All authors
Claude Skills by ngocsangyem
github.com/ngocsangyem330 skills0 installs698 views
- ReferenceSkills have become one of the most used extension points in Claude Code. They’re flexible, easy to make, and simple to distribute. But this flexibility also makes it hard to know what works best. What type of skills are worth making? What's the secret to writing a good skill? When do you share them with others? We've been using skills in Claude Code extensively at Anthropic with hundreds of them in active use. These are the lessons we've learned about using skills to accelerate our development.Votes: 0GitHub stars: 14
- Sample SkillSample skill for fixture purposes — small enough to land below noise floor.Votes: 0GitHub stars: 14
- AdviseTurn a raw idea into ONE honest recommendation: interview one question at a time until the problem, requirements, goals, non-goals, and constraints are CONFIRMED, then deliver a single verdict — do, don't, cheaper alternatives, trade-offs, ordered checklist, success metrics. Required: the user wants exactly ONE recommendation — not options, not a debate — and their framing is open to challenge (advise may answer a different question than the one asked). Triggers on "what should I do about X",...Votes: 0GitHub stars: 14
- Api Design PrinciplesDesign and review durable REST, GraphQL, RPC, or event-facing API contracts. Use for public or shared API contracts, endpoint/schema consistency, compatibility, pagination, error semantics, and API documentation. Discovers existing consumers and conventions before recommending a style.Votes: 0GitHub stars: 14
- Ask MeUse when answering factual or explanatory questions about the current project — codebase, architecture, conventions, workflows, constraints — with minimal cited evidence. Triggers on "how does X work here", "what does X mean", "why is X structured this way", "is this claim true in the repo", "explain X with sources". NOT for brainstorming or comparing approaches (mk:brainstorming), trade-off decisions (mk:party), debugging/root cause (mk:investigate), code review (mk:review), plans (mk:plan-c...Votes: 0GitHub stars: 14
- AutobuildUse when running an autonomous multi-hour build of a green-field product — orchestrates planner → contract → generator ⇄ evaluator loop with adaptive scaffolding density per model tier. Triggers on /mk:autobuild, "build me a kanban app", "build a retro game maker", "autonomous build", or any green-field product spec. NOT for scoped single-task work (see mk:cook); NOT for initial project scaffolding only (see mk:bootstrap).Votes: 0GitHub stars: 14
- Backend DevelopmentDesign and implement backend service changes: API contracts, service boundaries, auth integration, reliability and delivery checks. Use for backend/API handlers, services, webhooks, jobs, or backend architecture changes. Routes schema/migrations to mk:database; security review to the existing security workflow.Votes: 0GitHub stars: 14
- Chrome ProfileTarget a specific Google Chrome user profile for browser automation via CDP. Discovers installed profiles from the Chrome Local State file, launches Chrome with the requested profile attached to a debug port, and connects agent-browser via `agent-browser connect <port>`. Use when "automate using my Work/Personal Chrome", "open site with my saved session", or "use Chrome profile named <name>". NOT for headless scraping without an existing user profile (use mk:agent-browser directly); NOT for i...Votes: 0GitHub stars: 14
- Context EngineeringRuntime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overh...Votes: 0GitHub stars: 14
- DevopsPlan and implement infrastructure, containers, CI/CD, deployment safety, observability, and rollback changes. Use for Docker, IaC, cloud runtime, Kubernetes, pipeline, deployment, or operational reliability work. Does not read dotenv files or approve/release deployments.Votes: 0GitHub stars: 14
- GhpmGitHub project management via the gh CLI — create and triage issues, manage GitHub Projects v2 boards (add items, update status fields), manage labels and milestones, and generate handoff-status summaries. Use when "create a GitHub issue", "add to project board", "update sprint status", "create label/milestone", or "give me a handoff summary of open work". NOT for code review (see mk:review-pr); NOT for PR creation (see mk:ship); NOT for git operations (see mk:ship / mk:resolving-merge-confli...Votes: 0GitHub stars: 14
