Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Docs & knowledge
4,561 results · page 48 of 153
- View details
agentsop-crewaiSkillDocs & knowledge
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.
Ready to connect★ 398
- View details
agentsop-difySkillDocs & knowledge
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
Ready to connect★ 398
- View details
agentsop-llamaindexSkillDocs & knowledge
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query eng
Ready to connect★ 398
- View details
agentsop-multiscale-chunkingSkillDocs & knowledge
Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child o
Ready to connect★ 398
- View details
agentsop-reranker-stageSkillDocs & knowledge
Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and
Ready to connect★ 398
- View details
agentsop-tool-scopingSkillDocs & knowledge
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and b
Ready to connect★ 398
- View details
apply-findingsSkillDocs & knowledge
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to \"apply findings\", \"apply fixes\", \"apply suggestions\", \"apply accepted findings\", \"fix the fi
Ready to connect★ 402
- View details
map-codebaseSkillDocs & knowledge
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the u
Ready to connect★ 402
- View details
note-improvementSkillDocs & knowledge
Capture an out-of-scope improvement opportunity so it doesn't get lost. Use when the user asks to \"note improvement\", \"save improvement\", \"track this for later\", \"remember this improvement\", \"note this idea\", \"log improvement\", \"backlog this\", or \"park this idea\". Also invoke proacti
Ready to connect★ 402
- View details
self-improveSkillDocs & knowledge
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to \"self-improve\", \"distill this session\", \"distill past sessions
Ready to connect★ 402
- View details
simplify-allSkillDocs & knowledge
Run the code and documentation simplification passes together over one scope, launching every review sub-agent concurrently before applying a single round of fixes. Use when the user asks to \"simplify all\", \"simplify everything\", \"simplify code and docs\", \"clean up code and docs\", \"run both
Ready to connect★ 402
- View details
simplify-docsSkillDocs & knowledge
Run a multi-agent review of code comments and markdown documentation for unnecessary content, then fix the issues. Covers comments that misdescribe the code, what-restating comments, name-mirroring doc comments, status-update prose, and other documentation noise. Use when the user asks to \"simplify
Ready to connect★ 402
- View details
cultural-tourism-xiaohongshu-feedSkillDocs & knowledge
Cultural tourism Xiaohongshu feed — searches popular Xiaohongshu notes related to cultural tourism, filters the hottest content by like count, and generates a polished HTML report. Use when users need cultural tourism Xiaohongshu content, travel guides, scenic spot popularity, cultural tourism news,
Ready to connect★ 399
- View details
playlet-xhs-feedSkillDocs & knowledge
Short drama Xiaohongshu (RED) feed — Daily scans viral short-drama content on Xiaohongshu, filters hot notes by engagement, intelligently clusters content themes, and generates an HTML daily report including covers, engagement data, and creative insights. Supports targeted queries by theme (time-tra
Ready to connect★ 399
- View details
xiaohongshu-account-analyzerSkillDocs & knowledge
Deeply analyzes Xiaohongshu (rednote) accounts and produces a seven-dimension quantitative scoring diagnostic report with exportable HTML. Use when a user provides a Xiaohongshu ID for account diagnosis, rednote analysis, account health assessment, commercial value evaluation, multi-account comparis
Ready to connect★ 399
- View details
xiaohongshu-ai-feedSkillDocs & knowledge
AI Xiaohongshu feed — automatically scans AI-related Xiaohongshu notes daily, filters the hottest content by engagement (likes/shares/comments), intelligently clusters it into a polished HTML daily report with cover images, metrics, and daily subscription. Use when the user asks for an AI Xiaohongsh
Ready to connect★ 399
- View details
xiaohongshu-dailytopSkillDocs & knowledge
Xiaohongshu daily viral notes: tracks daily trends across Xiaohongshu categories, monitors real-time heat changes in different fields, identifies content directions that are gaining traction, and anticipates the next wave of traffic opportunities. Based on the day's viral content, it distills reusab
Ready to connect★ 399
- View details
xiaohongshu-lowtopSkillDocs & knowledge
Xiaohongshu low-follower viral notes: mines viral data from low-follower accounts on the Xiaohongshu platform, fetching a ranking of notes with fewer than 5,000 followers but more than 500 interactions. Finds quality samples that show viral patterns and trending topics.
Ready to connect★ 399
- View details
xiaohongshu-note-analyzerSkillDocs & knowledge
Xiaohongshu note optimization assistant tool that scores user copy across multiple dimensions based on viral post data across the web and provides improvement suggestions; use when the user needs to evaluate copy quality or get optimization suggestions
Ready to connect★ 399
- View details
xiaohongshu-weeklytopSkillDocs & knowledge
Focused on content trend analysis for the Xiaohongshu (RED) platform, offering deep insights based on the TOP 50 trending notes from the past 7 days. Supports queries across 24 vertical categories, discovery of niche viral hits, and daily subscription push notifications. Creators can look up trendin
Ready to connect★ 399
- View details
xiaohongshu-writeSkillDocs & knowledge
A one-stop note generation tool built for Xiaohongshu content creation. Based on 2000+ viral notes continuously collected daily across the web, it precisely retrieves currently trending viral notes on the platform according to user keywords, uses AI to deeply analyze the structure, opening logic, in
Ready to connect★ 399
- View details
release-note-creatorSkillDocs & knowledge
Writes Release Notes for Xiaomi Album Syncer. Use cases: (1) generate a changelog for a specified version number before a release; (2) determine a version's scope of changes (based on comparison with the previous tag); (3) proofread existing release notes for compliance with writing guidelines.
Ready to connect★ 399
- View details
component-guidelines-docsSkillDocs & knowledge
Generate comprehensive component guideline documentation for SEED Design System. Use when creating or updating design guideline documentation in ./docs/content/docs/components directory. This skill helps create high-quality documentation similar to action-button.mdx.
Ready to connect★ 396
- View details
conference-talk-builderSkillDocs & knowledge
Create conference talk outlines and iA Presenter markdown slides using the Story Circle narrative framework. Use when the user wants to structure a tech talk, create presentation slides, or needs help organizing talk ideas into a story-driven format.
Ready to connect★ 396
- View details
create-plansSkillDocs & knowledge
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that Claude will execute. Produces Claude-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.
Ready to connect★ 396
- View details
data-export-pdfSkillDocs & knowledge
Create professional PDF reports with text, tables, and embedded images using reportlab. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
Ready to connect★ 396
- View details
design-by-contractSkillDocs & knowledge
Automated contract verification, detection, and remediation across multiple languages using formal preconditions, postconditions, and invariants. This skill provides both reference documentation AND execution capabilities for the full PLAN -> CREATE -> VERIFY -> REMEDIATE workflow.
Ready to connect★ 396
- View details
doc-syncSkillDocs & knowledge
Keeps IdeaVim documentation in sync with code changes. Use this skill when you need to verify documentation accuracy after code changes, or when checking if documentation (in doc/, README.md, CONTRIBUTING.md) matches the current codebase. The skill can work bidirectionally - from docs to code verifi
Ready to connect★ 396
- View details
docs-consistency-checkerSkillDocs & knowledge
Validate consistency across SEED Design component documentation layers (design guidelines in ./docs/content/docs/components, Rootage specs in ./packages/rootage/components, and React docs in ./docs/content/react/components). Use when auditing documentation completeness, before releases, or validatin
Ready to connect★ 396
- View details
Documentation reviewSkillDocs & knowledge
Reviews documentation for factual accuracy
Ready to connect★ 396
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
55,111 of the 55,543 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.