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: Files & storage
4,446 results · page 141 of 149
- View details
mm-clear-gateSkillFiles & storage
A gate before /clear — a read-only check of "whether everything has been saved", with the verdict taken from the script's exit code, not from the model's reply. Checks the freshness of the GSD-handoff in the project repository, the freshness of vault files for Project Knowledge, the state of the vau
Ready to connect
- View details
mm-focusSkillFiles & storage
RETIRED 2026-08-02 — the command no longer loads anything. Its stage detection duplicated /gsd-resume-work and diverged from the actual GSD layout, causing it to load the wrong files without saying so. Replacement: /gsd-resume-work; for silent loading without a menu, directly ask to read the phase f
Ready to connect
- View details
mm-handoffSkillFiles & storage
Generates handoff.md — a compact summary for a new claude.ai chat when the current context is full. Includes a 15-category Session Guide (inspired by context-mode), a digest of recent sessions, current state, open questions, and (if GSD is present) the current phase + last 3 SUMMARY.md files. Use wh
Ready to connect
- View details
naming-consultantSkillFiles & storage
Suggests consistent, well-reasoned names for variables, functions, files, or classes given context. Use when a name feels off, ambiguous, or inconsistent with surrounding conventions.
Ready to connect
- View details
onboarding-guide-generatorSkillFiles & storage
Generates a new-engineer onboarding guide from a codebase's actual structure - setup steps, architecture overview, key files, and where to start. Use when a project has no onboarding doc or an outdated one.
Ready to connect
- View details
penpot-mcpSkillFiles & storage
Use this skill whenever the user wants to use AI agents to work with Penpot design files via the Penpot MCP Server. Triggers include: using Penpot through an AI agent, design files, design systems, design tokens, Penpot MCP, design-to-code, generating UI from design, auditing a design system, creati
Ready to connect
- View details
pin-recordSkillFiles & storage
Use when you need to record a single pin entity to the knowledge graph. Invokes lib/pins record() to validate and write a canonical .md file. Triggers on "record pin", "pin this", "save this as a pin".
Ready to connect
- View details
pin-setupSkillFiles & storage
Use when initializing the pins knowledge graph for the first time in a project. Guides the user through creating pins.yaml (the storage manifest). Triggers on "setup pins", "initialize pins", "create pins.yaml", "first-run pins".
Ready to connect
- View details
readme-builderSkillFiles & storage
Creates professional README files for GitHub projects, covering purpose, installation, usage, and contribution info. Use when a repo has no README or an outdated/thin one.
Ready to connect
- View details
self-improvementSkillFiles & storage
Capture user feedback and corrections to enhance repository documentation and skills. Transforms conversational feedback into persistent knowledge by updating the appropriate CLAUDE.md files, skills, or other documentation.
Ready to connect
- View details
slides-reviewSkillFiles & storage
HTML design review skill using Gemini CLI. Passes generated HTML files to Gemini to receive visual design improvement guidance, then fixes CSS/HTML in the main session. Includes an in-session fallback when Gemini is unavailable. Triggers: "디자인 리뷰", "gemini review", "design review", "디자인 검토", "디자인 보완
Ready to connect
- View details
source-command-qcheckSkillFiles & storage
Skeptical staff-engineer code review of changed files against coding-standards.md.
Ready to connect
- View details
subagent-task-orchestratorSkillFiles & storage
Decomposition playbook and anti-temptation rules for an orchestrator agent that routes work through the Surogates subagent task layer. Pair this skill with an AgentDef whose tool filter strips the implementation tools (terminal, file, web, code) — that's how 'don't do the work yourself' is enforced
Ready to connect
- View details
sync-claudeSkillFiles & storage
Validate and synchronize Claude documentation (CLAUDE.md files and skills) against actual codebase state. Two modes: full (all docs) or changed (only docs affected by current branch, default).
