphrase>\"` example. Table rows underneath show **bare phrases** — pass them straight to `aiwg discover` (the verb is implied by the section header). Phrases have been verified against the index; each surfaces the listed bundle in the top results.\n\n---\n\n## Addon capability domains\n\n### Dataset intelligence, indexing & provenance\n\nWhen a user points AIWG at files, an API, a corpus, or another dataset and asks\nfor search, indexing, traceability, provenance, lineage, synchronization, or\nsafe retirement—even when they do not know those terms.\n\nExample: `aiwg discover \"make this searchable\"`. Phrases below pass straight to\n`aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Start from only a source and outcome | `use this data` | dataset-intelligence |\n| Recommend custom indexing safely | `make this searchable` | dataset-intelligence |\n| Add evidence-bearing traceability | `trace this dataset` | dataset-intelligence |\n| Explain record or field lineage | `where did this record come from` | dataset-intelligence |\n| Verify freshness and provenance | `verify this dataset` | dataset-intelligence |\n| Resume an incremental source | `sync this source` | dataset-intelligence |\n| Retire data and derived artifacts safely | `retire this dataset` | dataset-intelligence |\n\nThe same governed intake and handoff envelopes serve SDLC, research,\nknowledge-base, media, marketing, ops, and project-local bundles. All execution\ndelegates to `aiwg dataset`; the addon does not create a shadow runtime.\n\n### Schemas & data contracts\n\nWhen the user describes a record, configuration file, event, API payload,\nmessage, import\u002Fexport, or other structured data—even when they do not know to\nask for a schema.\n\nExample: `aiwg discover \"define data shape\"`. Phrases below pass straight to\n`aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Decide whether structured data needs a contract | `define data shape` | schema-governance |\n| Explain schemas and continue examples-first | `why do I need a schema` | schema-governance |\n| Author and register a canonical schema | `create a schema` | schema-governance |\n| Evolve an existing contract safely | `change an existing schema` | schema-governance |\n| Review correctness and readiness | `review a data contract` | schema-governance |\n\nThe SDLC discovery track invokes this addon automatically for persistent or\nexchanged data. Users should describe the data need; they need not choose a\ndialect, identifier, lifecycle, or compatibility policy themselves.\n\n### Loops & iteration\n\nWhen the user needs an iterative coding loop, recursive context decomposition, eval gates, or guided autonomous implementation.\n\nExample: `aiwg discover \"ralph loop\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Iterative AI coding loop (Ralph) | `ralph loop` | agent-loop |\n| Loop status \u002F abort \u002F resume \u002F attach | `ralph attach` (or `ralph abort` \u002F `ralph resume` \u002F `ralph status`) | agent-loop |\n| External crash-resilient loop variant | `ralph external loop` | agent-loop |\n| Recursive decomposition of a huge corpus | `rlm query` | rlm |\n| RLM batch processing with parallel sub-agents | `rlm batch fan-out` | rlm |\n| Bounded autonomous issue-to-code | `guided implementation` | guided-implementation |\n| Inner generator\u002Fcritic eval loop in a pipeline | `eval loop` | nlp-prod |\n| KAMI-based agent quality eval framework | `agent quality eval` | aiwg-evals |\n\n### Session history and exploration\n\nUse `aiwg discover \"spelunk session data\"` to find catalog exploration. Useful\nphrases include `search past conversations`, `trace session tool calls`,\n`compare provider sessions`, and `harvest session decisions`. `session-explore`\nhandles search, timelines, analytics, citations and coverage; `session-harvest`\nhandles candidate review and promotion. `session-analyst` and the\n`session-investigation` flow compose bounded evidence collection and synthesis.\nThe singular `session` launcher and cost-history telemetry serve different needs.\n\n### Memory & state\n\nWhen the user needs persistent agent memory, semantic ingestion, or context curation.\n\nExample: `aiwg discover \"memory ingest\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Semantic memory ingest | `memory ingest` | semantic-memory |\n| Lint memory entries | `semantic memory lint` | semantic-memory |\n| Capture \u002F query memory | `memory query` | semantic-memory |\n| Filter context to remove distractors | `filter distractors from context` | context-curator |\n\n> `llm-wiki` has a first-class discoverable driver for profile selection and\n> activation; its topology composes with the knowledge-base framework and\n> semantic-memory drivers. `auto-memory` remains a template bundle pending its\n> own operational driver.