pixel-diff
Pixel-level image comparison between two screenshots. Generates a visual diff overlay highlighting differences. Use for comparing Figma designs against web implementations.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
git-conventional-commits
Professional git commit workflow with Conventional Commits format. Enforces commit type categorization (feat, fix, docs, style, refactor, perf, test, build, ci, chore), validates messages against the 7 rules of great commits, previews before committing, and supports multiple languages. Use when you need to create high-quality, traceable git commits.
logic-coder
Vue 3 前端邏輯技能（邏輯 Agent）。接收 enriched-spec.md（含 API 對應表、State 結構定義、錯誤處理方案），將切版完成的純展示元件（Dumb Components）與 API / 狀態管理邏輯整合，產出可執行的容器層、services、composables。觸發情境包含：接續 api-enrichment 完成後的邏輯實作、「幫我串 API」、「實作資料邏輯」、「加上 loading / error 狀態」、「幫我寫 composable」、「實作 Pinia store」、提到 enriched-spec.md 或 component_paths handoff payload 的情境。
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vue-layout
Vue 3 + SCSS 切版技能（切版 Agent）— 像素級精確實現。從 Figma 設計稿生成 **1:1 視覺保真的** Vue 3 純展示元件（Dumb Components）。觸發情境包含：「幫我切版」、「根據 Figma 產出元件」、「根據 spec 建立 UI」、「幫我建 Vue 元件」、「切這個畫面」、「實現 Figma 設計」、「補切版」、有提到 Figma URL 或 Node ID 加上 Vue/元件/切版等字詞。保證顏色、間距、字號、圓角、邊框等像素級精確匹配，同時支援與規格流程集成（使用 `draft-spec.md` 或 handoff payload 增強理解）或無規格快速實現。只要上游提供了核准 node 清單，就必須先做 node-to-component mapping 與 coverage 自查，未覆蓋 node 不得宣稱切版完成。僅產出 props/emits 介面的純 UI 結構，不含 API 呼叫或業務邏輯。
vue3-best-practices
Vue 3 performance optimization and best practices guidelines for modern frontend applications. This skill should be used when writing, reviewing, or refactoring Vue 3 code to ensure optimal performance patterns, proper Composition API usage, and modern development practices. Triggers on tasks involving Vue 3 components, Composition API, reactivity, state management, or performance optimization.
react-agent
Pragmatic React development focused on avoiding over-engineering, effective state management, and render optimization. Use when building React components or features where you need clear guidance on (1) choosing appropriate state management solutions, (2) optimizing component rendering and performance, (3) avoiding common over-engineering patterns, (4) implementing TypeScript with React, or (5) making architectural decisions that balance simplicity with scalability.
codex-app-themer
Turn an image, a theme URL, or a loose aesthetic description into a valid portable Codex app theme string. Use this when someone wants a `codex-theme-v1:` import for Codex.app and needs the result clearly labeled as a dark or light theme.
crawl-to-markdown
Use when web.run fails to parse a webpage and you need raw Markdown via Crawl4AI.
youtube-transcript
Use when a YouTube video transcript is needed e.g. for summarisation or Q&A on the content.
tailscale-serve
Expose a local dev server (localhost port) as a tailnet-only HTTPS URL using `tailscale serve`, and show the resulting ts.net URL.
ultrathink
Run deep plan-first analysis. Use when the user explicitly asks for ultrathink (for example, "plan this first with ultrathink").
debug-tauri
Automates Tauri WebView debugging using official plugins (tauri-plugin-log + screenshots) with process verification, automated screenshots, console logs, and state analysis. Use when debugging Tauri apps, investigating WebView issues, analyzing runtime errors, or troubleshooting UI problems.
demand-mining
|
requirements-analyst
需求分析助手，将模糊需求转换为结构化文档。支持两种输出格式：用户故事（User Story）适合敏捷开发，PRD（产品需求文档）适合完整功能规划。通过针对性提问澄清歧义。
code-review-assistant
Comprehensive code review assistant that analyzes code for security vulnerabilities, performance issues, and code quality. Use when reviewing pull requests, conducting code audits, or analyzing code changes. Supports Python, JavaScript/TypeScript, and general code patterns. Includes automated analysis scripts and structured checklists.
