Analyze session work and automatically convert reusable patterns into Claude Code skills. Use when: "세션을 스킬로", "스킬 만들어", "이거 스킬로", "skill factory", "이 작업 자동화해", "스킬 추출", "make…
Refine Harness Engineering artifacts, plans, specs, or work into clearer action plans. Use when users ask for tightening, simplification, or lifecycle repair.
WHAT: Generate local Codex usage reports. WHEN: Use when users ask for usage analytics, weekly insights, session summaries, telemetry patterns, or prompting help.
Create and validate implementation-grade CLI specifications when command trees, JSON contracts, dry-run plans, errors, or agent-ready behavior need a binding spec.
Plan execution work from specs, brainstorm outputs, bugs, or feature requests into an implementation-ready sequence.
Define problem scope, requirements, and decision options before spec or plan stages. Use when the user has ambiguity in what to build, why it matters, or which direction to choose.
Run a bounded Harness Engineering lifecycle across multiple stages. Use when the user wants coordinated brainstorm, spec, plan, work, review, and fix flow rather than one isolated…
Implement approved Harness Engineering work. Use when a plan, todo list, or tiny spec needs traceable delivery and validation.
Audit, validate, and troubleshoot Agentation integrations in frontend apps. Use when annotations, MCP registration, endpoint sync, webhook delivery, or watch mode readiness are…
Review diffs, PRs, specs, plans, or review-feedback items and return severity-ranked engineering findings with exact locations.
Generate and compare grounded product or engineering directions with tradeoffs. Use when users want possibilities, critique, or direction-setting before a spec.
Run, plan, and validate pnpm workspace operations. Use when a user needs pnpm monorepo installs, tests, builds, filters, changed-package selection, or publish routing.
Use when creating, installing, validating, folding, or troubleshooting Codex custom subagent role TOML and discoverability config.
Analyze broad, mixed, or unclear Plugin Factory follow-up requests and select the correct plugin lane. Use when plugin intent lacks a clear lane owner.
Create, review, and validate an alignment checkpoint. Use when a request is ambiguous, high-stakes, multi-step, or requires explicit approval before tool use.
Build behavior-safe code changes with TDD and RED/GREEN evidence. Use when he-plan or he-work requires TDD for a concrete behavior target.
Ship skill changes to PRs when Codex skills need source edits, rooted sync, strict audit, reviewer evidence, commit, push, and PR status.
Install, repair, and validate Vale prose linting. Use when users need Vale config, style sync, docs lint gates, or broken Vale workflow diagnosis.
Design, review, and validate Codex app automations when recurring background workflows need safe scheduling, scope, preflight, and consolidation.
Analyze broad frontend design requests and route them to the correct local UI skill after classifying intent and maturity.
Analyze, compare, and recommend a Codex build primitive. Use when the user is packaging or automating a workflow and the right primitive is unclear.
Deepen an existing system or UI spec so boundaries, lifecycle rules, failure handling, and validation are strong enough for planning.
WHAT: Route plugin-factory requests to the right lane. WHEN: Use when plugin creation, building, installation, review, or routing is broad, mixed, or under-specified.
Improve existing Harness Engineering implementations or workflows with evidence-backed changes. Use when users ask for targeted enhancement of shipped or drafted work.
Run, audit, and design authorized Recon Workbench workflows when scoped target interrogation needs evidence artifacts, redaction, validation, and safe reporting.
Analyze, review, and plan architecture alternatives through a structured interview. Use when the user needs tradeoffs surfaced before implementation or a Linear decision note…
Scan Codex session history for skill failures, usage patterns, and coverage gaps. Use when the user wants daily skill-health monitoring or evidence-backed recommendations about…
Write Harness Engineering specs before planning. Use when a feature, QA report, Linear issue, or UI source needs a clear WHAT contract.
Selects the correct Harness Engineering lifecycle stage and compatibility alias route. Use when a request is ambiguous, mixes brainstorm/spec/plan/work/review intent, references…
Review, configure, and troubleshoot prek hooks when users need prek.toml edits, shim installs, hook validation, or pre-commit migration help.
Remove AI slop and corporate jargon from text without applying a personal voice. Use when the user asks to "unslopify", "remove AI slop", "deslopify", "clean up AI writing",…
Create, repair, and validate uv Python project setup. Use when initializing Python apps or libraries, managing uv dependencies, virtual environments, or CI-ready uv workflows.
Analyze, design, or triage LLM evaluation workflows. Use when the user asks for evaluator design, error analysis, judge prompts, RAG evals, synthetic data, or review tooling.
Review PRs, branches, diffs, and workflow artifacts for package-level go/no-go readiness with severity-ranked synthesis.
Install, update, audit, diagnose, and explain @brainwav/coding-harness when repository governance, harness init, CI migration, or action-sync needs live command evidence.
Review, create, and validate Bash scripts when shell work needs strict mode, quoting safety, portability, or interpreter-compatible behavior.
Capture a completed Codex workflow as a reusable SKILL.md package by analyzing session context plus optional session-collector evidence, interviewing the user with structured…
Deepen an existing implementation plan so sequencing, verification, and risk treatment are strong enough for execution.
Create, validate, and repair Project Brain .harness memory files when setting up Project Brain, saving repo learnings, recording decisions, or preserving quality rules.
Restore broken behavior by reproducing failures, identifying root cause, and delivering verified fixes.
Generate, review, and refine high-retention technical YouTube hooks, outlines, and scripts. Use when the user wants video scripting tailored to a topic, audience, runtime, and…
Analyze and validate compound Harness Engineering run state, blockers, validation status, and Linear context.
Route skill lifecycle requests to a Skill Factory lane. Use when users ask to create, harden, install, audit, or skillify skills.
Create or refactor AGENTS.md and linked instruction docs using progressive disclosure. Use when the user wants repo-specific agent guidance organized, deduplicated, or routed…
Use when creating, auditing, upgrading, or validating Codex hook packs, hooks.json files, hook scripts, or repo-local/user-level .codex hook installs.
Review services, APIs, and multi-component systems for reliability risks including failure modes, cascading failures, resilience gaps, and SLO readiness.
Build and audit polished interaction refinements for existing React or Tauri UI when motion, accessibility, reduced-motion, and browser-verified behavior need focused improvement.
Review, triage, and validate visual regression diffs. Use when the user wants snapshot-change analysis, layout regression evidence, Storybook diffs, Playwright screenshots, or…
Create, review, or repair recurring Harness Engineering heartbeats that wake a thread, re-check live state, and route back into the right HE stage; use when PRs, CI, reviews,…
Use when you need focused cleanup audits, safe removals, scoped quality-risk reductions, and evidence-backed cleanup plans before touching code.
Create, install, validate, and orchestrate Codex custom subagents as standalone TOMLs with canonical global defaults (`~/dev/configs/codex/agents/{name}/{name}.toml`,…
Route ambiguous Harness Engineering requests to one lifecycle stage when users ask where to start, resume, plan, implement, review, debug, schedule a heartbeat, or resolve domain…
Review and prune stale branches safely. Use when branch cleanup needs evidence, protected-branch caution, PR awareness, and non-destructive recommendations.
Diagnose, fix, and validate mise runtime failures. Use when commands fail from mise config, missing runtimes, stale pins, trust prompts, or shell activation drift.
Generate, validate, and refresh @brainwav/diagram architecture artifacts when repo diagrams, context packs, PR impact, or CI drift evidence is needed.