\n\n### Voice & writing quality\n\nWhen the user is producing or reviewing prose and needs voice consistency, AI-pattern detection, or related text quality work.\n\nExample: `aiwg discover \"apply voice profile\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Apply a voice profile to existing content | `apply voice profile` | voice-framework |\n| Create a new voice profile | `create voice profile` | voice-framework |\n| Blend two voices | `blend voice profiles` | voice-framework |\n| Analyze content's current voice | `analyze voice` | voice-framework |\n| Detect AI-pattern artifacts in writing | `ai pattern detection` | writing-quality |\n| Improve output diversity (verbalized sampling) | `verbalized sampling` | verbalized-sampling |\n\n### NLP & inference pipelines\n\nWhen the user is building or optimizing LLM inference systems.\n\nExample: `aiwg discover \"pipeline architect\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| LLM inference pipeline architecture | `pipeline architect` | nlp-prod |\n| Pipeline pattern selection | `pipeline pattern` | nlp-prod |\n| Cost optimizer for LLM workloads | `llm cost optimizer` | nlp-prod |\n| Eval-loop generator\u002Fcritic | `eval loop` | nlp-prod |\n| Productionize an inference pipeline | `pipeline productionize` | nlp-prod |\n| Prompt engineering | `prompt engineer` | nlp-prod |\n| Agentic or bounded classification | `agentic classification` | decision-engine (opt-in) |\n| Jev decision engine | `Jev decision engine` | decision-engine (opt-in) |\n| Reduce frontier tokens with bounded decisions | `classify to reduce frontier tokens` | decision-engine (opt-in) |\n| Offload a yes\u002Fno, pick-one, or 1-N decision to Jev | `offload decisions to jev` | decision-engine (opt-in) |\n| Set up Jev with a token | `set up jev` | decision-engine (opt-in) |\n| Questions sharing authorized state | `shared-state batching` | decision-engine (opt-in) |\n| Offline decision fixtures and readiness plans | `decision playground` | decision-engine (opt-in) |\n\n`decision-engine` requires explicit installation: `aiwg use decision-engine`.\nIt is excluded from bulk installs. Discover `decision-offload` for\nsingle-question offload via `aiwg decision ask` (enabled by\n`aiwg decision setup jev`); discover `decision-evaluate` for pinned\nclassification requests; evaluation requires `AIWG_DECISION_ENABLED=1` plus\nan explicit backend binding and approved projection for live egress. Library\nbatching also needs host policies; discovering the skill does not enable it.\nDiscover `decision-playground` to list and run offline recorded fixtures without\ncredentials or inference. Its `live-plan` command only reports readiness; live\nevaluation requires the separate explicit opt-in and host configuration.\nThese phrases use deterministic discovery and require no model inference.\n\n### Documentation intelligence\n\nWhen the user is scraping, extracting, or analyzing documentation as a corpus.\n\nExample: `aiwg discover \"doc analyst\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Coordinate doc analysis (master orchestrator) | `doc analyst` | doc-intelligence |\n| Scrape documentation sites | `doc scraper` | doc-intelligence |\n| Extract from PDFs | `pdf extractor` | doc-intelligence |\n| Run an OpenProse program | `prose run` | prose-integration |\n| Validate \u002F parse a Prose program | `prose validate` | prose-integration |\n\n### Testing & quality\n\nWhen the user needs test enforcement, UAT, or quality automation.\n\nExample: `aiwg discover \"tdd enforce\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| TDD enforcement \u002F test gates | `tdd enforce` | testing-quality |\n| Mutation testing analyst | `mutation analyst` | sdlc-complete (agent) |\n| Mutation test runner | `mutation test` | testing-quality |\n| UAT plan generation via MCP | `uat plan` | uat-mcp |\n| UAT execution via MCP | `uat execute` | uat-mcp |\n\n### Skill \u002F extension authoring\n\nWhen the user is building new AIWG content (skills, addons, framework changes).\n\nExample: `aiwg discover \"skill architect\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| End-to-end skill creation orchestrator | `skill architect` | skill-factory |\n| Build a skill | `skill builder` | skill-factory |\n| Enhance \u002F validate \u002F package a skill | `skill packager` | skill-factory |\n| Validate an AIWG addon | `validate addon` | aiwg-dev |\n| Validate a framework component | `validate component` | aiwg-dev |\n| AIWG devkit build helpers | `devkit build` | aiwg-dev |\n| Link-check across docs | `link check` | aiwg-dev |\n\n### Color & UX\n\nWhen the user needs color theory or palette tooling.