Edit existing footage into vertical 9:16 short-form videos (TikTok/Reels/Shorts) with burned-in styled captions in PT-BR — convert to 1080x1920 (center-crop or blur-pad), trim…
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 —…
Keep EN/PT README.md pairs in parity across a repo (and across twin repos like ai-dev-toolkit + ai-dev-toolkit-pt-br).
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…
Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening.
Mark a spec shipped and move it to `docs/specs/archived/`. Stamps the frontmatter with `status: shipped`, `shipped: <date>`, and optional PR URL.
Composite skill — one-pass cleanup of stale local branches, dead worktrees, merged branches, and abandoned remote PR branches.
Localize the LinkedIn Engage extension UI and search-query generation without mixing user-facing UI language with automation/search language.
Build robust, secure MCP servers — tool schemas, stateful interactions, async patterns, error handling, and testing
Recover a PR whose head SHA disagrees with its branch ref (webhook desync). Force-push and close+reopen rarely fix it — recreate the PR.
Meta-skill codifying the no-wakeup-polling pattern. Describes the ScheduleWakeup anti-pattern, the fix (--auto merge + detached watcher), and when to still use wakeups.
Optimize context window usage — compact stale data, compress via summarization, preserve active state
Improve RAG corpus quality by adding missing docs, rewriting weak chunks, and filling retrieval gaps.
Composite skill — full production incident workflow from alert to post-mortem. Chains sentry (triage incoming events) → debug-deep (root cause) → incident-response (coordinate fix…
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.
How you ask the model matters more than which model you ask. Two disciplines stop most AI coding failures before they start.
Composite skill — three-phase test quality pipeline. Chains test-health (assess state) → test-cleanup (remove redundant/brittle tests) → mutation-test (validate surviving suite).
Composite skill — full security pass across secrets, dependencies, code paths, and OWASP risks. Chains security-audit (broad) + socket-audit (npm supply chain) + semgrep (pattern…
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…
Composite skill — runs the postmortem chain after any production incident (`/hotfix`, rollback, or prod outage acknowledged).
Capture a real LinkedIn search-result card from a live profile session, sanitize it, and add it as a regression fixture.
Scan a codebase for dead code: files not imported anywhere, exports never used, dependencies declared but not called. Use before a cleanup pass to identify safe deletions.
Guide for creating specialized Claude Code subagents with proper YAML frontmatter, focused descriptions, system prompts, and tool configurations.
Create a committed per-feature spec under `docs/specs/YYYY-MM-DD-<slug>/{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags).
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…
Composite skill — take a PR from "I think it's ready" to merged with full gate verification. Chains pr-merge-readiness (verdict) → ci-watch / gh-fix-ci (if blockers) →…
Detect and fix stale chunks (files that changed or were deleted since last indexing)
Composite health audit skill — runs test-health, config-drift-detect, hook-effectiveness, performance-audit, security-audit, mcp-audit, plugin-audit, socket-audit in parallel and…
Development workflow for forge-ai-init — the AI governance layer CLI. Covers architecture, dev commands, test patterns, release process, and common contribution patterns.
End-to-end performance audit composite — baseline the slow metric, profile to find the real hotspot, implement the smallest targeted fix, re-benchmark to confirm improvement,…
Plan a code change before editing — identify files, sequence steps, set verification criteria
Scan recent git history and open issues to find architectural decisions that were made without a corresponding ADR. Use when auditing documentation coverage or before a 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 /…
Pre-push SonarCloud gate preflight — scans changed files for S5852 (ReDoS), S5144 (SSRF), and coverage gaps. Project-agnostic; auto-detects base branch and SonarCloud project key.
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who…
Fan out N independent investigations as parallel agents in a single tool-use block, then roll up the results.
Meta-skill — defines when to apply other skills automatically without being asked
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…
Use when the user asks to design database schemas, plan data migrations, optimize queries, choose between SQL and NoSQL, or model data relationships.
Choose and configure inference servers (vLLM, TGI, Ollama) — quantization, batching, scaling, and serving patterns
Decide the highest-value safe thing to do right now in the active repo or workspace. Use when triaging repo state, deciding what to work on next, or when a plan's phase c — from…
Composite skill — research a question, challenge the conclusion, plan adoption, and capture the decision.
Discover all customers of a given company by scanning websites, case studies, review sites, press, social media, job postings, and more.
Use when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y feature', 'the Z module is broken', 'foc — from…
Composite skill — full MCP server lifecycle audit and repair. Chains mcp-audit (usage stats) → mcp-health (live readiness) → mcp-doctor (fix broken servers) → suggest mcp-builder…
Full dependency lifecycle composite — audit known vulnerabilities, triage by severity and breaking-change risk, upgrade targeted packages, verify tests pass, ship PR.
Extract a cluster of pure functions from popup.js, background.js, or a content script into a new UMD module under extension/lib/.
Composite skill — promote the long-lived `release` branch to `main`, cut a single version that batches every PR accumulated since the last tag, then clean up.
Show status table for multiple PRs in one batch API call with color indicators
Composite skill — design, scaffold, build, and verify a UI in one workflow. Chains ui-ux-pro-max or web-design-guidelines (audit/principles) → shadcn or tailwind-design-system…
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) +…
Composite skill — audit and deepen codebase architecture in one orchestrated workflow. Chains: coupling-map → orphan-hunt → improve-codebase-architecture → domain-modeling →…
Fan out N independent investigations as parallel agents in a single tool-use block, then roll up the results.
AI coding agents fail in consistent, predictable ways. They fabricate npm packages that don't exist. They catch errors and continue silently.
Build a compact, validation-gated implementation plan for multi-step, risky, or ambiguous work — typically when phases need explicit checkpoints, the change touches multiple…
Bump the ai-dev-toolkit version pin in a downstream consumer repo and verify the sync path
Manually improve corpus quality by adding missing docs and filling retrieval gaps
Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/.
Pre-build audit with dedup checks before creating new skills or agents. Check existing agents/skills before creating new ones.
Analyze a proposed multi-agent workflow, Workflow() script, or active session for token waste and time bottlenecks.