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: AI & models
8,868 results · page 227 of 296
- View details
churn-predictionSkillAI & models
Build churn prediction models — leading indicators, risk scoring, early warning systems, intervention playbooks. Triggers on: "churn prediction", "predict churn", "churn model", "early warning", "risk scoring".
Ready to connect★ 52
- View details
codeSkillAI & models
Implement production changes with or without new test coverage.
Ready to connect★ 52
- View details
coherence-engineSkillAI & models
The LLM as consistency maintainer and orchestrator
Ready to connect★ 52
- View details
dev-debugSkillAI & models
Debug an issue by identifying root causes, fixing the most probable one, testing, and committing. Use with "/dev-debug <description of the issue>".
Ready to connect★ 52
- View details
dev3-prdSkillAI & models
Generate questions, clarify unknowns, then write a PRD using pyramid principles. Sub-skill of the /dev workflow.
Ready to connect★ 52
- View details
dev4-implementSkillAI & models
Implement a feature from its PRD. Creates a work tree if needed, writes clean code following Google-level standards, and tests iteratively. Sub-skill of the /dev workflow.
Ready to connect★ 52
- View details
dev5-reviewSkillAI & models
Review implemented code for quality, correctness, and style. Produces review comments and creates a commit. Sub-skill of the /dev workflow.
Ready to connect★ 52
- View details
dev6-review-fixSkillAI & models
Apply fixes for review comments from dev5-review and commit. Sub-skill of the /dev workflow.
Ready to connect★ 52
- View details
dev7-prSkillAI & models
Create a PR, push to GitHub, wait for Greptile review, address comments, and push final. Sub-skill of the /dev workflow.
Ready to connect★ 52
- View details
draft-prSkillAI & models
Prepare commits, push a branch, and create a draft PR targeting your base branch.
Ready to connect★ 52
- View details
emacsSkillAI & models
GNU Emacs as a stateful Lisp machine for agents — daemon, moo-* protocol, emacs.py router, emacs:// URLs, spoken grammar, play-learn-lift.
Ready to connect★ 52
- View details
enterprise-salesSkillAI & models
Create an Enterprise Deal Execution Pack (buying committee map, mutual action plan, ROI model).
Ready to connect★ 52
- View details
fable-promptSkillAI & models
Rewrite a rough, terse, or under-specified request into a prompt that follows Anthropic's "Prompting Claude Fable 5.1" guide, then carry it out. Use only when the user invokes it: "/fable-prompt …", "프롬프트 개선해서", "가이드에 맞게 요청해", "제대로 시켜줘", "improve this prompt", "prompt it properly". Do not trigger on
Ready to connect★ 52
- View details
fill-formSkillAI & models
Intelligently fill web forms using provided data — handles text fields, dropdowns, checkboxes, radio buttons, and multi-step forms. Use when the user asks to fill out, complete, or submit a form.
Ready to connect★ 52
- View details
find-alternativesSkillAI & models
Find alternative products to something the user is looking at or considering. Searches across retailers and review sites, compares options, and delivers a ranked HTML report with ratings, pricing, and direct links. Use when the user asks for alternatives, similar products, or "something like this bu
Ready to connect★ 52
- View details
gtm-tool-cost-modelSkillAI & models
GTM tool cost modeling — per-seat licensing, usage-based fees, cloud infra, enrichment credits, annual vs monthly contracts, and fully-loaded RevOps stack TCO. Use when budgeting GTM tools, calculating cost per rep, vendor renewal negotiation, or stack ROI. Triggers on: "GTM tool budget", "tool cost
Ready to connect★ 52
- View details
interrogeSkillAI & models
Structured questioning to scope a feature or brainstorm an app: one question at a time, walks down the decision tree, justified recommendation. Triggered by /interroge, "help me plan", "I have an app/feature idea".
Ready to connect★ 52
- View details
lenny-skillpack-creatorSkillAI & models
Convert a Refound/Lenny Skill into an agent-executable Skill Pack.
Ready to connect★ 52
- View details
livreSkillAI & models
Commits changes, syncs with remote main, pushes the current branch and creates a Pull Request. Refuses to run directly on main. Triggered by /livre, or when the user wants to deliver/ship their work: "commit and push", "open a PR", "ship this", "ship", "send the
Ready to connect★ 52
- View details
manage-bookmarksSkillAI & models
Organize bookmarks — find duplicates, categorize by topic, create a clean folder structure, and clean up unused bookmarks. Use when the user asks to organize, clean up, sort, or manage their bookmarks.
Ready to connect★ 52
- View details
orchestration-templateSkillAI & models
Reference template for multi-agent orchestrated skills. Use as a pattern when creating complex skills that need parallel execution.
Ready to connect★ 52
- View details
organizational-transformationSkillAI & models
Lead org transformation toward a product operating model: diagnostic, pilot plan, roadmap, governance.
Ready to connect★ 52
- View details
organize-tabsSkillAI & models
Analyze open tabs, group related ones by topic, close duplicates, and clean up tab clutter. Use when the user asks to organize, clean up, sort, or manage their tabs.
Ready to connect★ 52
- View details
planifieSkillAI & models
Break a PRD into independently deliverable phases as vertical slices (tracer bullets), then produce or extend `docs/PLAN.md` using a fixed template (architectural decisions + phases with user stories, deliverable, acceptance criteria, dependencies). Trigger on /planifie, "découpe le PRD",
Ready to connect★ 52
- View details
pr-descriptionSkillAI & models
Generate a PR description for the current branch against your base branch.
Ready to connect★ 52
- View details
prioritizing-roadmapSkillAI & models
Prioritize product roadmap: scoring model, ranked opportunities, decision narrative. See also: technical-roadmaps (engineering roadmap).
Ready to connect★ 52
- View details
- View details
smithSkillAI & models
Initialize SpecKit on a new or existing project — scans the codebase, interviews you about project details, and generates CLAUDE.md, constitution.md, and the full .specify/ scaffolding with commands and agents.
Ready to connect★ 52
- View details
smith-auditSkillAI & models
Run a comprehensive audit on a specific system or all systems. Prompts for system selection, then runs all sub-audits and produces a unified report.
Ready to connect★ 52
- View details
smith-syncSkillAI & models
Sweep team-shareable .smith/ artifacts (manifest, .meta describe layer, ledger, bank, agents, sessions) AND debug reports (.specify/systems/*/debug/, .specify/debug/) into a single chore commit and push directly to the default branch. Runs automatically at the end of smith-new / smith-bugfix / smith
Ready to connect★ 52
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.
53,585 of the 54,017 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.