Orient on a project or project family. Shows recent activity, milestones, and commits from event logs.
RAG 시스템 품질 평가 및 개선을 위한 스킬입니다. RAGAS 기반 LLM-as-Judge 평가, 사용자 페르소나 시뮬레이션, 합성 데이터 생성, 평가 결과 저장 및 분석 기능을 제공합니다. — from LucasSantana-Dev/sharekit
Build production-grade frontend interfaces that look like they came from Linear, Vercel, Stripe, Notion, Raycast, or Apple — not from an LLM.
Set up Langfuse LLM observability to trace Claude API calls with costs, tokens, and latency
Scan recent session JSONLs and PR descriptions for skills that bailed out, returned "out of scope", or reported diagnostics without action.
Flag over-engineering — speculative abstractions, premature generalization, single-use "flexibility", unnecessary indirection, config for things that never vary, and patterns…
Take a labeled snapshot of repo state (sha, open issue count, open PR count, latest release, drafts, uncommitted files) and optionally diff against a prior snapshot.
Audit project gates (jest/vitest coverage thresholds, tsconfig strictness, eslint rules, husky/lint-staged, sonar quality gate, branch protection) and flag values mathema — from…
Read-only diagnostic that reports the state of a project's test suite — count vs. proportionality, coverage vs.
Aggregate CI, reviews, conflicts, branch staleness, and third-party checks (CodeRabbit, Sonar, Greptile, Socket) into a single MERGE / WAIT / FIX verdict.
Reduces Claude Code context bloat across three dimensions: (1) duplicate skill deduplication — clears .claude/ copies since Claude Code already reads from plugins/ directly; (2)…
Audit and prune a bloated test suite down to the minimum tests that hit the coverage threshold and guard real behavior.
Standalone post-generation QA pass that lints any frontend output (HTML/JSX/Vue/Svelte/CSS) against the named anti-pattern catalogue and proposes specific rewrites with severity…
Run Socket.dev supply chain security audit on npm dependencies for malicious packages and typosquatting
Audit Claude Code hooks for fire frequency, latency, exit codes, and output value. Surfaces hooks that never fire, hooks that fire too often (spam), hooks that exit non-zero…
Atomic PR creation workflow — branch-first, conventional commits, no direct main push. Use when: - packaging staged work into a reviewable PR with minimal git overhead -…
Single entry point for ALL frontend building and restyling — any page, component, dashboard, landing page, app shell, modal, settings panel, onboarding flow, hero, pricing…
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.
Ship validated changes with repeatable release evidence — version bump, changelog, tag, and optional GitHub release
Audit project memory files for stale entries — items where the cited PR is merged, the cited bug is fixed, the cited file/function no longer exists, or the gotcha was patched out…
Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas.
Three-layer skill quality evaluation (Static → LLM Judge → Monte Carlo). Layer 1: deterministic checks (frontmatter, triggers, size, links) in <2s.
Composite skill — one-call answer to "merge this?", "ship this?", "ready for merge?". Chains: pr-merge-readiness (verdict) → ci-watch/gh-fix-ci/gh-address-comments (resolve…
Shortcut for security review on current change set. Runs layered checks (secret-scan, dep-audit, semgrep, OWASP patterns, prompt-injection review).
Composite skill — full project health check across testing, config, hooks, performance, security, MCP, and plugins.
Sync ~/.claude/ (skills, hooks, standards, CLAUDE.md, agents) into the public sharekit profile repo, sanitize personal paths/identity, scan for secrets, show diff, and…
Run mutation testing against a project's test suite to verify the tests actually catch failures when source code is broken.
Audit and prune a bloated test suite down to the minimum tests that hit the coverage threshold and guard real behavior.
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…
Audit corpus distribution by source type and repo; identify coverage gaps and underindexed topics
Audit project gates (jest/vitest coverage thresholds, tsconfig strictness, eslint rules, husky/lint-staged, sonar quality gate, branch protection) and flag values mathema — from…
Recover session state from git, plans, and open PRs, then continue from the last completed phase without repeating work
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.
Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing.
Composite skill — land a safe first PR in an unfamiliar repo without rediscovery loops or guessing at conventions.
Mega-composite — full greenfield feature development from idea to live. Chains research-and-decide (validate the idea + capture decision) → scope-and-execute (analysis + plan +…
Validate live MCP provider health — separate config issues from auth and connectivity failures
Composite RAG maintenance skill — runs a full retrieval index audit end-to-end: measure quality, find corpus gaps, detect stale chunks, and curate (add missing docs, rewrite weak…
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…
Orchestrate teams of agents — DAG execution, routing, state sharing, failure recovery. Use when coordinating parallel agents in task pipelines with dependencies or distributing…
Automate CHANGELOG.md maintenance: promote [Unreleased] → versioned section, compute version bump (major/minor/patch), update package.json + src/index.ts VERSION constant, commit,…
Scans a codebase for self-contained, low-coupling modules (often a secondary part of a feature — a util, parser, state machine, algorithm) that are generic enough to reuse across…
Capture an Architecture Decision Record — what was decided, why, what alternatives were considered, and when to revisit.
Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain).
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…
Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking
Compact session-bootstrap brief — answers "what was I doing, what's blocking, what's next" in ~600-900 tokens.
Brief a subagent with task context + constraints, then verify comprehension via drill before delegating real work.
Decide the highest-value safe thing to do right now in the active repo or workspace. — from LucasSantana-Dev/forgekit
Composite: end-to-end refactor with plan, parallel 3-agent implementation, test cleanup, ADR capture, and sync.
Orchestrate 3–5 independent tasks in parallel with auto-dispatch and reconciliation. Use for multiple independent work items (multi-repo audits, translations, investigations,…
Composite skill — understand a problem area, plan the work, execute it, and ship it in one chained workflow.
Composite skill — evaluate library/pattern/architecture choices by chaining research → critic challenge → adoption plan → ADR record → vault index.
Regenerate `docs/roadmap.md` for a repo from all specs under `docs/specs/` + their frontmatter (status, tags, pr). Produces Now/Next/Recently-shipped sections.
Diagnose and repair failing MCP servers. Captures real launch tracebacks, identifies stale tool/config references, prunes the bad entries, and reconnects.
Sync durable project/session knowledge into memory systems so future sessions have accurate context. Use after meaningful work completes (PR merged, feature shipped, release…
Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak…
Force a decision when the agent is stuck in analysis paralysis, going in circles, or repeatedly weighing options without committing.
Keep sessions focused and efficient — prune stale outputs, preserve active state, recommend compaction
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,…