Claude Skills by jscraik

Read when: full content is needed at fixtures/budget-archive/2026-04-19/skills/code_quality_review/skill-builder/templates/router-skill.md

Read when: full content is needed at fixtures/budget-archive/2026-04-19/skills/code_quality_review/skill-builder/workflows/audit-skill.md

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 installing, improving, merging, or pruning skills.

Install Codex skills into the canonical git source tree from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Guide for creating effective skills. Use this skill when users need to create a new skill or reshape a draft skill package before hardening, benchmarking, or distribution.

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 prompts, and writing a validated skill artifact. Use when the user asks to skillify or operationalize a repeatable process.

Front-door router for the Skill Factory plugin. Use when users ask generally to create, improve, install, or skillify skills and need the correct lane selected before deeper execution.

Analyzes Codex skill-management requests, selects the workflow lane, and returns selected_lane, mode, next_step, and blockers. Use when the user says create a skill, add/update/fix/review a skill, install/sync/list skills, choose a workflow, or merge/retire a skill.

Canonical skills live in categorized folders below. Runtime projection is mode-dependent: - `flat`: selected allowlisted skills are projected directly. - `rooted`: only root skill sets are projected; latent modules route through `.skillsets/**` manifests. - `hybrid`: deferred until a named consumer and budget gate exist. Do not hand-edit runtime projections.

Use when reviewing, creating, shrinking, or refactoring AGENTS.md agent instructions, agent config files, routing rules, or repository guidance that need scoped routing, dedupe, contradiction fixes, progressive disclosure, and cleaned instruction surfaces.

Create, review, and validate an alignment checkpoint. Use when a request is ambiguous, high-stakes, multi-step, or requires explicit approval before tool use.

Apply approved fixes for unresolved CodeRabbit review comments, Codex P1-P3 findings, PR feedback, and code review issues with validation evidence. Use when asked to address review comments, fix review findings, clear unresolved comments, or autofix PR feedback.

Run bounded automated experiment iterations by recording baselines, applying hypothesis patches, comparing metrics, protecting regression guards, and deciding keep, discard, rollback, or block. Use when $autoresearch is named or a repo/skill needs evidence-backed research, metric tracking, or safe optimisation loops.

Review, create, and validate Bash scripts when shell work needs strict mode, quoting safety, portability, or interpreter-compatible behavior.

Analyze, fix, and validate Biome linting workflows. Use when JavaScript or TypeScript projects need Biome commands, diagnostics, safe fixes, or CI lint gates.

Create, diagnose, and validate a local dev bootstrap. Use when the user asks to clone a repo, install toolchains, install dependencies, and prove the project runs.

Turn Slack #code-fixes, CodeRabbit, Codex Review, CI, and check-status noise into a repo-and-PR action queue. Use when Jamie asks for a daily code-fixes digest, recent review-noise triage, or what needs fixing across active engineering repos.

Create, validate, install, fold, or troubleshoot Codex subagent role TOML, agents-table config, discoverability wiring, and duplicate-role merges. Use when a user asks for a Codex agent role, reviewer agent, role config, TOML role file, subagent setup, or overlapping agents to merge.

Use when designing, reviewing, or updating Codex app automations, cron jobs, scheduled tasks, recurring runs, or heartbeat follow-ups.

Use when a project or Codex runtime needs environment TOML created, triaged, or updated with safe setup, actions, exec-server providers, and validation evidence.

Scaffold hook packs, validate hooks.json schema, verify hook script permissions, migrate hook configuration, and troubleshoot Codex hook execution errors. Use when creating, auditing, upgrading, or validating Codex hook packs, hooks.json files, hook scripts, SubagentStart/SubagentStop lifecycle hooks, PreToolUse/PostToolUse/PreCompact hooks, Stop claim checks, or repo-local/user-level .codex hook installs.

Review local dirty changes, committed branches, and PR diffs with Codex CLI; report findings, validation, blockers, and merge-readiness evidence. Use when the user asks for Codex review, autoreview, independent model review, or pre-ship validation.

Use when users need to install, bootstrap, upgrade, audit, diagnose, or explain @brainwav/coding-harness in a repository, including harness init/upgrade, CI migration, governance gates, command discovery, and Codex environment action sync.

