Trending Skills
The hottest skills gaining momentum in the community right now.
Add Admin API Endpoint
by aiagentskills
Add a new endpoint or endpoints to Ghost's Admin API at ghost/api/admin/**.
review
by kelvinz
"Review branch changes against a base branch for correctness, security, tests, and scope, then return a clear go/no-go decision. Triggers: review, readiness check, pre-commit review, pre-finalise review."
prd
by kelvinz
"Create, update, or list PRDs for features, fixes, and chores. Handles project setup (first PRD) and ongoing PRD management. Each PRD is a self-contained spec with status, priority, and acceptance criteria. Triggers: prd, new feature, write prd, plan feature, create spec, list prds, update prd, add feature."
design
by kelvinz
"Router-first workflow for high-craft design execution across four modes: ui, ux, motion, and imagery. Use when designing or refining interfaces, structuring and auditing UX/usability/accessibility, implementing or specifying interaction motion, or producing static visual artifacts (.png/.pdf) with a matching philosophy note. Triggers: design ui, improve ux flow, run design audit, add transitions, reduce motion issues, create visual imagery, craft poster composition."
implement
by kelvinz
"Implement an existing PRD (Type: feat/fix/chore), update tests/checks, and mark completed PRD checklist items. Triggers: implement prd, build feature from prd, execute prd checklist."
commit
by kelvinz
"Create atomic user-approved commits with feat/fix/chore titles. Include inline PRD checklist and context updates per atomic commit. Finalise branch merge/cleanup when requested. Triggers: commit changes, split commits, finalise branch, commit message."
context
by kelvinz
"Maintain durable project context in tasks/context.md (state, decisions, milestones, gotchas, optional context links), inline during other workflows or standalone for cleanup/backfill. Triggers: update context.md, decision log, record project context, capture high-value reference links that improve context handoff."
compact
by kelvinz
"Compact tasks/context.md by summarising older completed history while preserving active context. Triggers: compact context, prune context log, trim context."
sweetlink
by bjesuiter
Use SweetLink to connect your AI agent to a real browser tab. Like Playwright, but works in your current tab. Enables authentication, screenshots, smoke tests, and DevTools telemetry without headless automation.
mcporter
by bjesuiter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
jb-docs-scraper
by bjesuiter
Scrape documentation websites into local markdown files for AI context. Takes a base URL and crawls the documentation, storing results in ./docs (or custom path). Uses crawl4ai with BFS deep crawling.
jb-bgproc
by bjesuiter
Manage and inspect background processes for agents using the bgproc CLI. Use when asked to start, stop, list, clean, check status, or view logs for bgproc-managed processes, or when a task needs a JSON-outputting process manager.
read-github
by yuanxiao0115
Read and search GitHub repository documentation via gitmcp.io MCP service. Use when given a GitHub repo URL or owner/repo path and asked to read docs, understand the codebase, search code, or explore repository contents. Converts github.com URLs to gitmcp.io for LLM-friendly access.
browserpilot-executor
by yuanxiao0115
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, semantic tree analysis, screenshot, JavaScript execution, and batch operations.
planner
by yuanxiao0115
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
plan-harder
by yuanxiao0115
Use when user specfically says 'plan harder'.
dev-browser
by yuanxiao0115
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
vue-best-practices
by yuanxiao0115
Vue 3 TypeScript, vue-tsc, Volar, Vite, component props, testing, composition API.
codex-subagent
by yuanxiao0115
Spawn Codex subagents via background shell to offload context-heavy work. Use for: deep research (3+ searches), codebase exploration (8+ files), multi-step workflows, exploratory tasks, long-running operations, documentation generation, or any other task where the intermediate steps will use large numbers of tokens.
backend-dev-guidelines
by yuanxiao0115
Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or working with Express APIs, Prisma database access, Sentry error tracking, Zod validation, unifiedConfig, dependency injection, or async patterns. Covers layered architecture (routes → controllers → services → repositories), BaseController pattern, error handling, performance monitoring, testing strategies, and migration from legacy patterns.
parallel-task
by yuanxiao0115
Execute plan files by launching multiple parallel subagents to complete tasks simultaneously. Triggers on explicit "/parallel-task" commands.
openai-docs-skill
by yuanxiao0115
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
context7
by yuanxiao0115
Fetch up-to-date library documentation via Context7 API. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff (6) AND MOST IMPORTANTLY, when you are installing dependencies, libraries, or frameworks you should ALWAYS check the docs to see what the latest versions are. Do not rely on outdated knowledge. Always prefer this over guessing library APIs or using outdated knowledge.
vercel-react-best-practices
by yuanxiao0115
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.