Ready to connect
- View details
xml-structure-reviewSkillFiles & storage
A check loop for 1C metadata XML structures: correctness of object files, forms, data composition schemas, roles, and templates; object registration within the configuration; two-way 'disk ↔ composition' reconciliation; object rights in extension roles. Invoked by the quality-gate orchestrator when
Ready to connect
- View details
ai-infrastructure-replicateSkillFiles & storage
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training
Ready to connect
- View details
annotation-reviewerSkillFiles & storage
Use this agent when you need to systematically review existing GO annotations for a gene and make curation decisions based on literature evidence and functional analysis. This agent should be called after seeding the SPECIES/GENE/GENE-ai-review.yaml file, which seeds each annotation with `action: PE
Ready to connect
- View details
api-baas-appwriteSkillFiles & storage
Appwrite backend-as-a-service — Auth, TablesDB, Storage, Functions, Realtime, permissions model, typed client
Ready to connect
- View details
api-baas-firebaseSkillFiles & storage
Firebase backend-as-a-service — Firestore, Authentication, Cloud Functions v2, Storage, Hosting, Admin SDK, security rules, emulator suite
Ready to connect
- View details
context-setupSkillFiles & storage
Build, import, or refresh this workspace's identity, project, reusable-workflow, and weekly-state files through a guided review. Use only when the user explicitly asks to initialize or redo workspace context.
Ready to connect
- View details
convert-to-devtoSkillFiles & storage
Converts Markdown content into the format required for Dev.to publication, ensuring correct YAML frontmatter, headers, liquid tags, and inline formatting. Use when the user asks to format or convert an existing blog post or Markdown file for Dev.to.
Ready to connect
- View details
core-function-synthesizerSkillFiles & storage
Use this agent when you need to synthesize and distill the core functions of a gene from multiple information sources (textual summaries, reviewed annotations, bioinformatics analysis) and populate the `core_functions` section of a gene review YAML file. This agent should be called after completing
Ready to connect
- View details
deepenSkillFiles & storage
Use when the user wants to know where the design is hurting, before choosing what to fix: "this is getting messy", "where should we clean up?", "what is the worst part of this codebase?", "why is this so hard to change?", "it takes five files to add one field". Surveys an area, ranks the candidates,
Ready to connect
- View details
desktop-agentSkillFiles & storage
Native Windows desktop bridge — breaks out of Claude Code's Git Bash sandbox to open terminal windows, launch URLs, open files, run commands, and send toast notifications on the user's actual desktop. Use when: (1) user says "open", "launch", "start", "show me", "pop up", "new window", (2) you need
Ready to connect
- View details
direct-integrationsSkillFiles & storage
Query Gmail, Google Calendar, Asana, Slack, Google Sheets, Google Docs, and Google Drive directly via Python APIs. Use when the user asks to check email, view calendar, list tasks, check Slack messages, read/write spreadsheets, read documents, or find files in Drive. Triggers on requests like "check
Ready to connect
- View details
download-encodeSkillFiles & storage
Download ENCODE genomics files (BED, FASTQ, BAM, bigWig, etc.) to the user's machine. Use when the user wants to download data files from ENCODE experiments.
Ready to connect
- View details
evolveSkillFiles & storage
Cluster related instincts into higher-level skills. Analyzes instinct patterns and generates consolidated skill files.
Ready to connect
- View details
explainSkillFiles & storage
Explain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system overview. What it does and why, not whether it's good.
Ready to connect
- View details
frappe-driveSkillFiles & storage
Frappe Drive guidance for files, folders, sharing, permissions, storage, previews, document workflows, and file-linked business processes. Use when work touches Frappe Drive or file management in the Frappe ecosystem.
Ready to connect
- View details
homie-self-mapSkillFiles & storage
Framework architecture map for The Homie. Use when an agent needs to understand the framework's vertical slice structure, locate key files, or extend the framework (add a skill, slash command, integration, or lane). Load this skill BEFORE attempting to modify or extend the framework.
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.
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.