- GrillRelentlessly interview the user about THEIR plan or design — one question at a time — resolving each branch of a decision tree until shared understanding. Claude is the interviewer; the user is the interviewee. Triggers on "grill me", "stress-test this plan", "get grilled on my design", "interrogate my plan". Checkpoints every answer to docs/knowledge/<slug>.md so progress survives a context-window reset. Flags knowledge the user cannot answer as a gap to chase. Do NOT use to PROPOSE solution...Votes: 0GitHub stars: 14
- Html VideoRender an HTML/CSS/JS template to a local MP4 video by capturing frames with headless Chromium (via Playwright) and encoding them with ffmpeg. Use when "render my animation as a video", "export HTML to MP4", "make a video from my web template", or "capture CSS animation as MP4". NOT for recording live browser interactions (use `agent-browser record start`); NOT for screen recording; NOT for AI video generation (use mk:multimodal).Votes: 0GitHub stars: 14
- Improve Codebase ArchitectureUse when surfacing architectural friction and proposing deepening refactors (shallow modules → deep modules) for testability and AI-navigability. Triggers on "improve architecture", "find deepening opportunities", "where is this codebase shallow", "architecture review". Emits structured candidates + precise patches; delegates ALL rendering to mk:preview. NOT for diagram/HTML rendering (see mk:preview); NOT for trade-off deliberation (see mk:party); NOT for plan critique (see mk:plan-ceo-review).Votes: 0GitHub stars: 14
- LoopUse when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, ''optimize coverage/bundle size/lint count'', ''iterate until the metric improves''. NOT for subjective cleanup (see mk:cook), known-root-cause bugs (see mk:fix), behavioral grading (see mk:evaluate), or shipping (see mk:ship).Votes: 0GitHub stars: 14
- Markdown ReaderServe any markdown file or directory as a calm, book-like reader via a local HTTP server (127.0.0.1 only). Best for long-form documents — RFCs, runbooks, design docs, plan files — where comfortable in-browser reading matters. Supports Mermaid diagrams, dark/light mode, plan navigation sidebar, and keyboard shortcuts. Requires explicit start and stop lifecycle.Votes: 0GitHub stars: 14
- Mermaidjs V11Create inline Mermaid v11 diagram blocks — flowcharts, sequence, class, ER, Gantt, state, timeline, user-journey, and 20+ other types — rendered in markdown files and browser environments. Zero external dependencies; mmdc is optional for CLI export.Votes: 0GitHub stars: 14
- OrchestrateCoordinates staged or parallel jobs across live-verified coding-agent runtimes (Claude Code, Codex, Cursor, and other installed CLIs) and in-session toolkit subagents. Routes each job by capability and risk tier, isolates parallel writers in git worktrees, captures redacted output, resumes interrupted runs, and blocks completion until an independent arbiter verifies the results. Use when work should be split across multiple runtimes or subagents, run as staged or parallel jobs, and reviewed b...Votes: 0GitHub stars: 14
- ResearchUse when a decision needs deep multi-source technical research with cited evidence — technology evaluation, ecosystem comparison, standards/spec fact-finding, "how do others solve X". Triggers on "research X", "deep dive on X", "evaluate X vs Y", "find best practices for X". NOT for library/API doc lookup (see mk:docs-finder); NOT for one-shot URL fetch (see mk:web-to-markdown); NOT for internal codebase discovery (see mk:scout); NOT for project-only Q&A (see mk:ask-me); NOT for comparing sol...Votes: 0GitHub stars: 14
- Resolving Merge ConflictsResolve an in-progress git merge or rebase conflict end to end: read the conflict state, recover each side's original intent, resolve every hunk, run the project's checks, and prepare the merge/rebase for an explicitly approved finish. Use when asked to "resolve merge conflicts", "fix this rebase", "finish the merge", or when `git status` shows conflicted (unmerged) paths. NOT for the full ship pipeline that merges the base branch first (see mk:ship); NOT for debugging a runtime bug or test f...Votes: 0GitHub stars: 14