\n\nExample: `aiwg discover \"color palette\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Generate or review a color palette | `color palette` | color-palette |\n| Color theory fundamentals reference | `color theory` | color-palette |\n| Accessibility \u002F contrast review | `color accessibility` | color-palette |\n\n### Daemon & background work\n\nWhen the user needs persistent sessions or background orchestration.\n\nExample: `aiwg discover \"daemon init\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Concierge daemon entry \u002F init | `daemon init` | aiwg-utils |\n| Concierge agent (front-of-house) | `concierge daemon` | daemon |\n| Mission Control (background mission orchestrator) | `mc dispatch` | agent-loop |\n| Star-prompt for repo recommendations | `star prompt` | star-prompt |\n\n### Setup & installer\n\nWhen the user is bootstrapping a project or installing AIWG itself.\n\nExample: `aiwg discover \"setup manifest generate\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| Generate a reproducible installer manifest | `setup manifest generate` | agentic-installer |\n| Validate \u002F run a setup manifest | `setup manifest validate run` | agentic-installer |\n\n### Hooks & integration\n\nWhen the user needs platform-level lifecycle hooks, HITL gates, or external bridges.\n\nExample: `aiwg discover \"hitl patterns\"`. Phrases below pass straight to `aiwg discover`.\n\n| Need | Phrase | Bundle |\n|---|---|---|\n| HITL gate patterns (rule) | `hitl patterns` | sdlc-complete (rule) |\n| HITL gates (rule, ensemble review) | `hitl gates` | sdlc-complete (rule) |\n| Factory AI compat agent | `factory compat` | sdlc-complete (agent) |\n\n> `aiwg-hooks`, `agent-persistence`, and `droid-bridge` now expose\n> discoverable activation drivers. Their low-level hooks, HITL gates, and MCP\n> server remain implementation artifacts reached through those drivers.\n\n### Core meta-utilities\n\nFor everything else AIWG-internal — context regeneration, workspace management, index\u002Fquery, validation, and project-status surfaces — see `aiwg-utils-quickref`. It's already loaded; this map points back at it.\n\n---\n\n## Extension domains (ops-complete)\n\nOperational extensions live under `agentic\u002Fcode\u002Fextensions\u002F\u003Cdomain>\u002F` and extend `ops-complete`. They carry both skills AND rules. The framework-level `ops-quickref` lists the high-level extension model; this section gives you direct phrases.\n\nEach block opens with one explicit `aiwg discover` example; remaining phrases are bare — pass straight to `aiwg discover`.\n\n### sys — per-host operations\n\nHardware, OS, boot chains, fleet host documentation, immutable bases, hardware safety procedures.\n\n```\naiwg discover \"sys host profile\"   # → sys-host-profiler agent (1.00)\nsys host audit                     # → sys-host-audit skill\nluks tpm dual phase                # → sec-luks-dual-phase rule (sys+sec border)\nsys host independence              # → sys-host-independence rule\n```\n\n### net — network operations\n\nVLANs, DNS, firewalls, Cloudflare tunnels, UniFi config, network state authority, cert expiry gates, tunnel safety.\n\n```\naiwg discover \"vlan audit\"   # → net-vlan-audit (1.00)\nnet dns check                # → net-dns-check skill\nnet change blast radius      # → net-change-blast-radius rule\ntunnel safety                # → net-tunnel-safety rule\nnet state authority          # → net-state-authority rule\n```\n\n### sec — security operations\n\nPKI, LUKS, TPM2, YubiKey, SSH CA, access auditing, cert expiry gates, key material handling.\n\n```\naiwg discover \"sec cert scan\"   # → sec-cert-scan\nsec access snapshot             # → sec-access-snapshot\nsec access audit frequency      # → sec-access-audit-frequency rule\nsec cert expiry gate            # → sec-cert-expiry-gates rule\nkey material handling           # → sec-key-material-handling rule\nsec luks dual phase             # → sec-luks-dual-phase rule\n```\n\n### dev — CI\u002FCD and build automation\n\nPipeline safety, idempotent builds, secret hygiene, self-contained CI builders.\n\n```\naiwg discover \"pipeline safety ci\"   # → dev-pipeline-safety rule\nidempotent build                     # → dev-idempotent-builds rule\nci secret hygiene                    # → dev-secret-hygiene rule\nself contained ci builder            # → dev-ci-self-contained rule\n```\n\n### it — IT ops, CMDB, asset management\n\nAsset registry, service deployments, disaster recovery, change control, asset authority, DR validation.