ship-vercel-app
Deploy a local web app idea from this Mac to production using a new GitHub repository and Vercel GitOps. Use when the user asks to ship, launch, deploy, productionize, or publish a local app/site from ~/code or another local folder, especially with GitHub, Vercel, custom domains, Cloudflare DNS, or "from this Mac mini to production".
pr-review
Single entry point for reviewing a PR, diff, or branch. Owns the goal-conformance pass — does this achieve its stated purpose, for every input, not just do the lines look fine — and dispatches specialist reviewers (complexity, security, AGENTS.md staleness) in parallel as subagents, then merges everything into one report. Use when reviewing a pull request, diff, or branch, especially when the change instruments, transforms, routes, or tags data over a set of inputs, or claims to do something "for all X".
pr-work-log
Surface off-PR work on the pull request as a maintained comment. Triggers when, while a PR is open, you do work tied to that PR that the diff does NOT show — dispatching/watching GitHub Actions runs, running a backfill/migration/data job, writing to a database, kicking off manual workflows, validation runs, or anything happening in CI/Actions/a DB/an external system. Keeps a single "Off-PR work log" comment up to date as each step lands.
reflection
Interrogate your own just-completed work with three questions — what you're least confident about, what you claimed works but never verified, and the biggest thing you're probably missing. Use when the user runs /reflection, says "reflect on that", "check yourself", or after finishing a non-trivial chunk of work where confident-but-wrong is a real risk.
ship
>-
understanding-first
>
use-browser
Default protocol for browser automation. Load this skill FIRST whenever any task requires opening a browser, reading a webpage, filling a form, clicking buttons, taking screenshots, scraping data, or any web interaction. Defines the startup sequence, tool priority, and failure protocol so agents always try the right way first and stop on failure instead of guessing alternatives.
write-pr-description
>-
tdd
Comprehensive guide for Test-Driven Development (TDD) methodology. Use this skill when the user asks to implement features using TDD, write tests first, follow red-green-refactor cycle, or develop code with test-first approach. Also use when user mentions TDD, unit testing workflow, or wants to refactor code with test coverage.
write
>-
live-review
Review an HTML file from Claude with inline comments. Spins up a Claude Code custom channel that serves the HTML with a commenting widget; the reviewer's comments are pushed into a dedicated reviewer Claude session that edits the file and replies in-page. Use when the user produces or has an HTML report/draft/output and wants to comment on it, mark it up, or iterate on it visually — triggers on "review this HTML", "let me comment on", "open for review", "live review", or finishing a draft HTML file. Also triggers whenever the user asks to "create an HTML" (or build/generate/make an HTML file/page/report): after producing it, proactively SUGGEST opening it in live-review — offer the command, don't auto-launch.
persona-reader-site
Build a single-file reading site for any person or company from their tweets (ranked by engagement) and long-form writing (blogs, Medium, RSS). Use when the user says "build/refresh a reader site for <person/company>", "scrape <handle>'s tweets and writing into a site", "make Karpathy's writing easier to read", "turn <someone>'s posts into a mini site", or wants a personal index of someone's public output. Backed by Camoufox (stealth Firefox) + a logged-in X profile.
agents-md-review
Review a PR/diff for whether it makes the repo's AGENTS.md or CLAUDE.md stale, and audit those two files for anti-patterns (generic filler, tools named without runnable commands, stale paths). Classifies the change's materiality High/Medium/Low and demands an instructions update for High. Use as the AGENTS.md reviewer in a review panel, or when asked whether a change needs an AGENTS.md/CLAUDE.md update.
babysit-pr
>-
claude-code-session-tracker
Append unfinished Claude Code sessions to a tracker file so they can be resumed via `claude --resume "<session name>"`. Trigger when user signals ending ("done for now", "wrap up", "goodbye"), hits rate/context limit, or asks to save/track the session. Skip short one-offs, clean completions, or trivial Q&A.
