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
4,502 results · page 140 of 151
- View details
rag-knowledge-builderSkillDocs & knowledge
Build and evaluate RAG corpora - ingest, chunk, embed, index, and spot-check retrieval quality. Use when creating knowledge bases for agents.
Ready to connect
- View details
verifySkillDocs & knowledge
Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF p
Ready to connect
- View details
word-documentsSkillDocs & knowledge
Use when creating, reading, or editing Word documents (.docx). Covers document generation with styles and structure, extracting content, find-and-replace, tracked changes, and templates.
Ready to connect
- View details
works-council-reviewerSkillDocs & knowledge
Reviews a proposal, business case, deck or rollout plan in character as a Works Council Representative archetype, then saves a structured review document with a verdict, findings that cite the artifact, employee-impact risks and five interrogation questions. Use when the user asks for a works counci
Ready to connect
- View details
write-like-meSkillDocs & knowledge
Builds a personal voice profile from roughly 90 days of the user's sent email and meeting transcripts, then drafts emails and documents that match how the user actually writes. Use when the user asks to write like me, match my voice or tone, build or refresh my voice profile, or wants an email or do
Ready to connect
- View details
\"algo-nlp-lda\"SkillDocs & knowledge
\"Implement LDA topic modeling to discover latent topics in document collections. Use this skill when the user needs to extract topics from a text corpus, categorize documents by theme, or explore thematic structure — even if they say 'what are the main topics', 'topic extraction', or 'document clus
Ready to connect
- View details
\"algo-nlp-ner\"SkillDocs & knowledge
\"Implement Named Entity Recognition to identify and classify entities in text. Use this skill when the user needs to extract people, organizations, locations, dates, or custom entities from documents — even if they say 'extract names from text', 'find companies mentioned', or 'entity extraction'.\"
Ready to connect
- View details
\"algo-nlp-similarity\"SkillDocs & knowledge
\"Calculate text similarity using lexical and semantic methods for matching and deduplication. Use this skill when the user needs to find similar documents, detect near-duplicates, or measure semantic closeness between texts — even if they say 'how similar are these texts', 'find duplicates', or 'se
Ready to connect
- View details
\"algo-nlp-summarization\"SkillDocs & knowledge
\"Implement text summarization using extractive and abstractive approaches. Use this skill when the user needs to condense long documents, build an automatic summarization pipeline, or compare summarization strategies — even if they say 'summarize this document', 'TLDR', or 'key points extraction'.\
Ready to connect
- View details
agently-requestSkillDocs & knowledge
Use for Agently request-side setup and contracts: model settings, Prompt/input/output design, effect tuning, missing or redundant context, structured output, response reuse, streaming, session memory, embeddings, and retrieval within one request family. Review can be triggered by a developer's need
Ready to connect
- View details
benchSkillDocs & knowledge
One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.
Ready to connect
- View details
call-summarySkillDocs & knowledge
Process call notes or a transcript — extract action items, draft follow-up email, generate internal summary. Use when pasting rough notes or a transcript after a discovery, demo, or negotiation call, drafting a customer follow-up, logging the activity for your CRM, or capturing objections and next s
Ready to connect
- View details
content-quality-editorSkillDocs & knowledge
Use before publishing AI-generated content — blog posts, READMEs, release notes, commit messages, PR descriptions, docs, or social posts. Strips AI patterns and applies a final quality pass.
Ready to connect
- View details
ctxSkillDocs & knowledge
Capture a durable context note for any exploration or change made to this repo. Use after EVERY completed implementation - a phase, feature, upgrade, refactor or bug fix - and whenever you finish investigating an area of the codebase. Also use when the user says "write a ctx", "log this", "capture c
Ready to connect
- View details
docs-researcherSkillDocs & knowledge
Use when a task needs documentation-backed verification of APIs, version-specific behavior, or framework options.
Ready to connect
- View details
documentation-engineerSkillDocs & knowledge
Use when a task needs technical documentation that must stay faithful to current code, tooling, and operator workflows.