- Respond PrTriage reviewer comments on a GitHub PR with receiving-code-review discipline — verify each against the codebase, then accept/push-back/clarify, and optionally reply in-thread. Use when responding to received PR feedback. NOT for giving a review (see mk:review-pr); NOT for implementing the fixes (hand off to mk:fix).Votes: 0GitHub stars: 14
- Review PrReviews a GitHub PR with a single shallow correctness/security/breaking/AI-slop checklist and emits a verdict; optionally posts it via gh pr review. Use to review an external or teammate PR. NOT for deep pre-landing audit of your own diff (see mk:review); NOT for responding to received review comments (see mk:respond-pr).Votes: 0GitHub stars: 14
- ShowcaseCreate a self-contained, visually polished HTML showcase page for a topic or set of artifacts. Supply a mission (topic summary) and optional artifact paths explicitly — the skill never auto-scans the repo. Writes output to assets/showcase/<mission>/. Screenshots are optional (requires Puppeteer). Publishing is local-only by default; publish requests without a configured path fail clearly.Votes: 0GitHub stars: 14
- StitchGenerate novel UI from a text prompt via Stitch AI. Exports Tailwind/HTML, produces DESIGN.md for mk:frontend-design handoff. NOT for implementing existing designs — use mk:figma or mk:frontend-design for that.Votes: 0GitHub stars: 14
- Tech GraphGenerate publish-grade SVG+PNG technical diagrams — architecture, data flow, flowchart, sequence, agent-memory, class, ER, state-machine, comparison, timeline, and more — across 8 visual styles. Writes output to tasks/visuals/ or an active plan's visuals/ directory. Requires rsvg-convert (librsvg) for PNG export; degrades gracefully to SVG-only when absent.Votes: 0GitHub stars: 14
- Visual PlanUse when a plan directory (plan.md + phase-*.md) needs a visual review. By DEFAULT this drives the STRUCTURED visual-plan artifact (visual-plan/plan.json) via the mewkit visual-plan CLI — generate if absent, validate, open the local studio (view/edit), and export plan.html from the approved artifact. Pass --static for the legacy prompt-only single-file plan.html template render. Triggers on "render this plan", "visualize the plan", "open the plan studio", "make a shareable plan page", "plan.h...Votes: 0GitHub stars: 14
- Vue Best PracticesUse for deep Vue 3 best-practices review, recommendations, and the full ordered authoring workflow — built-in components (Teleport, Suspense, KeepAlive, Transition, TransitionGroup), animation techniques, slots, fallthrough attrs, custom directives, async components, render functions, plugins, and the post-functionality performance pass. Complements mk:vue (the everyday Composition API quick-reference). Invoke for "review my Vue", "Vue best practices", "recommend improvements", or non-trivial...Votes: 0GitHub stars: 14
- Vue Testing Best PracticesUse for Vue 3 testing best-practices review and recommendations — designing and auditing Vitest + Vue Test Utils tests for components, composables, Pinia stores, Vue Router, async/Suspense, Teleport, forms, and accessibility, plus Playwright E2E test-design strategy. Advisory/review only — recommends patterns and flags test smells; does not run tests. Complements mk:vue-best-practices (feature code). Invoke for "review my Vue tests", "how should I test this component/composable/store", or "Vu...Votes: 0GitHub stars: 14
- Wiki RenderRender a wiki into ONE self-contained HTML snapshot (pages + provenance) that opens offline — no CDN, no remote assets, page content HTML-escaped. Use to share or review accumulated wiki knowledge as a static page. NOT for capturing/approving knowledge (see mk:wiki); NOT for generic code/diagram visuals (see mk:preview).Votes: 0GitHub stars: 14
- Wiki ResearchFetch external sources (web / arXiv / GitHub) and turn them into scanner-gated wiki CANDIDATES — never canonical pages. Every fetched byte is DATA; url-guarded, size-capped, redirect-re-validated, injection-scanned, and secret-scrubbed before a candidate is even created. Requires network. NOT for capturing local knowledge (see mk:wiki); NOT for one-shot page-to-markdown (see mk:web-to-markdown).Votes: 0GitHub stars: 14