goal-audit
Audit a goal against the six qualities of a well-formed goal and rewrite it if it falls short. Triggers whenever the user states a goal, objective, or "what done looks like" for a task — phrases like "the goal is", "I want to", "make this better", "my objective is", "get X working", "build/fix/improve Y" — and whenever the user runs /goal-audit. Use this BEFORE starting work on any non-trivial task so the goal is auditable and has a real finish line, not just when the word "goal" appears. A vague goal gives no completion condition; this skill catches that early.
learn-quiz
Teacher mode after the agent has done work in a session. Verifies the human deeply understands what was done — problem, solution, design decisions, edge cases, broader impact — via incremental restating, gap-filling, and AskUserQuestion quizzes, tracked in a running checklist doc. Use when the user says "teach me this session", "make sure I understand", "quiz me on what you did", "/learn-quiz", or wants to learn from the work just completed. Session should not end until understanding is demonstrated.
loose-ends
End-of-session cleanup sweep. Triggers when the user signals they're wrapping up — "what else to wrap up before I end", "wrap up", "done for now", "anything left", "before I end", "loose ends", "clean up". Sweeps for uncommitted/unpushed work, stale branches & worktrees, leftover files & dev processes, ssh-key state, unverified changes, and unsaved knowledge — auto-doing the safe checks, asking before anything that could lose work.
codify-writing
>-
create-video-recording
Create PR-ready video verification artifacts for UI, report, browser, visual, or human-reviewable changes. Use when the user asks to record a demo, create a video recording, demo this, make a verification video, produce proof for a PR, prepare the PR Verification section, or when a change is demoable before review. Also use before `gh pr create` for product-visible changes and when building verification reports that should embed or link to a demo video.
eat-like-japanese-local-foodie
Research restaurants the way local Japanese foodies would. Use when Codex needs to find, compare, rank, or document what to eat in Japan for a trip, especially when the user asks for local Japanese recommendations, foodie picks, Tabelog, Hyakumeiten, Michelin Japan, Japanese beef, ramen, coffee, cafes, family-friendly meals, or Japan city/area food surveys.
explain-diff
Use when the user asks for a rich explanation of a code change, diff, branch, or PR — "explain this diff/PR/change", "walk me through what changed", "help me understand this branch". Produces a single self-contained interactive HTML explainer (background → intuition → code walkthrough → quiz). Geoffrey Litt's /explain-diff prompt, verbatim.
linkml-engineering
The operational LinkML craft, downstream of an existing model or spec — never greenfield. Use to derive a LinkML schema from a UML model, a text spec, a model2owl output, or another existing model; to author/refine it (reusable slots, the URI-as-datatype artifice, implicit class_uri/slot_uri, enums, schema-level constraints); to generate the full target set (Pydantic/JSON Schema/OWL/SHACL/TS/SQL) with custom templates and make-target automation including diagrams; and to establish LinkML quality gates. Trigger on "write/derive a LinkML schema", "generate models/OWL/SHACL from LinkML", "custom Pydantic template", "LinkML quality gates", "per-module generation", "make generate-models". Reuses modelling-conventions for generic craft; defers the model concept to conceptual-modelling. Not an ontology-authoring skill.
architecture
System-level solution architecture — C4 levels (Context, Container, Component, Code), ArchiMate and UML notations, ADRs, and contracts (OpenAPI/AsyncAPI/LinkML). Use for system and solution design, architecture documentation, and architectural decision-making. Distinct from code structure inside a service (see the cosmic-python skill).
bdd-gherkin
Write BDD Gherkin feature files and fabricate test data from a specification. Use to project a use case catalogue (Cockburn White/Blue) or turn acceptance criteria or an EPIC into business-language `.feature` scenarios — Scenario Outline with Examples, explicit edge cases, no implementation detail, traced back to use cases. Trigger on "write Gherkin", "write feature files", "BDD scenarios for this acceptance criterion", "derive scenarios from use cases", "fabricate test data".