Analyze current external library or API docs with Context7 when dependency behavior, version-sensitive references, or ctx7 CLI setup/install guidance is needed.

Analyze, compare, and recommend a Codex build primitive. Use when the user is packaging or automating a workflow and the right primitive is unclear.

Generate, validate, and refresh @brainwav/diagram architecture artifacts when repo diagrams, context packs, PR impact, or CI drift evidence is needed.

Audit, rewrite, and validate README, runbook, code-doc, config-doc, and public trust-surface documentation by checking stale instructions, command examples, dependency claims, file paths, configs, workflows, and code references against live repository evidence. Use when documentation needs proof-backed correction or reader-focused validation.

Create and review idiomatic Elixir code with OTP patterns, supervision trees, and Phoenix LiveView. Use when building or debugging Elixir services that need reliable concurrency and fault tolerance.

Use when evaluating LLM or RAG outputs: audit eval coverage, analyze failed traces, write binary judge prompts, validate judges against labels, generate targeted synthetic cases, evaluate retrieval quality, or plan review tooling. Do not use for general software tests.

Diagnose, fix, and validate mise runtime failures. Use when commands fail from mise config, missing runtimes, stale pins, trust prompts, or shell activation drift.

Analyze ambiguous frontend design requests and route the right UI owner. Use this skill when broad design intent needs classification before implementation.

Best practices for working with Go codebases. Use when writing, debugging, or exploring Go code, including reading dependency sources and documentation.

Use when a Codex goal/task is stuck, hanging, not finishing, or needs status. Reads goal.md, state.yaml, receipts.jsonl; syncs reported status with board files; fixes invalid state.yaml; classifies blockers; decides done. Not for ordinary reviews or one-off fixes.

Use when reviewing or improving codebase architecture needs deeper module boundaries, clearer context language, better interfaces, stronger testability, or Linear-backed decisions.

Generate local Codex usage reports. Use when users ask for usage analytics, weekly insights, session summaries, telemetry patterns, or prompting help.

Create and debug modern JavaScript code with ES6+, async patterns, and Node.js APIs. Use when working on runtime behavior, promises, or browser and Node compatibility.

Diagnose Codex Desktop or CLI local-state bloat and safe recovery options. Use when sessions, archived history, logs, worktrees, or stale Codex config may be making Codex feel slow.

Create, review, and validate npm release workflows. Use when preparing or publishing npm packages, release channels, dist-tags, provenance, or 2FA-protected publishes.

Run, plan, and validate pnpm workspace operations. Use when a user needs pnpm monorepo installs, tests, builds, filters, changed-package selection, or publish routing.

Automate until-green PR review, CI, merge, and cleanup follow-through. Use when open project PRs need GitHub/gh, CodeRabbit, CircleCI, Context7, Snyk, autofix, heartbeat, and branch/worktree pruning.

Review, configure, and troubleshoot prek hooks when users need prek.toml edits, shim installs, hook validation, or pre-commit migration help.

Plan, execute, and validate production deployments when rollout safety, health checks, observability, rollback, or production-parity verification is required.

Create, validate, and repair Project Brain .harness memory files when setting up Project Brain, saving repo learnings, recording decisions, or preserving quality rules.

Create and review Rust 1.75+ systems code with ownership-safe async patterns and production error handling. Use when building or debugging Rust services that need performance and reliability.

Analyze recent Codex session evidence for repeated manual workflows and route them to skills, subagents, validators, or no artifact when Jamie asks what he keeps doing manually.

Review changed code for behavior-preserving simplification by removing dead code, eliminating duplication, extracting shared helpers, improving names, and tightening tests. Use when a user asks for code review, refactor, clean up PR, simplify, tidy up code, review my changes, or maintainability cleanup before merge.

Ship skill changes to PRs when Codex skills need source edits, rooted sync, strict audit, reviewer evidence, commit, push, and PR status.

Select, run, and report repo-native test and validation evidence. Use when users ask what tests to run, ask to validate a change, fix failing tests, design test coverage, build eval proof, classify validation failures, or prove behavior before closeout.

Create and review TOML configuration with strict typing and predictable structure. Use when editing tool configuration files that require schema-safe TOML.

Review file-based todo findings into ready, skipped, customized, or blocked states. Use this skill when pending todo files need approval.