ワンクリックで
MaintainabilityAI
MaintainabilityAI には AliceNN-ucdenver から収集した 27 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Append one hash-chained audit event to okrs/<id>/audit/events/<run-id>.jsonl. Returns the new chain head.
Replay the hash chain over an existing audit JSONL; returns the chain head on success, the first integrity failure reason on failure.
Query the mesh's threat library for entries matching a concern (e.g. "identity", "data-licensing").
Academic paper search via arXiv. Returns ranked paper results per query envelope.
Aggregated architecture context for a scope — CALM nodes + ADRs + fitness functions + quality attributes. PURE data; the Architect persona is in the parent agent's prompt.
Aggregated quality context for a scope — quality attribute definitions + performance SLOs + reliability targets per BAR.
Aggregated security context for a scope — STRIDE threats + OWASP refs + NIST controls + prior threat-model docs. PURE data; the Security persona is in the parent agent's prompt.
Merge ProviderResult arrays from all search Skills, dedupe by URL, rank by relevance + recency + diversity.
Format a research run's signals as a Markdown comment for the OKR anchor issue.
Practitioner-community search via Hacker News Algolia API. Returns story + Show/Ask HN text per query envelope.
Reads bounded file contents (≤10 KB) from the brownfield clone retained by knowledge-code. Lets the code-design-agent ground design with real code excerpts, not paraphrased guesses. Shares the session clone cache with knowledge-code — call knowledge-code first for the same repo.
Per-repo grounding for the code-design-agent. Three modes per A12.v1.1 targetCodeRepoStatus — brownfield (clone + classify), greenfield (scaffolding hints, no clone), refuse (not-connected / unreachable).
Query the mesh's ADRs by concern. Returns matching ADR documents from any BAR's architecture/ADRs/.
Read a BAR's CALM model + threats + ADRs + app.yaml from the mesh by BAR id.
Read a Platform's CALM model + cross-BAR design from the mesh by platform id.
Read the OKR card by id from the mesh. Returns the BTABoK 9-section structure as JSON.
Read the merged PRD for an OKR. Returns FRs / SRs / coverage table for the code-design agent and reviewers.
Optional exemplar grounding for the code-design-agent. Clones + indexes a per-mesh-configured list of "patterns we want the agent to honor" from mesh/.caterpillar/reference-repos/. Same shape as knowledge-code, but the agent treats every returned repo as a reference EXEMPLAR — never as an edit target.
Read the merged research-doc.md for an OKR. Returns structured findings (R-N anchors) for the PRD agent to cite.
Authoritative tier + prompt-pack handoff for the Architect persona-switch self-critique round. PURE data; the Architect persona reasoning is in the parent agent's prompt. Returns the OKR action's frozen governanceTier + computed max_auto_rounds + should_proceed gate + the architecture-review.md prompt pack contents.
Authoritative tier + prompt-pack handoff for the Code-Architect persona-switch self-critique round (WHAT phase). PURE data; the Code-Architect persona reasoning is in the parent code-design-agent's prompt. Returns the OKR action's frozen governanceTier + computed max_auto_rounds + should_proceed gate + the code-design/architecture-review.md prompt pack contents.
Authoritative tier + prompt-pack handoff for the Code-Security persona-switch self-critique round (WHAT phase). PURE data; the Code-Security persona reasoning is in the parent code-design-agent's prompt. Returns the OKR action's frozen governanceTier + computed max_auto_rounds + should_proceed gate + the code-design/security-review.md prompt pack contents.
Authoritative tier + prompt-pack handoff for the Architect persona-switch self-critique round in the IMPLEMENTATION phase. PURE data; the Architect persona reasoning is in the implementation-agent's prompt. Returns the OKR's frozen governanceTier (passed in from the landing-issue Hatter Tag) + computed max_auto_rounds + should_proceed gate + the architect-review.md prompt pack contents read from .cheshire/prompts/implementation/ in the target repo.
Authoritative tier + prompt-pack handoff for the Security persona-switch self-critique round in the IMPLEMENTATION phase. PURE data; the Security persona reasoning is in the implementation-agent's prompt. Returns the OKR's frozen governanceTier (passed in from the landing-issue Hatter Tag) + computed max_auto_rounds + should_proceed gate + the security-review.md prompt pack contents read from .cheshire/prompts/implementation/ in the target repo.
Authoritative tier + prompt-pack handoff for the Security persona-switch self-critique round. PURE data; the Security persona reasoning is in the parent agent's prompt. Returns the OKR action's frozen governanceTier + computed max_auto_rounds + should_proceed gate + the security-review.md prompt pack contents.
Web search via Tavily's research-grade API. Returns ranked results per query envelope.
Patent search via USPTO's PatentsView API. Two-stage XML fetch returns claim abstracts per query envelope.