- WikiCapture, gate, query, and render long-term project knowledge through the gated `mewkit wiki` subsystem. Use to create a wiki, propose/approve candidates (scanner-gated), hand off a skill's terminal artifact as a scanned candidate, recall context, search the FTS index, or list pages. Agents may only PROPOSE candidates; canonical pages are written only via human approve. NOT for short-lived JSON memory (see mk:memory); NOT for fetching external sources (see mk:wiki-research); NOT for HTML snaps...Votes: 0GitHub stars: 14
- Demo SkillDemonstration skill exercising reference categoriesVotes: 0GitHub stars: 14
- Mk AdviseTurn a raw idea into ONE honest recommendation: interview one question at a time until confirmed, then give a verdict with trade-offs and a checklist. Not for options or debate.Votes: 0GitHub stars: 14
- Mk Agent BrowserBrowser automation CLI for agents: navigate, click/fill, screenshot, extract data, test apps, Electron/Slack, cloud browsers. NOT for the user's real Chrome profile/cookies (mk:chrome-profile).Votes: 0GitHub stars: 14
- Mk Agent DetectorDetects the right agent and complexity tier at Phase 0 orient; runs first in every workflow. NOT for runtime agent routing inside a single skill.Votes: 0GitHub stars: 14
- Mk AngularAngular v20+ patterns: components, signals, services, forms, routing, HTTP, testing, SSR. Auto-activates on .ts files in Angular projects (angular.json detected).Votes: 0GitHub stars: 14
- Mk Api Design PrinciplesDesign and review durable REST, GraphQL, RPC, or event API contracts: shape, compatibility, pagination, error semantics. Discovers existing consumers first. Not implementation, schema, or release.Votes: 0GitHub stars: 14
- Mk Ask MeAnswer factual project questions (codebase, architecture) with cited evidence. NOT for brainstorming, trade-offs (mk:party), debugging (mk:investigate), review (mk:review), or plans (mk:plan-creator).Votes: 0GitHub stars: 14
- Mk AutobuildRuns autonomous multi-hour green-field builds: planner, contract, generator/evaluator loop, scaffolding density per model tier. NOT for scoped tasks (mk:cook); NOT for scaffolding only (mk:bootstrap).Votes: 0GitHub stars: 14
- Mk Backend DevelopmentDesign and implement backend changes end to end: endpoints, handlers, services, integrations, webhooks, jobs, authenticated access. Routes contracts to api-design-principles, schema to database.Votes: 0GitHub stars: 14
- Mk BenchmarkExperimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.Votes: 0GitHub stars: 14
- Mk BootstrapBootstraps a new project end to end: research, design, plan, scaffold, implement, docs. Explicit invocation only. NOT for autonomous builds (mk:autobuild); NOT for existing-repo work (mk:cook).Votes: 0GitHub stars: 14
- Mk BrainstormingGenerate or compare multiple technical approaches for one validated decision. NOT for product discovery or refining an existing plan.Votes: 0GitHub stars: 14
- Mk Build FixBuild error triage: detect language, load fix patterns, auto-retry. Chains into mk:verify. NOT for runtime errors (mk:fix); NOT for architecture debugging (mk:investigate).Votes: 0GitHub stars: 14
- Mk CarefulSession-scoped guardrails warning before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, etc; user can override. NOT for scoping edits to a directory (mk:freeze).Votes: 0GitHub stars: 14
- Mk ChomCopies or adapts features from external repos/apps into this project. Triggers on 'copy this from', 'replicate'. NOT for packing this project (mk:pack); NOT for URL fetches (mk:web-to-markdown).Votes: 0GitHub stars: 14
- Mk Chrome ProfileTarget a specific Chrome profile for browser automation via CDP: discovers profiles, launches on a debug port, connects agent-browser. NOT for headless scraping without a profile (mk:agent-browser).Votes: 0GitHub stars: 14
- Mk Clean CodeEnforces KISS/DRY/YAGNI during authoring and ad-hoc reviews: concise, direct, no unneeded comments. NOT for post-hoc diff/PR review (mk:review); NOT for simplification passes (mk:simplify).Votes: 0GitHub stars: 14
- Mk Confluence BulkBulk Confluence ops (10+ pages): bulk-label/move/delete via confluence-as; dry-run mandatory. NOT single-page (mk:confluence-page) or comments/attachments (mk:confluence-collaborate).Votes: 0GitHub stars: 14
- Mk Confluence CollaborateConfluence comments, attachments, labels, watchers via confluence-as. Inline-vs-footer safety enforced. NOT page CRUD (mk:confluence-page) or bulk ops (mk:confluence-bulk).Votes: 0GitHub stars: 14