\n\n```\naiwg discover \"it asset sync\"   # → it-asset-sync skill (0.81)\nit asset authority              # → it-asset-authority rule\nit service health               # → it-service-health rule\nit dr validation                # → it-dr-validation rule\nit change control               # → it-change-control rule\n```\n\n### stream — streaming media operations\n\nTranscoders, restreaming, platform integrations, stream pipeline gates.\n\n```\naiwg discover \"stream deploy\"   # → stream-deploy skill\nstream pipeline gates           # → stream-pipeline-gates rule\nstream safety                   # → stream-safety rule\n```\n\n### api-adapter — external API integrations\n\nReserved for external API adapter scaffolding. Currently a placeholder bundle with no skills or rules; phrases will appear as adapters are added.\n\n---\n\n## Categories at a glance (cheat sheet)\n\nWhen you don't know which domain a need falls into:\n\n| If the user mentions... | Look in... |\n|---|---|\n| \"loop\", \"iterate\", \"ralph\", \"recursive\", \"decompose huge file\" | Loops & iteration |\n| \"remember\", \"memory\", \"context\", \"wiki\", \"ingest\" | Memory & state |\n| \"voice\", \"writing style\", \"AI pattern\", \"diversity\", \"samples\" | Voice & writing quality |\n| \"inference\", \"pipeline cost\", \"model selection\" | NLP & inference pipelines |\n| \"documentation scrape\", \"extract from PDF\", \"Prose program\" | Documentation intelligence |\n| \"test enforcement\", \"TDD\", \"UAT\", \"MCP test\" | Testing & quality |\n| \"build a skill\", \"scaffold addon\", \"framework dev\" | Skill \u002F extension authoring |\n| \"color\", \"palette\", \"contrast\", \"WCAG\" | Color & UX |\n| \"daemon\", \"background mission\", \"mission control\" | Daemon & background work |\n| \"installer\", \"setup manifest\", \"bootstrap\" | Setup & installer |\n| \"hooks\", \"permissions\", \"session\", \"droid\", \"HITL\" | Hooks & integration |\n| \"host\", \"BIOS\", \"boot chain\", \"OS install\" | Extensions \u002F sys |\n| \"VLAN\", \"DNS\", \"firewall\", \"tunnel\" | Extensions \u002F net |\n| \"cert\", \"LUKS\", \"YubiKey\", \"PKI\", \"access audit\" | Extensions \u002F sec |\n| \"CI\", \"pipeline\", \"build\", \"secret in workflow\" | Extensions \u002F dev |\n| \"CMDB\", \"asset\", \"DR\", \"service deploy\", \"change control\" | Extensions \u002F it |\n| \"transcoder\", \"restream\", \"live broadcast\" | Extensions \u002F stream |\n\n---\n\n## Project-local extensions (pilot → promote)\n\nAddons, extensions, and frameworks don't all have to come from upstream. Users can pilot content bundles per-project under `.aiwg\u002F{extensions,addons,frameworks}\u002F\u003Cname>\u002F`, validate them, then promote to upstream when mature. Use `.aiwg\u002Fplugins\u002F\u003Cname>\u002F` only when wrapping a bundle for marketplace delivery. Curated phrases:\n\n```bash\naiwg new-bundle \u003Cname>                         # scaffold; auto-builds project graph\naiwg new-extension \u003Cname> --starter rule       # extension with starter rule\naiwg new-addon \u003Cname>                          # addon\naiwg new-framework \u003Cname>                      # framework\naiwg new-plugin \u003Cname>                         # marketplace delivery wrapper\naiwg new-bundle \u003Cname> --dry-run               # preview without writing\naiwg list --project-local                      # inventory + validation status\naiwg doctor --project-local                    # health check (counts, drift, shadows)\naiwg use \u003Cname>                                # deploy single project-local bundle\naiwg promote \u003Cname>                            # graduate to upstream (hash-verified)\naiwg promote \u003Cname> --to corpus \u003Cpath>         # promote to private corpus instead\naiwg promote \u003Cname> --dry-run                  # preview promotion\n```\n\nAfter scaffolding, the bundle is immediately discoverable via `aiwg discover \"\u003Cname>\"` — the project graph is rebuilt automatically. No manual `aiwg index build --graph project` step needed.\n\n## When this map doesn't have a phrase that fits\n\n**Don't enumerate from memory.** Run `aiwg discover` with the user's natural-language phrasing — the index is forgiving. If you get zero results, try:\n\n1. A broader phrase (e.g., drop a noun)\n2. A different vocabulary (e.g., \"deploy\" vs \"publish\" vs \"release\")\n3. `aiwg index stats --graph framework` to confirm the index is built and populated\n4. Check whether the bundle is even installed via `aiwg list`\n5. If the workspace has project-local bundles, also check `aiwg index stats --graph project`\n\nIf after that the capability genuinely doesn't exist, you can tell the user honestly — but only after the search ran and came up empty. The `skill-discovery` HIGH rule mandates the search before declining.