Ready to connect
- View details
geml-code-graphSkillDocs & knowledge
Build, view, update, and navigate a project's call graph as GEML codemap documents. Use when asked to see/update/build a project's code graph or codemap (看下/更新下 code-graph), when asked "who calls X" / "what does X call" / to trace a call chain or impact path, or whenever a .geml-code-graph/ director
Ready to connect
- View details
open-claude-design-systemSkillDocs & knowledge
Extract, document, or normalize a product UI design system from code, screenshots, or brand sources. Use for visual tokens, theme variables, typography, spacing, colors, radii, shadows, component inventories, variants, states, or building a reusable UI library. Do not use for software architecture,
Ready to connect
- View details
owen-burnett-officecraftSkillDocs & knowledge
📎 Editable documents, slides, and sheets.
Ready to connect
- View details
perfetto-performance-analysisSkillDocs & knowledge
Analyze Android, Linux, and Chromium Perfetto traces with local trace_processor_shell evidence. Use for startup, scrolling or jank, input latency, ANR, CPU scheduling, memory or GC, Binder or IO, GPU or SurfaceFlinger, power or thermal, rendering-pipeline identification, trace capture guidance, scen
Ready to connect
- View details
refactoringSkillDocs & knowledge
Refactoring process. Invoke immediately when programmer or document mentions refactoring, or proactively when code gets too complex or messy.
Ready to connect
- View details
review-rewrite-contentSkillDocs & knowledge
Use when Indonesian, English, or code-mixed notes, experiences, scripts, or drafts need coordinated story structure, hook improvement, headline options, anti-AI-slop editing, Jabodetabek register adaptation, platform formatting, a scored content audit, multi-variant comparison, or an end-to-end cont
Ready to connect
- View details
storytelling-contentSkillDocs & knowledge
Use when facts, experiences, notes, interviews, scripts, or existing Indonesian, English, or code-mixed drafts need an honest story outline, narrative restructuring, full story rewrite, tension and pacing work, delivery notes, or repurposing into new content formats or angles without invented events
Ready to connect
- View details
brainstormingSkillDocs & knowledge
You MUST use this before any creative work — creating features, building components, drafting documents, designing workflows, or modifying behavior. Explores your human partner's intent, requirements, and design before any implementation begins.
Ready to connect
- View details
ce-brainstormSkillDocs & knowledge
Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says ''let''s brainstorm'', or when they want to think through options before deciding what to buil
Ready to connect
- View details
ce-release-notesSkillDocs & knowledge
Summarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation. Use when the user types `/ce-release-notes` or asks "what changed in compound-engineering recently?" or "what happened to `<skill-name>`?".
Ready to connect
- View details
closer-playbookSkillDocs & knowledge
YourProduct's client sales playbook — drafts client-facing messages in the premium-exclusivity brand voice, runs rebuttal sparring on objections, generates follow-up/check-in notes, and debriefs deals into lessons. Use this whenever the user is writing or planning ANY message to a YourProduct client
Ready to connect
- View details
cognitive-bias-detectorSkillDocs & knowledge
Audits design documents, sprint estimates, and technical debates for cognitive biases like anchoring, sunk cost, and optimistic scoping.
Ready to connect
- View details
colab-course-publisherSkillDocs & knowledge
Use when Codex needs to create, edit, publish, package, or validate The Colab CourseViewerPlatform course content, including tenant course repos, course.json, blueprint.json, module manifests, markdown lessons, quizzes, generated educational images, HTML widgets, and live CourseViewerPlatform conten
Ready to connect
- View details
craft-tasksSkillDocs & knowledge
Use when a design is already settled (intent, approach, invariants, and boundary decided — typically after deep-interview) and it must be broken into concrete implementation tasks filed as shareable child tickets in the PM tool (Linear sub-issue / Notion / Jira) for the team to track. Triggers inclu
Ready to connect
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.
53,788 of the 54,220 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.