Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing.
Composite skill — repair and validate a test suite end-to-end when: suite is bloated (test count >2× proportionality), slow (runtime >5 min), or cleanup previously stalled at…
Composite skill — runs the postmortem chain after any production incident (`/hotfix`, rollback, or prod outage acknowledged).
React composition and performance optimization patterns from Vercel. Use when building component libraries, refactoring components with prop proliferation, optimizing…
Composite skill — safely refactor a module end-to-end with sequencing, parallel implementation, post-refactor cleanup, and rationale capture.
Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak…
Audits a JS/TS codebase for hand-rolled boilerplate that a secure, well-maintained, widely-used npm package could replace, and vets each candidate for security advisories,…
Composite skill — first-touch workflow for an unfamiliar repo. Chains adt-repo-intake (understand) → audit-deep (health check) → config-drift-detect (gate audit) → init ( — from…
Audit skill catalog for rot, dead links, oversize files, and orphans. Detect stale generated artifacts, skills exceeding size limits, and skills not referenced by any composite or…
Composite skill — query, capture, improve, persist knowledge in one workflow. Chains recall (semantic lookup) → sync-memories (write note) → rag-curate (improve weak retrievals) →…
Quality assurance and continuous improvement for software projects. Covers Deming's 14 Points for Management, PDCA cycle (Plan-Do-Check-Act), Six Sigma DMAIC, total quality…
Add new area presets (professional verticals) to LinkedIn Engage for Connect, Companies, and Jobs modes.
Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.
Mandatory default entry point for any non-trivial build/add/fix/implement/refactor request — drives work through explicit spec-driven-development phases (constitution check →…
Use when the user wants browser automation, page inspection, or web research and you need to choose between public-web tools, the live browser session, or a separate browser…
Development workflow for forge-ai-init — the AI governance layer CLI. Covers architecture, dev commands, test patterns, release process, and common contribution patterns.
Guide for creating specialized Claude Code subagents with proper YAML frontmatter, focused descriptions, system prompts, and tool configurations.
Diagnose and fix macOS resource pressure for Claude Code workflows. Use when load avg is high, swap is saturated, CC feels slow, or before spinning up parallel agents/worktrees.
Composite skill — full production incident workflow from alert to post-mortem. Chains sentry (triage incoming events) → debug-deep (root cause) → incident-response (coordinate fix…
Composite skill — full debugging workflow from "this is broken" to root cause and fix. Chains systematic-debugging (root-cause hypotheses) → tracer agent (evidence walk) — from…
Configure Warp terminal to share Claude Code's MCP servers and AI rules via File-based MCP + AGENTS.md. One-time UI toggles plus file sync.
Diff the Anthropic `claude-plugins-official` marketplace against installed plugins and surface the delta, filtering known-unwanted entries (language LSPs you don't use, SaaS…
Coordinate multiple subagents/worktrees for parallel workstreams. Decomposes larger tasks into independent sub-tasks, dispatches each to a dedicated agent.
Audit project gates (jest/vitest coverage thresholds, tsconfig strictness, eslint rules, husky/lint-staged, sonar quality gate, branch protection) and flag values mathema — from…
Analyze a proposed multi-agent workflow, Workflow() script, or active session for token waste and time bottlenecks.
Reverse-engineer a live application (web app, SaaS, mobile) by walking its real flows in the browser and map every idea worth taking — UX patterns, features, visual design, copy,…
Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking
Ship validated changes with repeatable release evidence — version bump, changelog, tag, and optional GitHub release
Composite skill — take a merged PR all the way to production. Chains version-bump → changelog-update → ship (tag + release) → deployment-automation or vercel-deploy /…
Full dependency lifecycle composite — audit known vulnerabilities, triage by severity and breaking-change risk, upgrade targeted packages, verify tests pass, ship PR.
Build distinctive, production-grade interfaces with Ralph Wiggum velocity. Ships working code — web or mobile — with modern CSS, fluid typography, purposeful motion, and zero…
Fan out N independent investigations as parallel agents in a single tool-use block, then roll up the results.
Keep sessions focused and efficient — prune stale outputs, preserve active state, recommend compaction
Sync files (skills, packages/core/patterns, agents, specs) from EN canonical repo to PT mirror, inserting "Tradução pendente" blockquote after YAML frontmatter, then open PR.
How you ask the model matters more than which model you ask. Two disciplines stop most AI coding failures before they start.
Choose and configure inference servers (vLLM, TGI, Ollama) — quantization, batching, scaling, and serving patterns
Orchestrate 3–5 independent tasks in parallel with auto-dispatch and reconciliation. Use for multiple independent work items (multi-repo audits, translations, investigations,…
Regenerate `docs/roadmap.md` for a repo from all specs under `docs/specs/` + their frontmatter (status, tags, pr). Produces Now/Next/Recently-shipped sections.
Mega-composite — full greenfield feature development from idea to live. Chains research-and-decide (validate the idea + capture decision) → scope-and-execute (analysis + plan +…
Localize the LinkedIn Engage extension UI and search-query generation without mixing user-facing UI language with automation/search language.
Keep EN/PT README.md pairs in parity across a repo (and across twin repos like ai-dev-toolkit + ai-dev-toolkit-pt-br).
Brief a subagent with task context + constraints, then verify comprehension via drill before delegating real work.
Regenerate the cross-repo roadmap aggregate in your Claude memory directory by walking every curated repo's `docs/specs/**` frontmatter.
Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers.
Capture an Architecture Decision Record — what was decided, why, what alternatives were considered, and when to revisit.
A narrow, opinionated post-generation lint for backend/server-side code. Audits a changeset against a named catalogue of backend anti-patterns — swallowed errors, unvalidated…
Validate live MCP provider health — separate config issues from auth and connectivity failures
Three-layer skill quality evaluation (Static → LLM Judge → Monte Carlo). Layer 1: deterministic checks (frontmatter, triggers, size, links) in <2s.
Losslessly compress PNG and SVG assets in place and generate .webp siblings for every raster image. Use when the user asks to "compress assets", "optimize images", "shrin — from…
Detect naming conventions from existing code, then audit new or all symbols for violations. Reports inconsistencies across files without enforcing a single style.
Inspect current CI state, identify the first real blocker, separate required failures from noise, and monitor until checks settle.
Composite skill — one-pass cleanup of stale local branches, dead worktrees, merged branches, and abandoned remote PR branches.
Execute phased plans with multiple independent tasks per phase by fanning out one agent per task, reconciling outcomes per wave, gating between phases with verify commands, and…
Run a workspace backup sync on demand — rsyncs Claude/Codex configs, memories, standards, hooks, skills-index, and per-project dev files to a private git repo (e.g.
Assemble a Jira/Linear/GitHub-Issue body from recent commits, diff, and branch context
Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/.
Dispatch ad-hoc tasks to remote agent-box (agent-box scripts or free-form claude prompts). Maps named aliases (ci-watch, health, security, etc.) to shell scripts on homelab;…
UI/UX design system reference, pattern library, and focused review guidance for web and mobile applications.
Composite skill — full SEO + Accessibility audit of a website or webapp in one workflow. Chains audit-website (squirrelscan SEO + tech + perf scan) + seo-audit (SEO framing) +…
Checks that no probe command returns EC=3 (ask-rule) from `rtk rewrite` after an rtk update. In bypassPermissions mode, EC=3 causes commands to silently drop rather than prompt —…