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
4,535 results · page 27 of 152
- View details
meeting-transcriptSkillDocs & knowledge
Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering
Ready to connect★ 1k
- View details
memory-hygieneSkillDocs & knowledge
Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries
Ready to connect★ 1k
- View details
review-cockpitSkillDocs & knowledge
Produce and continuously maintain ONE living review document for a multi-item session — a cockpit header (Progress checklist, Working folder, Context) plus per-item review cards that you approve or request changes on directly in the doc or side panel. Use whenever a session has multiple deliverables
Ready to connect★ 1k
- View details
update-knowledge-baseSkillDocs & knowledge
Maintain and update product knowledge base from releases, features, and project changes with optional wiki sync
Ready to connect★ 1k
- View details
writing-plansSkillDocs & knowledge
Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.
Ready to connect★ 1k
- View details
perf-benchmarkingSkillDocs & knowledge
Measure React Native performance on-device for stream-chat-react-native — Hermes CPU profiles, deterministic call/listener counting, component render profiling, and memory/jank capture. Use when asked to benchmark a change, prove or disprove a perf claim, compare before/after, find what re-renders o
Ready to connect★ 1k
- View details
- View details
code-reviewSkillDocs & knowledge
Review pull requests in this repository. Use when reviewing changes to Markdown rendering, the marked configuration, renderers, knowledge/** content, or the CI and git-hook gates. Encodes the failure modes that have actually shipped here — most importantly the ones where the test suite was green whi
Ready to connect★ 1k
- View details
twmd-distillSkillDocs & knowledge
Distill LESSONS-INBOX entries to canonical layer (MANIFESTO/DNA/MEMORY). TRIGGER when: user says "distill", "消化教訓", "整理 LESSONS-INBOX".
Ready to connect★ 1k
- View details
twmd-finaleSkillDocs & knowledge
Full session wrap-up commander for Taiwan.md. Takes inventory of the session's work → runs the chain /twmd-memory + /twmd-diary + /twmd-evolve → finally produces a final wrap-up summary for observers. TRIGGER when: user says "收官", "twmd-finale", "完整收官", "session 結束 三件套", "finale".
Ready to connect★ 1k
- View details
twmd-memorySkillDocs & knowledge
Write Taiwan.md session memory via canonical MEMORY-PIPELINE. TRIGGER when: user says "收官", "寫 memory", "Beat 4", "session 收官".
Ready to connect★ 1k
- View details
refactorSkillDocs & knowledge
Improve code readability, enforce idiomatic Kotlin conventions, and enhance documentation quality in S3Mock without changing behavior. Use when asked to clean up code, improve naming, add KDoc, or align with Kotlin/project idioms. Also invoked by the implement and test skills before adding new code
Ready to connect★ 1k
- View details
adhd-output-styleSkillDocs & knowledge
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
Ready to connect★ 1k
- View details
curate-a-team-librarySkillDocs & knowledge
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack once the first pass is solid.
Ready to connect★ 1k
- View details
cpu-z180SkillDocs & knowledge
Z180 notes for z88dk: mlt multiply, math32_z180, eZ80 Z80-mode mlt share, ticks -mz180 / -mez80_z80, ASCI/IO context for yaz180/scz180 targets. Use when writing or measuring Z180 or eZ80-Z80-mode float/mul code.
Ready to connect★ 1k
- View details
cpu-z80SkillDocs & knowledge
Z80-family coding notes for z88dk library and app asm: IX/IY, exx, djnz, shadow registers, documented vs strict Z80, opcode map (flags and T-states). Use when writing or reviewing z80 (not 8085/8080/gbz80) assembly under libsrc or hand asm.
Ready to connect★ 1k
- View details
methodology-measureSkillDocs & knowledge
How to measure and prove z88dk library changes: z88dk-ticks TIMER/hotspots, map/nm proof, suite gates, A/B library swaps, math32 multi-CPU rebuilds, classic +test benchmarks, wiki number paste rules. Use when optimising, explaining deltas, or running +test -clib=8085 benches.
Ready to connect★ 1k
- View details
style-ste-writingSkillDocs & knowledge
Rewrite prose (docs, READMEs, PR descriptions, error messages, release notes, comments — never code) into ASD-STE100 Simplified Technical English to remove AI slop. Modes: strict (procedures/safety) and STE-flavored (general prose).
Ready to connect★ 1k
- View details
tool-asmppSkillDocs & knowledge
z88dk-asmpp assembler preprocessor helper. Niche; see wiki Tool---asmpp.
Ready to connect★ 1k
- View details
figure-duplicate-auditSkillDocs & knowledge
Audit scientific figures for duplicated, reused, transformed, or uninformative image panels. Use for \u56fe\u7247\u67e5\u91cd, \u8bba\u6587\u56fe\u50cf\u91cd\u590d, PDF figure \u5ba1\u6838, when the user attaches a PDF, asks to review selected PDF pages, or tags a directory containing manuscript inp
Ready to connect★ 1k
- View details
journal-club-pptSkillDocs & knowledge
Use this skill whenever the user provides a scientific paper PDF and asks for a group-meeting literature report, journal-club slides, 文献汇报PPT, 组会PPT, paper presentation, article walkthrough, or to explain a paper with PowerPoint. The skill first reconstructs the paper's scientific logic, then builds
Ready to connect★ 1k
- View details
literature-reviewSkillDocs & knowledge
Retrieve, verify, and synthesize scientific literature. Use for seminal-paper lookups, evidence summaries, method comparisons, and gap analyses. Every citation must come from a live lookup, never from memory; retractions are checked; the deliverable is argued prose with resolvable DOI links.
Ready to connect★ 1k
- View details
social-noteSkillDocs & knowledge
Turn a scientific conversation, paper takeaway, or figure story into paste-ready social copy. Use when the user asks for 小红书文案, a Xiaohongshu note, 微信/朋友圈, 公众号草稿, a tweet, Twitter/X copy, or share-to-social text from a Wisp session. Ask which platform unless the user already named one.
Ready to connect★ 1k
- View details
agent-team-designSkillDocs & knowledge
Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.
Ready to connect★ 1k
- View details
agentlas-operationsSkillDocs & knowledge
Agentlas system operation procedures — hep-network configuration, hep-graph automation, using cargo/Agent Cloud and marketplace, reusing workforce rosters, and memory contracts. One (personal agent) follows these procedures when operating Agentlas.
Ready to connect★ 1k
- View details
api-documentingSkillDocs & knowledge
Generate API documentation from code. Use when the user wants to document APIs, create API reference, generate endpoint documentation, or needs help with OpenAPI/Swagger specs.
Ready to connect★ 1k
- View details
api-generatingSkillDocs & knowledge
Generate API endpoint code and documentation from specifications. Use when the user wants to create new API endpoints, generate route handlers, scaffold REST APIs, or produce OpenAPI/Swagger specs from code.
Ready to connect★ 1k
- View details
doc-writingSkillDocs & knowledge
Generate API documentation from a route manifest. Use when you have a list of discovered routes and need to produce markdown documentation.
Ready to connect★ 1k
- View details
memory-ticketingSkillDocs & knowledge
Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.
Ready to connect★ 1k
- View details
pm-soulSkillDocs & knowledge
Use when preserving product intent, acceptance criteria, decision memory, open loops, roadmap context, or the product-manager continuity layer of an agent team.
Ready to connect★ 1k
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.
54,764 of the 55,196 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.