By sorawit-w
Auto-triggering skills for Claude Code and Cowork — expertise that activates for the job at hand. Five tracks: Startup (idea to shipped), Review (product, UX, and eval critique), Code (discipline, stack choices, parallel agents), Calibration (tune how the agent works with you and write in your voice), and Language & Visuals (localization, in-context meaning, pixel art). Skills chain into pipelines and share a common harness — and you can author and audit your own.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Audit the evaluation layer of an AI product against design-completeness questions: offline criteria, ground-truth quality, online signal, cohort/disparate-impact, adversarial + robustness coverage, and drift detection. Eval-side companion to `ai-ux-review`. Produces an editable Markdown artifact plus a self-contained HTML report under `docs/ai-ux/`. Use when the user asks to "review my AI eval setup", "audit my eval design", "is my AI eval rigorous enough", "responsible-AI eval review", "fairness eval check", or "drift detection design", or ships an LLM/ML feature and wants an eval-rigor check. Invoke even if only one block is named — the others stress-test it. Does NOT trigger for: human-AI UX review (`ai-ux-review`); lean-canvas work (`validation-canvas`); adversarial pre-mortem with a verdict (`startup-grill`); SKILL.md audits (`skill-evaluator`); implementing eval pipelines, writing eval code, or labeling datasets (this skill names gaps, it does not build them).
Audit an AI product against structured human-AI design questions — classical UX (user need, mental models, trust calibration, feedback + control, graceful failure) plus the gen-AI integrity surface older frameworks miss: hallucination handling, output verifiability, provenance + citation, prompt-injection exposure, and agent autonomy. Produces an editable Markdown artifact plus a self-contained HTML report under `docs/ai-ux/`. Use when the user asks to "review my AI feature", "audit my AI product", "is my AI experience trustworthy", "responsible AI UX review", or ships an LLM feature and wants a pre-launch trust review. If `validation-canvas` output exists, assume the business model is settled and focus on UX execution. Does NOT trigger for: lean-canvas work (`validation-canvas`); adversarial pre-mortem with a verdict (`startup-grill`); SKILL.md audits (`skill-evaluator`); brand/logo work (`brand-workshop`); building eval pipelines or writing eval code (names gaps only).
Simulate a collaborative branding team to create a launch-ready brand identity package from a business overview. Use whenever the user asks to create a logo, brand identity, tagline, or brand concept for a business, product, or app — "help me brand this", "I need a logo", "come up with a tagline", "brand identity for my app" — or gives a business description and asks for visual identity work. Runs a multi-role workshop producing: a brand strategy brief, tagline, code-generated SVG logo, favicon pack, social banner set (OG/X/LinkedIn/Instagram), descriptions pack, and a starter DESIGN.md. Use it even for just a logo or just a tagline. Do NOT trigger for pitch decks or investor materials (hand off to `pitch-deck`). Do NOT trigger on revising a LIVE brand — "refresh our brand", "update our style guide", "evolve our identity", "audit our logo" — those go to `team-composer` (@brand_strategist / @senior_copywriter) and the `brand-voice:*` family. Generates net-new identity only.
Contextual definition and translation of a single word or phrase, resolved from the sentence or paragraph around it — the true in-context sense, not the dictionary default. The user names a target word/phrase and supplies surrounding text; this skill disambiguates the sense and explains it for a language learner (meaning, why this sense, register, etymology, related senses, difficulty), and can translate it contextually into another language. Triggers on "what does X mean here", "what does this word mean in this sentence", "define X in context", "meaning of X as used here", "translate just this word in context", or any word-sense / vocabulary / reading-comprehension request that supplies a target plus its context. Does NOT trigger on editing, creating, or syncing translation/locale files, adding a language to a product, or i18n JSON/YAML/TS keys — that is the `i18n` skill. Does NOT trigger on full-document translation, or a context-free dictionary lookup with no surrounding text.
