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 249 of 296
- View details
deductive-verification-with-dafny-and-why3SkillAI & models
Use when an imperative program needs pre-conditions, post-conditions, and loop invariants proved automatically by SMT in Dafny or Why3, short of a tactic prover.
Ready to connect
- View details
deprecate-and-migrateSkillAI & models
Use when asked to remove old code, migrate consumers, or decide whether to maintain or sunset a system. Not for untracked data or changes without VCS rollback.
Ready to connect
- View details
dimensional-analysisSkillAI & models
Lets your agent add comments to code that document units and dimensions, catching unit-mismatch bugs early.
Ready to connect
- View details
doubt-drivenSkillAI & models
Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.
Ready to connect
- View details
enforce-workflow-constraintsSkillAI & models
Use when any bounded workflow starts or reaches an action, path, proposal, or merge boundary. Refuses rather than default-allow on an unreadable constraint set.
Ready to connect
- View details
erc-8004SkillAI & models
Build with ERC-8004 Trustless Agents - on-chain agent identity, reputation, validation, and discovery on EVM chains. Use when registering AI agents on-chain, building agent reputation systems, searching/discovering agents, working with the Agent0 SDK (agent0-sdk), or implementing the ERC-8004 standa
Ready to connect
- View details
extremely-optimizeSkillAI & models
Use when asked to run a performance campaign against a measured floor. Not for hypothesis-only analysis without mutation: use fastopt.
Ready to connect
- View details
fastoptSkillAI & models
Use when optimizing suspected hot paths without waiting for benchmarks. Not for estimated-floor optimization: use fastopt-extreme. Not for measured-floor rebuild campaigns: use extremely-optimize.
Ready to connect
- View details
fastopt-extremeSkillAI & models
Use when optimizing estimated hot and complexity-neutral cold paths while refusing complexity theater. Not for measured-floor rebuilds: use extremely-optimize. Not for hypothesis-only: use fastopt.
Ready to connect
- View details
final-grainSkillAI & models
Use when asked to push an already-working artifact to finished composition, texture, and feel. Not for remote or irreversible changes. Not for hygiene routing: use clean-and-true.
Ready to connect
- View details
finish-branch-menuSkillAI & models
Use when implementation is complete, the test suite is green, and an integration decision is needed for a development branch or worktree. Not for failing tests or starting new work.
Ready to connect
- View details
fix-p0-issuesSkillAI & models
Use when the user asks to fix P0s, address critical issues, or work on priorities from the weekly product briefing. Don''t use for non-P0 issues or local bug fixes.
Ready to connect
- View details
frictionSkillAI & models
Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
Ready to connect
- View details
from-business-perspectiveSkillAI & models
Use when the user wants an answer only from the business seat: money, customers, timing. Not for any other from-* lens seat or multi-lens synthesis.
Ready to connect
- View details
from-career-perspectiveSkillAI & models
Use when a user wants an answer only from the career seat: effects on human trajectories. Not for any other from-* lens seat or multi-lens synthesis.
Ready to connect
- View details
from-codebase-perspectiveSkillAI & models
Use when asked to answer only from the codebase seat: what existing code tolerates or punishes. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
from-human-perspectiveSkillAI & models
Use when a user wants an answer only from the human seat: what a person can love, trust, and tolerate. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
from-impact-perspectiveSkillAI & models
Use when asked to answer only from the impact seat: who and what actually moves. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
from-innovation-perspectiveSkillAI & models
Use when the user wants an answer only from the innovation seat. Not for rebuilding from primitives: use from-first-principle. Read-only. No source or remote mutation.
Ready to connect
- View details
from-moat-perspectiveSkillAI & models
Use when the user wants an answer only from the moat seat: building, keeping, and thickening defensibility. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
from-rentseeking-perspectiveSkillAI & models
Use when the user wants an answer only from the rent-seeking seat: extraction without building. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
from-skeptic-perspectiveSkillAI & models
Use when the user wants an answer only from the skeptic seat: cold reasoning without project loyalty. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
from-stability-perspectiveSkillAI & models
Use when the user wants an answer only from the stability seat: preservation of the working machine. Not for rebuilding from primitives: use from-first-principle.
Ready to connect
- View details
fromzeroSkillAI & models
Use when replacing a greenfield attempt with a clean pad of verified requirements. Not for rebuilding from primitives: use from-first-principle. Requires a committed, VCS-recoverable attempt.
Ready to connect
- View details
frontend-fidelity-rebuildSkillAI & models
Use when an authorized reference surface needs a clean-room frontend reconstruction across static, motion, and responsive fidelity. Not for styling or component work without a reference surface.
Ready to connect
- View details
fuzz-harness-writingSkillAI & models
Use when a user needs to create or improve a deterministic, engine-agnostic fuzz harness for raw or structured target inputs. Not for coverage measurement: use fuzzing-coverage-analysis.
Ready to connect
- View details
fuzzing-obstaclesSkillAI & models
Helps your agent patch out checksum checks and other obstacles so a fuzzer can explore more code.
Ready to connect
- View details
gate-and-mergeSkillAI & models
Use when landing a queue of open PRs: gate each PR, sweep its review feedback to root cause, then merge, repair, hold, or close it. Human-only.
Ready to connect
- View details
gh-review-requestsSkillAI & models
Lets your agent find GitHub pull requests where your team's review is requested.
Ready to connect
- View details
git-cleanupSkillAI & models
Use when the user explicitly invokes branch or worktree cleanup for a repo with accumulated local branches. Don''t use for remote branch deletion or force-push operations.
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.
53,585 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.