Menu
Use when deciding what to optimize or refactor for performance — ranks code by combining runtime profile hotness with static complexity and coupling, so effort lands where it is both expensive at runtime and hard to change.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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 | hot-path-refactor |
| description | Use when deciding what to optimize or refactor for performance — ranks code by combining runtime profile hotness with static complexity and coupling, so effort lands where it is both expensive at runtime and hard to change. |
Prioritize performance/refactor effort on code that is both hot at runtime and structurally hard. Optimizing cold code wastes effort; optimizing hot-but-trivial code rarely pays; the wins are where hotness meets complexity.
A speedscope profile (py-spy/Austin or pprof→speedscope) and the source tree. Overlays are MCP tools (Architecture tier).
profile_overlay with the speedscope report to rank symbols by self_pct (direct cost) and total_pct (inclusive cost).analyze_hotspots to rank files/functions by composite complexity (cyclomatic, statements, nesting).analyze_coupling to find how entangled a hot symbol's module is (refactoring a high-coupling hot path is riskier and higher-value).self_pct AND high complexity is the top refactor target (expensive and changeable). High self_pct + low complexity → consider an algorithmic/throughput fix, not a refactor. High total_pct but low self_pct → the cost is in callees; follow the stack.A ranked target list. Each: symbol id, self_pct/total_pct, complexity/coupling signals, and a one-line recommended action. Lead with hot-and-hard intersections.
Profile percentages are relative to the captured workload — say so; a different workload shifts the hot set. Respect modeled_kinds/unmapped: frames that mapped to no symbol are excluded, not zero-cost. Complexity is a syntactic estimate.