Analyze a product, idea, or resource set (code, docs, URLs) against a stated goal and produce a restraint-first report on where gamification genuinely fits, and more prominently where it deliberately does NOT. Most features should not be gamified; the value is discrimination, not idea volume. SDT-anchored; avoids default Points/Badges/Leaderboards; refuses manipulation (non-droppable ethics veto). Produces an editable Markdown artifact plus a self-contained HTML report. Requires TWO inputs: the resources AND a goal/metric (it infers and confirms the goal if missing). Use when the user asks to "gamify my product", "where should I add gamification", "should I gamify X", or points the skill at a codebase/docs/URL plus a goal. Does NOT trigger for: UX review of an existing AI feature (`ai-ux-review`); designing an actual game (`team-composer` @game_designer); implementing the mechanics (suggests, then hands off); dark-pattern or engagement-maximization hacks (refused).
A personal shelf of Claude Code plugins. Hand-crafted, one skill at a time.
Specialized skills for Claude Code & Cowork — each one narrow, opinionated, and evaluated before it ships.
Claude Code (recommended) — installs the full plugin: every skill, slash-command entry points, and one-step updates.
/plugin marketplace add sorawit-w/agent-skills
/plugin install agent-skills@sorawit-w
That's it — every skill below is now on the shelf. Works from Claude Code, Cowork, and OpenAI Codex (≥ 0.133.0) — the same /plugin marketplace add + /plugin install commands run on Codex, then /reload-plugins. The repo ships native manifests for both: .claude-plugin/ for Claude Code and .codex-plugin/plugin.json + .agents/plugins/marketplace.json for Codex.
When the plugin updates, refresh once and reinstall:
/plugin marketplace update sorawit-w
/plugin install agent-skills@sorawit-w
Claude Code caches the marketplace index locally — new skills and fixes only appear after an explicit refresh.
Any agent — via npx skills. Works with Cursor, opencode, Claude Code, and any tool that reads SKILL.md files — no plugin system required.
npx skills add sorawit-w/agent-skills # the whole shelf
npx skills add sorawit-w/agent-skills --list # browse, don't install
npx skills add sorawit-w/agent-skills --skill team-composer # just one
This copies the skill folders — SKILL.md plus their references/, templates/, and hooks/ — into your agent's skills directory. It does not carry the Claude Code plugin wiring: slash-command entry points and MCP/hook registration come only via the marketplace path above.
Most skills are self-contained and install cleanly on their own. A few share resources —
defineusesi18n's locale data;startup-grill,sub-agent-coordinator, andwear-the-hatuseteam-composer's role personas.startup-auditgoes further: it has hard dependencies onteam-composer,validation-canvas, andriskiest-assumption-testand will refuse to run if they're absent — install the full set for it. Install shared skills alongside their sibling (or just grab everything) so the references resolve.
New here? Find your job and jump in. The complete map is in
docs/skill-graph.md; each skill links to its own README
for the full usage, design notes, and cross-skill pairings.
Idea to investor-ready — and each step runs standalone, so jump in anywhere.
brand-workshop → validation-canvas → riskiest-assumption-test → pitch-deck → startup-grill
full chain in How skills chain.
brand-workshop — Discovery → Concept → Creation: ships a brand identity package (logo, tagline, brief, DESIGN.md tokens).
Try:
validation-canvas — interview block-by-block into a rigorous Lean Canvas + Value Proposition Canvas.
Try:
riskiest-assumption-test — turn the canvas's stress-tests into falsifiable hypotheses with a risk×impact matrix + test plan.
Try:
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub sorawit-w/agent-skills --plugin agent-skillscerby — the gate guardian for agentic coding. A loadable rule-corpus plus opt-in guardrail hooks that govern how an AI agent does coding work: clarity over cleverness, safety over speed, never leave the repo broken, and nothing unproven passes the gate. Load it into a session, reload after compaction, install per-project hooks, prepare an existing repo, or audit a repo's conformance to the rules.
Lean agent skills for building, shipping, strategy, and growth — no context bloat.
Claude Code multi-agent team orchestration (Chinese version). Set up parallel AI agent teams with file-based planning and role-based collaboration.
Multi-agent team orchestration for parallel task execution, research, and implementation
Dynamically assemble expert agent teams for complex tasks using Claude Code's agent teams feature
Multi-agent team bootstrapper and runtime orchestrator — analyzes projects and generates tailored Claude Cadre teams via AI debate (init), then coordinates live agent teams for parallel review, debate, planning, building, and research (orchestrate)
AI team orchestration. Give Claude Code an AI team — CTO, Engineer, QA, Designer work together while you watch.