Code Gen
Generate code, boilerplate, scaffolding
line-liff
by yangnim21029
"Expert guide for developing LINE Front-end Framework (LIFF) applications. Covers SDK integration (CDN/npm), initialization, authentication (LINE Login), user profile retrieval, sending messages, and using advanced features like Share Target Picker and 2D code reader. Use when a user needs to: (1) Build a web app that runs inside LINE, (2) Get user profiles from a web page, (3) Send messages to LINE chats from a website, (4) Implement deep linking with LIFF URLs."
add-cuda-kernel
by slurpyb
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
maui-project-setup
by Rimblehelm
A brief description of what this skill does
resume-assistant
by liwei-xyz
简历助手技能，生成专业可编辑的 HTML 简历模板，支持照片上传、PDF 导出。触发词："简历"、"简历模板"、"帮我写简历"。
nextjs-turborepo
by brixtonpham
"Full-stack web development with Next.js and Turborepo. Stack: Next.js 14+ (App Router, RSC, Server Actions, PPR, SSR, SSG, ISR), Turborepo (monorepo, pipelines, remote caching), RemixIcon (3100+ icons). Capabilities: server components, API routes, middleware, caching strategies, build optimization, monorepo management. Actions: create, build, deploy, optimize Next.js apps, setup monorepo, configure caching. Keywords: Next.js, App Router, Server Components, RSC, Server Actions, SSR, SSG, ISR, PPR, Turborepo, monorepo, remote cache, build pipeline, parallel execution, workspace, pnpm, icons. Use when: building Next.js apps, implementing SSR/SSG, setting up monorepos, optimizing build performance, configuring caching strategies, managing shared dependencies."
worktree-manager
by saar120
Manage git worktrees using the w shell function. Use when the user asks to create, switch to, list, remove, or clean up git worktrees, or when starting feature work that needs an isolated workspace. Triggers on keywords like "worktree", "create worktree", "switch worktree", "w <name>", or when needing to work on a branch in isolation. Also use proactively when implementing features that benefit from workspace isolation.
chat-reply
by paulo20223
Generate a reply for a Telegram chat using mtcute. Use when the user asks to draft a reply, respond to a chat, or wants to send a message. Trigger phrases include "reply to chat", "draft response", "respond in chat", "write reply", "answer in chat".
bamboohr
by CodeDraig
Manage small business HR with BambooHR's people management platform.
skill-creator
by kimasplund
Guide for manually creating custom skills from scratch with templates and validation. Use when designing NEW skills with specific requirements. For auto-generating skills from existing git repos, use /generate-skills instead.
numpy-set-ops
by cuba6112
Set-theoretic operations for finding unique elements, membership testing, and array intersections. Triggers: unique, isin, intersect1d, setdiff1d, union1d.
gbp-api-automation
by garrettjsmith
When the user wants to programmatically manage Google Business Profiles at scale via API, automate GBP updates, build GBP management tools, or integrate GBP data into their systems. Also use when the user mentions "GBP API," "Google Business Profile API," "bulk GBP management," "automate GBP," "GBP integration," or "programmatic GBP." For manual GBP optimization, see gbp-optimization. For multi-location strategy, see multi-location-seo.
spec-system-init
by B2CExpress
Initialize the SPEC-driven documentation system v2 (features-based) in a workspace. Creates docs/ (RULES.md, INDEX.md, features/, active/, future/, archive/, discard/) and scripts/ (generate-index.sh, lint-docs.sh, audit-docs.sh). Creates or updates CLAUDE.md at project root to orient AI. Use when the user says "inicializar sistema de documentação", "setup specs", "init doc system", "bootstrap docs", or is starting a new project that needs disciplined spec-based documentation.
modular-skill-crafter
by M-M-Tech-House
Guidelines and rules for creating new skills that adhere to the standard skill structure.
elenweave
by the-code-rider
Manage Elenweave project-scoped boards and assets through the local REST API and build rich visual explanations. Use when asked to create/reuse projects, create or update boards from node/edge data, append nodes and edges, upload or reference media assets, inspect API responses, explain code visually, summarize commits as diagrams, or present implementation plans as explorable boards.
hybrid-decision-analysis.v1
by squirrel289
'Hybrid decision workflow that combines expert rubric design, explicit evidence capture, hard-constraint gating, scenario bakeoffs, and deterministic scoring. Use when selecting skills, tools, architectures, workflows, or build-vs-buy options and when you need consistent, reliable, and auditable recommendations.'
algorithmic-art
by zhongjis
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
nano-banana-skill
by vishalx360
Generates, edits, and restores images using Google Gemini image models (Nano Banana). Use when the user wants to create images from text prompts, edit existing images with natural language, restore or enhance photos, or generate icons, patterns, diagrams, or visual content. Requires a GEMINI_API_KEY environment variable.
deep-research
by tonyflo79
Comprehensive deep research system producing 1,000+ verbatim quotes across 6 buckets (Pain, Hope, Root Cause, Solutions Tried, Competitor Mechanism, Villain). Use when conducting market research for a new campaign, gathering audience intelligence, or building the evidence base for downstream copywriting. This is the most complex skill in the engine — it orchestrates multiple subagents across 4 layers with 57 microskills. Produces the research handoff package with market snapshots, avatar profiles, competitive landscape analysis, and categorized verbatim quotes. Trigger when users mention research, market research, audience research, gathering quotes, competitive analysis, or building the evidence base for a promotion. Requires Soul.md from Skill 00.
Keyword Tier 3 — State-Specific Programmatic SEO
by kolegadev
```
naming-analyzer
by VisualxIntelligence
Suggest better variable, function, and class names based on context and conventions.
olakai-add-monitoring
by olakai-ai
Add Olakai monitoring to an existing AI agent or LLM integration. AUTO-INVOKE when user wants to: add monitoring to existing code, integrate observability into a working agent, instrument an existing AI system, add tracking to LLM calls, wrap OpenAI/Anthropic clients, add analytics to working AI code, or retrofit monitoring to production AI. TRIGGER KEYWORDS: olakai, add monitoring, integrate monitoring, instrument, wrap client, observability, SDK integration, @olakai/sdk, olakai-sdk, existing agent, existing code, add tracking, analytics, telemetry, retrofit monitoring, existing LLM, existing OpenAI, existing Anthropic. DO NOT load for: creating new agents from scratch (use olakai-create-agent), troubleshooting issues (use olakai-troubleshoot), or generating reports (use generate-analytics-reports).
pnote
by thevertexlab
pnote - The PromptNote CLI for managing prompts, notes, and snippets
wp-plugin-version
by Tmeister
Analyze changes and update WordPress plugin version references safely.
sling-transforms
by slingdata-io
Data transformation functions for Sling replications, pipelines, and API specs. Use when transforming data, applying string/date/numeric functions, type casting, cleaning data, computing fields, or using expressions like trim, upper, lower, date_format, cast, coalesce, hash.