メニュー
Use when onboarding to an unfamiliar codebase — produces a guided reading order (entry points first, then high-traffic and load-bearing code) annotated with ownership and risk flags.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Audit whether an AI agent edit to a file is safe — composes secret-surface, taint-flow, change-impact, and API-surface analysis into an agent-edit safety report. Use before letting an agent modify a sensitive or high-blast-radius file.
Execute structural decompositions based on an architectural analysis report. Use when breaking circular dependencies, splitting god classes, reducing coupling between modules, extracting interfaces at seam boundaries, or executing any large-scale structural change identified in an architectural analysis. Requires a prior architecture audit (the architecture-audit skill) that produced project-map.md and a run report.
Use when asked to audit architecture, produce a comprehensive architectural overview, get the full structural picture of a codebase, assess overall health and porting readiness, find module boundaries, circular dependencies, coupling hotspots, dead code, or code patterns. Depth 3 — full audit with hypothesis-driven investigation. Optionally enriches the structural audit with runtime and git evidence (coverage, churn, co-change coupling, ownership) when those overlays are available. Replaces the architectural-analysis and architecture-audit-plus skills.
Use when looking for extraction candidates, planning a module split, analyzing module boundaries, or before decomposing a large component. Also use when asked "where should I split this?" or "find natural module boundaries". Depth 2 — investigate. Produces extraction candidates with cut costs, layer violations, interface width assessment, orphan types, and a recommended decomposition sequence.
Use before modifying a file or symbol, or when asked "what breaks if I change X?". Depth 0 — fast, no follow-up queries, returns immediately. Two modes: inline (no artifacts, default for agent-initiated use) and artifact (writes to docs/act/, triggered for human-initiated requests or Critical risk verdicts).
Traverse large repositories efficiently using act's query tools. Use when exploring unfamiliar code, mapping dependencies, understanding API surfaces, analyzing side effects before modifying functions, or following call chains across files. Avoids reading entire files by querying only the structure needed.
| name | onboarding-map |
| description | Use when onboarding to an unfamiliar codebase — produces a guided reading order (entry points first, then high-traffic and load-bearing code) annotated with ownership and risk flags. |
Turn an unfamiliar repository into a guided reading order: where to start, what to read next, and what to be careful around.
repo_outline to get the file tree, languages, and sizes. This is the territory.analyze_entry_points to find mains, HTTP routes, CLI commands, and event listeners. These are where execution (and reading) should begin.churn_hotspots (workspace mode) to find the most actively-changed code — what the team touches daily.ownership_map to find who knows what, and which symbols have a low bus factor (read these carefully; the expert may be unavailable).An ordered reading list. Each step: what to read (file/symbol), why it's next (entry point / high churn / load-bearing), its owner(s), and any risk flag. End with "areas to be careful around" (low bus factor, high churn).
Ownership and churn are git facts but degrade to file-level for grammars without symbol extraction (modeled_kinds) — say so. Entry-point and outline data are syntactic.