\n\n## See also\n\n- `aiwg-utils-quickref` — core meta-utility surface and the canonical discover→show pipeline\n- Per-framework quickrefs: `sdlc-quickref`, `forensics-quickref`, `research-quickref`, `media-curator-quickref`, `marketing-quickref`, `ops-quickref`, `security-engineering-quickref`, `knowledge-base-quickref`\n- `skill-discovery` HIGH rule — discovery is mandatory before declining or improvising\n",{"name":5,"kernel":38,"namespace":39,"platforms":40,"description":7},true,"aiwg",[41],"all","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-language-map",36,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg","https:\u002F\u002Faiwg.io","https:\u002F\u002Fgithub.com\u002Fjmagly","https:\u002F\u002Fintegrolabs.io","ml\u002Fai, industrial automation, safety\u002Fsecurity, ssi\r\n\r\nmagly.net\r\nintegrolabs.io\r\naiwg.io\r\nfortemi.com\r\npagenary.com\r\nbytecask.com","2026-11-11 08:11:25",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":38},[54,57,60],{"tool":55,"command":56},"npx","npx skills add jmagly\u002Faiwg --skill aiwg-language-map",{"tool":58,"command":59},"bunx","bunx skills add jmagly\u002Faiwg --skill aiwg-language-map",{"tool":61,"command":62},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill aiwg-language-map","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-language-map\u002FSKILL.md",[65,71,75,79,83,89,93],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"environment.yml","REFERENCE","参考文档",475,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Fenvironment.yml",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fbackends.md",4010,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Freferences\u002Fbackends.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Foutput_format.md",3020,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Freferences\u002Foutput_format.md",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fserver_setup.md",2863,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Freferences\u002Fserver_setup.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fdocling_pipeline.py","SCRIPT","脚本",17714,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Fscripts\u002Fdocling_pipeline.py",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Focr_document.py",12299,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Fscripts\u002Focr_document.py",{"path":94,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Focr_utils.py",27034,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fbrunoasm-document_ocr\u002Fscripts\u002Focr_utils.py",[98,126,150,156,163,176],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":33},"01M70QA0BSYJ49EES9V4RE8QH1","host-hardening","Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[104],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":136,"publishedAt":33},"01M70PNT2Z4HMZPRBTAF6073NN","exposure-analysis","Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fforensics\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[132,135],{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[137,138,139,109,140,114,141,142,116,143,106,144,118,145,146,121,122,147,148,149],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":151,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":33},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[154],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[108,106,107,117,109,125,112,111,120,113,114,115,116,124,118,119,110,121,122,123],{"skillNo":157,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":162,"publishedAt":33},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[160,161],{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[138,137,121,140,114,141,116,139,106,144,118,145,146,109,122,143,142,147,148,149],{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":33},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[169],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[171,172,173,174,31,175],"fixture skill","fixture","rule","delivery","exercise",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":33},"01M6CB4AVK1W76MFMPP0JP32CJ","pi-local","Pi-local duplicate-precedence fixture.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fproviders\u002Fpi\u002Fproject\u002F.pi\u002Fskills\u002Fpi-local\u002FSKILL.md",[182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[184,185,145,186,172],"pi","pi local","duplicate"]