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 111 of 151

  • extract-competitive-overlap-data-from-joint-venture-business-planSkillDocs & knowledge

    Closes gaps in cross-document data reconciliation, pipeline-to-pipeline overlap analysis, merger control filing-threshold assessment, and clean team information distribution compliance.

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • extract-key-custodians-from-document-preservation-noticeSkillDocs & knowledge

    Closes gaps in accurate title and division extraction for each custodian, employment status verification, and gap analysis between the preservation notice list and the full custodian universe identified in source documents.

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • extract-pricing-data-from-document-productionSkillDocs & knowledge

    Supports extraction of complete pricing structures, temporal gap analysis between competitor contacts and later pricing changes, cost-justification assessment, and flagging of deletion or non-reply instructions.

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Judgment Document GenerationSkillDocs & knowledge

    Based on a description of case facts, coordinates and invokes 8 atomic capabilities to generate a complete criminal judgment with standardized formatting and rigorous reasoning. Covers the full workflow from fact-finding and application of law to sentencing reasoning and document output.

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Legal Document DraftingSkillDocs & knowledge

    Drafting of legal documents: drafts various types of legal documents, covering complaints, statements of defense, representation statements, legal opinions, contracts, lawyer's letters, and more

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Legal Document SummarizationSkillDocs & knowledge

    Triggers when a structured summary is needed for legal documents such as judgments, rulings, mediation agreements, arbitration awards, or administrative penalty decisions. Typical trigger scenarios include: - The user asks for a summary, key points, or holding of a legal document - The user needs to

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Legal Paper Writing and Citation VerificationSkillDocs & knowledge

    A complete workflow for Chinese-language legal papers: drafting and revision, citation verification, and true footnotes. Covers everything from topic positioning, thesis construction, careful reading of statutes and cases, argumentation, and citation tracking, to checking footnote formats one by one

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Legal TerminologySkillDocs & knowledge

    When an AI agent generates, reviews, or modifies any legal text (including but not limited to contracts, pleadings, legal opinions, judicial documents, statutory interpretations, legal memoranda, etc.), it must ensure that the legal terminology used is accurately worded, unambiguous, and conforms to

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • legal-qa-extractorSkillDocs & knowledge

    Extracts valuable legal Q&A pairs from lawyer-client communication records to generate structured knowledge base content. Use this skill when the user needs to organize client consultation records, extract reusable legal knowledge from conversations, create Q&A knowledge bases, or prepare content ma

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • longbridge-earningsSkillDocs & knowledge

    Earnings analysis — pre- and post-earnings. Pre-earnings preview: prior-guidance review, recent-events tracking, last call's Q&A, and a key-things-to-watch framework for an upcoming release. Post-earnings: two tiers — a fast in-chat summary card (default) and a full Markdown research report (on requ

    Ready to connect★ 61

    github.com/longbridge/skills61 stars

    View details
  • Meeting MinutesSkillDocs & knowledge

    Meeting notes: structured records and action-item tracking for legal meetings and case discussions

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Multi-Document SummarizationSkillDocs & knowledge

    Trigger this skill when you need to comprehensively analyze multiple related documents, extract common viewpoints, identify conflicts, and generate a unified overview. Typical trigger scenarios include, but are not limited to: - User uploads multiple judgments or rulings and asks for a summary of ad

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • OCR ExtractionSkillDocs & knowledge

    OCR text extraction: perform OCR on scanned documents, images, and PDFs without a text layer to extract editable text

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • open-kimi-pptSkillDocs & knowledge

    The single authoritative LegalWork Skill for creating, editing, styling, validating, and exporting every presentation. It combines Kimi-derived presentation style/detail rules, the editable PPTD project format, structural/style validation, visual QA, and deterministic local PPTX generation in one wo

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • prepare-antitrust-risk-assessmentSkillDocs & knowledge

    Closes gaps in a multi-deliverable structure, market-level concentration analysis, hot-document and HSR production identification, coordinated effects analysis, and entry barrier assessment.

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • second-brain-backfillSkillDocs & knowledge

    Import a large archive into the vault in controlled batches: triage what is worth ingesting, process oldest first, checkpoint after every batch, and keep cost visible. Use this skill whenever the user wants to import years of bookmarks, an export from another notes app, a downloads folder, a chat hi

    Ready to connect★ 59

    github.com/undefined-ui/second-brain-os61 stars

    View details
  • second-brain-publishSkillDocs & knowledge

    Prepare a subset of the vault for publishing: check opt-in flags, find private material, and report what would leak through links before anything is exported. Use this skill when the user wants to publish notes as a site or digital garden, asks what is safe to make public, or is setting up an export

