Agent Skills — Pre-Built Workflows for AI Coding Agents

10 pre-built agent skills that compose act's 183 refactor operations, 30 codebase analyzers, 15 query operations, and 8 porting operations into common engineering workflows: architecture-audit, code-review, refactoring, code-navigation, code-generation, migration-assessment, boundary-analysis, change-impact, health-check, and architectural-refactoring. Invoke with /skill-name in Claude Code, Cursor, Codex, OpenCode, or any MCP-compatible agent.

Invocation Skill Analysis Tools License
/agent-safety-audit Agent Safety Audit
Audit whether an AI agent edit to a file is safe — composes secret-surface, taint-flow, change-impact, and API-surface a…
analyze_impact
analyze_surface
Architecture
/architectural-refactoring Architectural Refactoring
Execute structural decompositions based on an architectural analysis report. Use when breaking circular dependencies, sp…
analyze_clusters
analyze_coupling
analyze_cycles
analyze_dead_code
analyze_seams
analyze_surface
simulate
split_module
Architecture
/architecture-audit Architecture Audit
Use when asked to audit architecture, produce a comprehensive architectural overview, get the full structural picture of…
analyze_chokepoints
analyze_clones
analyze_clusters
analyze_cohesion
analyze_conformance
analyze_coupling
analyze_cycles
analyze_dead_code
analyze_entry_points
analyze_export
analyze_hotspots
analyze_layers
analyze_patterns
analyze_roles
analyze_seams
analyze_stability
analyze_surface
churn_hotspots
co_change_clusters
coverage_overlay
ownership_map
simulate
split_module
Architecture
/boundary-analysis Boundary Analysis
Use when looking for extraction candidates, planning a module split, analyzing module boundaries, or before decomposing …
analyze_clusters
analyze_cohesion
analyze_extraction
analyze_interface_bloat
analyze_interfaces
analyze_layers
analyze_orphan_types
analyze_seams
analyze_surface
simulate
split_module
Enterprise
/change-impact Change Impact
Use before modifying a file or symbol, or when asked "what breaks if I change X?". Depth 0 — fast, no follow-up queries,…
analyze_cycle_risk
analyze_impact
analyze_test_gaps
Architecture
/code-generation Code Generation
Generate boilerplate code from existing types using AST-aware code generation. Use when creating constructors, getters/s…
/code-navigation Code Navigation
Traverse large repositories efficiently using act's query tools. Use when exploring unfamiliar code, mapping dependencie…
/code-review Code Review
Review code for bugs, complexity, unused symbols, and structural issues using AST-aware analysis. Use when reviewing PRs…
analyze_api_diff
analyze_impact
Architecture
/create-work-loop Create Work Loop
Generate a robust, idempotent work-loop tracker — the single resumable state file that drives a large implementation pro…
/dead-in-production Dead In Production
Use when you want to safely remove code — finds symbols that are statically unreferenced, never covered by tests, and ne…
analyze_dead_code
coverage_overlay
trace_overlay
Architecture
/health-check Health Check
Use when asked about code health, quality trends, what's getting worse, or for a periodic quality check. Depth 1 — fast,…
analyze_clones
analyze_cohesion
analyze_coupling
analyze_hotspots
analyze_inconsistencies
analyze_patterns
analyze_test_gaps
Architecture
/hot-path-refactor Hot Path Refactor
Use when deciding what to optimize or refactor for performance — ranks code by combining runtime profile hotness with st…
analyze_coupling
analyze_hotspots
profile_overlay
Architecture
/migration-assessment Migration Assessment
Use when assessing migration readiness, planning a port to another language, understanding what makes this codebase hard…
analyze_clusters
analyze_conformance
analyze_depth
analyze_fan_balance
analyze_features
analyze_inheritance
analyze_interfaces
analyze_layers
analyze_patterns
analyze_platform_deps
analyze_readiness
analyze_type_completeness
churn_hotspots
coverage_overlay
ownership_map
Enterprise
/onboarding-map Onboarding Map
Use when onboarding to an unfamiliar codebase — produces a guided reading order (entry points first, then high-traffic a…
analyze_entry_points
churn_hotspots
ownership_map
Architecture
/port-verify Port Verify
Gate a cross-language port for correctness — composes port-scoped behavioral equivalence, contract parity, and port-mani…
/refactor-receipt Refactor Receipt
Emit durable refactor receipts — content-addressed JSON artifacts proving a refactor was verified. Delegates to the ship…
/refactoring Refactoring
Perform semantic code refactoring using AST-aware tools. Use when renaming symbols, extracting functions or variables, i…
/safe-to-merge Safe To Merge
Decide whether a change is safe to merge — runs `act gate`, the deterministic verdict (MERGE / REVIEW / BLOCK / UNKNOWN)…
/security-surface Security Surface
Use to produce an application-security surface report for a file or module — dangerous constructs, secret-touching code,…
analyze_surface Engineering
/verify-refactor Verify Refactor
Verify a refactor preserved behavior — composes contract, side-effect, and CFG-equivalence checks across two versions of…
/where-bugs-live Where Bugs Live
Use when you need to find the riskiest code in a repository — where bugs are most likely to live — by combining git chur…
analyze_hotspots
churn_hotspots
co_change_clusters
ownership_map
Architecture