explanatory-writing
Apply explanatory craft so that Explanation-quadrant prose reads clearly — one controlling metaphor, a concrete example beside every abstract claim, self-answered question pivots, short declaratives, coin-and-explain, a confident grounded close. Use when writing or improving an explainer, a blog-style or internal explanation, or broad-audience teaching prose (Diátaxis Explanation; not Reference or How-to). Trigger on "make this explainer clearer", "why does this read flat", "write a blog-style explanation", "add a worked example or metaphor", "tighten the rhythm of this prose". Executes the Meaningfy technical/educational register from `company-voice.md`. Owns texture, not document structure (`executive-communication`) or doc placement (`technical-writing`).
ci-cd-delivery
Standardise the application-repo Continuous Delivery side of Meaningfy systems — the deploy trigger, the reusable deploy mechanism, and the release/image standard. Use to set up a CD/deploy workflow, release and push a versioned Docker image to a registry (recommended GHCR, tagged by semver + git sha), standardise or migrate the deploy trigger, kill the duplicated SSH/bastion/rsync/.env deploy block by consuming the canonical reusable workflow, or understand the three-repo deploy model. CI (build, test, lint, coverage, architecture, docs publish) is NOT here — that is owned by project-setup; this skill owns only CD + release + the delivery contract. Trigger on "set up CD / deploy workflow", "release and push a versioned image", "GHCR image build", "standardise the deploy trigger", "migrate the duplicated deploy block", "how do we deploy this repo".
technical-writing
Produce clear documentation, explanations, summaries, and docstrings — AsciiDoc/Antora or Markdown — with a lightweight clarity check. Use to write or improve project docs, explain how a module works, summarise an area, or add docstrings. Trigger on "document this", "write docs/README", "explain how X works", "add docstrings", "summarise this module".
conceptual-modelling
Build and evolve a living, representation-agnostic conceptual model for a product (programming) project — the domain's entities, attributes, relationships, and meaning — and choose how it is rendered. Use to model the domain, do conceptual data modelling in UML, run ontology-engineering at the concept level (stable-IRI policy, vocabulary reuse), decide the model *source* (LinkML directly vs model2owl-first), set up a conceptual model, or run terminology/definitions/glossary management. Trigger on "model the domain", "conceptual/UML data model", "set up conceptual model", "which model source", "ontology/terminology management", "ubiquitous language glossary". For the LinkML craft itself (authoring, generation, gates) see linkml-engineering; for generic modelling conventions see modelling-conventions. Conditional: applies to product-development repos that build software; a doc-only/non-product repo does not need it.
clarity-gate
Pre-ingestion quality gate for specifications and documents before they drive implementation. Use to score a spec/EPIC against a 13-item checklist (6-criterion rubric, must reach ≥9/10), surfacing hidden assumptions and ungrounded claims. Trigger on "score this spec", "is this spec ready", "run the clarity gate", "check this EPIC before implementation". A lightweight variant applies to routine docs.
executive-communication
Use when turning rough input into a clear, concise, persuasive executive message or analysis: a board paper, proposal, client recommendation, email or Slack note, spoken narrative, slide outline, or a strategic problem to be solved. Triggers include "structure this", "make this persuasive", "write this up for a board or client", "turn this into a recommendation", "tighten this message", or any request for McKinsey-style, Minto, SCQA, or pyramid communication. Not for casual chat or code.
estimation
A lightweight fixed-cost scoping / estimation discipline that de-risks fixed-cost bids — a CHECKLIST + METHOD, not a heavy model. Produces a work breakdown plus PERT-weighted effort estimates, uncertainty ranges, assumptions & exclusions, and contingency, feeding the SoW scope boundary. PERT (three-point: optimistic / most-likely / pessimistic) is the default technique; analogous, parametric, and bottom-up are alternatives. Gantt charts / scheduling are rendered in EXTERNAL tools (Smartsheet, MS Project) from the work breakdown — this skill produces the breakdown + estimates, not the chart. It OWNS the estimation/scoping discipline; it DELEGATES the proposal/SoW wrapper to `proposal-writing`, the build breakdown to `epic-planning`, and sequencing to `decision-package`. Triggers — "estimate this engagement", "PERT estimate", "fixed-cost scoping", "work breakdown for estimation", "contingency / uncertainty range". Independently triggerable; also the pricing step of the `proposal-writing` flow.
Page 1339 of 1714 · 85698 results