    Ready to connect★ 59

    github.com/undefined-ui/second-brain-os61 stars

    View details
  • second-brain-quizSkillDocs & knowledge

    Generate questions from the user's own concept pages so they can find out what they saved but never learned, and compare their answers against what the pages say. Use this skill when the user wants to test themselves, revise, make flashcards from their notes, or asks what they have forgotten. Do NOT

    Ready to connect★ 59

    github.com/undefined-ui/second-brain-os61 stars

    View details
  • seo-entity-linkingSkillDocs & knowledge

    Audit and generate entity & knowledge-graph linkage for a page — verify sameAs identity links (Wikidata/Wikipedia/LinkedIn/Crunchbase/official profiles) on Organization/Person, check NAP/entity consistency for local, confirm a defined primary entity, and measure entity density, then propose ready-to

    Ready to connect★ 61

    github.com/hainrixz/claude-seo-ai61 stars

    View details
  • seo-meta-onpageSkillDocs & knowledge

    Audit and generate the document head — title and meta description length against the shared bands (title pass 30-60 chars, recommended 50-60; description pass 70-160, recommended 150-160), viewport, charset, <html lang>, and robots-meta sanity — flagging missing/duplicate/out-of-band values and prod

    Ready to connect★ 61

    github.com/hainrixz/claude-seo-ai61 stars

    View details
  • vnx-managerSkillDocs & knowledge

    VNX orchestration infrastructure guardian - maintains dispatcher, smart tap, receipt processor, intelligence systems, and documentation.

    Ready to connect★ 61

    github.com/vinix24/vnx-orchestration57 stars

    View details
  • zheng-ju-cai-liao-zheng-liSkillDocs & knowledge

    Evidence material organization: receives case-related documents (complaints, evidence materials), generates an evidence list Word document in a fixed template format, and merges all evidence materials into a single paginated PDF collection. Trigger scenarios: used when the user makes requests such a

    Ready to connect★ 61

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • aztec-scannerSkillDocs & knowledge

    Use when the user wants to audit Aztec Network smart contracts written in Noir, scan for privacy-specific vulnerabilities including state leakage, note handling, or nullifier collisions, review private DeFi protocols for information disclosure, or analyze encrypted computation and zero-knowledge pro

    Ready to connect★ 60

    github.com/0x-shashi/web3-audit-skills57 stars

    View details
  • clay-to-deeplineSkillDocs & knowledge

    Convert a Clay table configuration into local Deepline scripts. Handles extraction (MCP or script), documentation, action mapping, script generation, and parity validation against Clay ground truth.

    Ready to connect★ 60

    github.com/getaero-io/gtm-eng-skills60 stars

    View details
  • doctype-developmentSkillDocs & knowledge

    Create and modify Frappe DocTypes including schema design, controllers, child tables, and customization. Use when building data models, adding fields, or implementing document lifecycle logic.

    Ready to connect★ 60

    github.com/lubusin/frappe-skills60 stars

    View details
  • evolving-memorySkillDocs & knowledge

    Evolving memory system inspired by EvoScientist. Extends ScienceClaw's research memory with four record types (finding, ideation, strategy, pitfall) to enable learning from past research sessions. Recall relevant strategies and pitfalls before recipe execution, extract and persist new lessons after

    Ready to connect★ 60

    github.com/zaoqu-liu/scienceclaw59 stars

    View details
  • export-docxSkillDocs & knowledge

    Export research project reports to Word (.docx) format with embedded figures and formatted references. Use when user says "导出 Word", "/export word", "转 docx", "生成 Word 报告", "export to Word", or wants a Word document from project results.

    Ready to connect★ 60

    github.com/zaoqu-liu/scienceclaw59 stars

    View details
  • export-pptxSkillDocs & knowledge

    Export research project findings to a presentation (.pptx) with key findings, figures, and conclusions. Use when user says "导出 PPT", "/export pptx", "做个汇报", "生成 PPT", "export to PowerPoint", "make a presentation from results", or wants slides from project results. Builds on pptx-generation skill.

    Ready to connect★ 60

    github.com/zaoqu-liu/scienceclaw59 stars

    View details
  • latex-writingSkillDocs & knowledge

    Create, edit, and compile LaTeX documents for academic papers using latex_compile, update_latex, and send_ui_directive tools

    Ready to connect★ 60

    github.com/zaoqu-liu/scienceclaw59 stars

    View details
  • obsidian-vault-locationSkillDocs & knowledge

    Use when David asks where Obsidian is installed, where his notes/vault/journal/writing live, or wants to read/find/edit a note from his Obsidian vault. Triggers on "Obsidian", "my notes", "my vault", "my journal", "private writing", "where do I write".

    Ready to connect★ 60

    github.com/matyasstoch/david-skills60 stars

    View details

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.

53,789 of the 54,221 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.

See how to connect your AI