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: Dev tools
16,902 results · page 326 of 564
- View details
mock-chargeSkillDev tools
Simulate a provider charge locally for deterministic Runx harness tests.
Ready to connect★ 90
- View details
mock-refundSkillDev tools
Simulate a refund locally for deterministic Runx harness tests.
Ready to connect★ 90
- View details
moltbookSkillDev tools
Scan Moltbook for credible opportunities, prepare evidence-bound posts, and publish an exact approved payload through any compatible provider binding with readback.
Ready to connect★ 90
- View details
n8n-handoffSkillDev tools
Validate a runx execution context and hand off a governed payload to an n8n workflow through any compatible provider binding, with idempotency and receipt-backed readback.
Ready to connect★ 90
- View details
nitrosend-provider-operationSkillDev tools
Execute one bounded Nitrosend MCP operation through Runx native HTTP.
Ready to connect★ 90
- View details
nws-weather-forecastSkillDev tools
Fetch National Weather Service forecast evidence through the governed HTTP front, producing a sealed provider packet for downstream weather planning.
Ready to connect★ 90
- View details
open-meteo-weather-forecastSkillDev tools
Resolve a place and fetch global forecast and air-quality evidence through governed, keyless Open-Meteo HTTP calls.
Ready to connect★ 90
- View details
openapi-adapterSkillDev tools
External-adapter sub-skill; turns an OpenAPI operation into a sealed tool result.
Ready to connect★ 90
- View details
openapi-graphSkillDev tools
OpenAPI front example; a graph whose step turns an OpenAPI operation into a sealed tool result.
Ready to connect★ 90
- View details
operator-inboxSkillDev tools
Maintain a provider-neutral local action queue from bounded provider observations and explicit human dispositions.
Ready to connect★ 90
- View details
ops-laneSkillDev tools
Deterministic fixture lane for the business-ops graph example.
Ready to connect★ 90
- View details
pay-fulfill-railSkillDev tools
Return a mock rail success without a required x402 rail proof.
Ready to connect★ 90
- View details
pay-quoteSkillDev tools
Refuse a malformed x402 challenge without issuing a quote.
Ready to connect★ 90
- View details
pay-reserveSkillDev tools
Refuse ambiguous x402 quote bounds without issuing a reservation.
Ready to connect★ 90
- View details
post-merge-final-outcome-publisherSkillDev tools
Publish a final provider-state update through the Rust thread-outbox-provider front.
Ready to connect★ 90
- View details
purchase-approvalSkillDev tools
Decide whether one proposed purchase is allowed under an explicit procurement policy before any spend flow starts, refusing budget overages and unapproved vendors instead of guessing.
Ready to connect★ 90
- View details
reflect-digestSkillDev tools
Internal reflection stage that groups durable run signals by skill and emits validated handoffs to skill-lab improve when evidence clears configured floors. Use diagnose-skill-run, run-history, or skill-lab directly instead.
Ready to connect★ 90
- View details
research-analyzeSkillDev tools
Internal evidence-index analysis and verification stage for the canonical research skill.
Ready to connect★ 90
- View details
return-refundSkillDev tools
Help return an item or request a refund from any retailer. Identifies the item, finds the return policy, navigates the process, and handles shipping labels or phone calls.
Ready to connect★ 90
- View details
review-skillSkillDev tools
Inspect, safely test, and assess one Runx skill package for capability, trust, and operator readiness. Use when deciding whether to adopt, improve, reject, install, or publish a skill; its evidence-only assess runner is available when native test evidence already exists.
Ready to connect★ 90
- View details
sbom-makerSkillDev tools
Derive a CycloneDX software bill of materials from a supplied lockfile deterministically, digest-bound to the exact bytes, with license risks surfaced and unsupported or unpinned lockfiles refused.
Ready to connect★ 90
- View details
scafld-native-smokeSkillDev tools
Prove the hosted scafld binary through the native v2 lifecycle.
Ready to connect★ 90
- View details
schema-guardSkillDev tools
Check a proposed API or data contract against the current contract, real sample payloads, and a compatibility policy, and gate publication behind a refusable verdict with native digest evidence.
Ready to connect★ 90
- View details
sign-receiptSkillDev tools
Bind an off-runtime action claim to opaque evidence references in a signed Runx receipt without pretending Runx verified the external action.
Ready to connect★ 90
- View details
- View details
speckit-git-commitSkillDev tools
Auto-commit changes after a Spec Kit command completes
Ready to connect★ 90
- View details
speckit-git-initializeSkillDev tools
Initialize a Git repository with an initial commit
Ready to connect★ 90
- View details
- View details
speckit-git-validateSkillDev tools
Validate current branch follows feature branch naming conventions
Ready to connect★ 90
- View details
summarizeSkillDev tools
Summarize supplied text while preserving material caveats.
Ready to connect★ 90
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.