adversarial-reviewThree parallel reviewer agents find contradictions, config gaps, and coverage holes across a project''s docs, config, and tests — then fix what you approve. Heavyweight (dispatches parallel agents, can modify files). Supports env-var automation hooks (ADVERSARIAL_REVIEW_TARGETS, ADVERSARIAL_REVIEW_R
crapRank functions by CRAP score (complexity × lack of real test coverage) on the current branch, then propose either a refactor or missing tests for the worst offender. Use when the user runs /crap or asks to find risky, complex, poorly-tested code.
diagnoseDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when the user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
evolveRun an ASI-Evolve style evaluator-driven search workflow for code, algorithms, prompts, or pipelines. Use when Claude needs to align the objective, scoring, evaluator, writable scope, and cognition first, then execute a preflight-gated learn/design/experiment/analyze loop with the bundled Evolve CLI
featureOrchestrate the full agentic-engineering chain on one brief — map → research → story → spec → rubric → backend lane → validator → frontend lane → final validator → PR — with three human checkpoints (story, spec+rubric, PR). Default path is in-conversation: each step runs as a forked Agent subagent s
grill-mePure socratic interrogation with NO project artifacts at all — no codebase, no CONTEXT.md, no ADRs to reference. One question at a time, walk the decision tree, recommend an answer for each branch. Rare edge case — most grilling happens inside a project, so use grill-with-docs by default (it handles
grill-with-docsStress-test a plan, design, or idea against the project''s domain language (CONTEXT.md) and recorded decisions (docs/adr/). One question at a time, walks the decision tree, captures crystallized terminology and decisions inline. THIS IS THE DEFAULT GRILLING SKILL — use for any interrogation in a rea
improve-codebase-architectureFind deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
mapGenerate or update ARCHITECTURE.md — a living map of a project''s structure, dependencies, and high-coupling zones. Polyglot-adaptive. Heavyweight (writes ARCHITECTURE.md, dispatches parallel agents). Use only when explicitly asked: /map, "generate ARCHITECTURE.md", "map this codebase", OR when anot
prd-to-issuesRead an existing PRD (typically issues/prd.md, written by write-a-prd) and break it into vertical-slice tracer-bullet issues at issues/NNN-short-title.md, tagged HITL (needs human) or AFK (autonomous). Step 2 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when a PRD exists an
prototypeBuild a throwaway prototype to flush out a design before committing. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or st
tddTest-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
work-issuesAutonomously work one task from an issues/ queue end-to-end — explore, implement (TDD when applicable), run feedback loops, commit, update the issue file. Step 3 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Heavyweight (commits code, modifies the issue queue). Use only when exp
write-a-prdInterview the user and produce issues/prd.md from a client brief, feature idea, or rough request. Step 1 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when no PRD exists yet and one is needed. NOT for breaking an existing PRD into tasks (use prd-to-issues), and NOT for track
write-a-rubricProduce a gradeable rubric file from an issue, PRD, or free-form goal — sharpened to the standard required by Anthropic''s Managed Agents user.define_outcome event. Sidecar artifact (issues/NNN-*.rubric.md or rubrics/SLUG.md); does not modify source files. Use when the user wants to define "what don
write-a-specTurn an approved story (issues/NNN-*.md) plus an optional research dump into a technical spec sidecar at issues/NNN-*.spec.md — data model, API, file-by-file change list per lane (as fenced ```paths blocks), behavior-list of tests required, and risks. The spec drives /feature''s lane allowlist; lane
zoom-outTell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.