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.
Filter by category
54,017 results · page 95 of 1,801
- View details
pua-p9SkillAI & models
Lets your agent invoke the pua-p9 alias that maps Codex subcommands to a Claude Code-style /pua:p9 command.
Ready to connect★ 20k
- View details
pua-proSkillAI & models
Lets your agent run Codex commands through a short alias command.
Ready to connect★ 20k
- View details
pua-reap-orphansSkillAI & models
Lets your agent clean up orphaned sessions or resources left behind by other agent runs.
Ready to connect★ 20k
- View details
pua-surveySkillAI & models
Lets your agent run a survey command through a Codex alias mapped from Claude Code usage.
Ready to connect★ 20k
- View details
pua-team-statusSkillAI & models
Lets your agent check and report team status on demand using a single command alias.
Ready to connect★ 20k
- View details
pua-teardown-allSkillAI & models
Lets your agent run a teardown command that clears all PUA prompt sessions at once.
Ready to connect★ 20k
- View details
pua-traeSkillProductivity
Lets your agent use pressure-style motivational prompts to push through repeated task failures and unverified completions.
Ready to connect★ 20k
- View details
pua-yesSkillAI & models
Lets your agent automatically answer yes to confirmation prompts when running the Codex CLI subcommand.
Ready to connect★ 20k
- View details
shotSkillAI & models
Lets your agent adopt a compact instruction set that pushes it to demand evidence before answering.
Ready to connect★ 20k
- View details
yesSkillDev tools
Changes your agent's tone to a warm, encouraging coach that praises and motivates while doing the same work.
Ready to connect★ 20k
- View details
notebooklmSkillSecurity
Lets your agent manage Gemini Notebook: add sources, chat over them, and generate or download artifacts like mind maps.
Ready to connect★ 19k
- View details
cranelift-auditorSkillDev tools
Lets your agent audit the Cranelift compiler codebase to find bugs and miscompilations and write structured reports.
Ready to connect★ 19k
- View details
reduce-test-casesSkillDev tools
Lets your agent shrink a failing Wasmtime/Cranelift test case down to the smallest input that still reproduces the bug.
Ready to connect★ 19k
- View details
wasmtime-auditorSkillSecurity
Guides your agent to audit Wasmtime's code for undiscovered bugs and security vulnerabilities and write test-case-backed reports.
Ready to connect★ 19k
- View details
agent-sourcesSkillMonitoring & ops
Lets your agent understand how ccusage reads agent logs, maps records to tokens and models, and computes costs.
Ready to connect★ 19k
- View details
cmux-debugSkillDev tools
Lets your agent run a command in a real terminal pane and capture its rendered output to verify how it displays.
Ready to connect★ 19k
- View details
commitSkillCommunication
Lets your agent split code changes into small, clean git commits with well-written messages.
Ready to connect★ 19k
- View details
developmentSkillDev tools
Guides your agent through ccusage repo work like editing packages, running builds, and tests.
Ready to connect★ 19k
- View details
fix-ciSkillMonitoring & ops
Lets your agent diagnose and fix failing GitHub Actions checks on a pull request using logs and local testing.
Ready to connect★ 19k
- View details
nushellSkillFiles & storage
Guides your agent in writing and editing Nushell scripts in the ccusage repo, following its style and validation rules.
Ready to connect★ 19k
- View details
profileSkillDev tools
Lets your agent profile the ccusage CLI's speed to find slow spots and verify that optimizations actually helped.
Ready to connect★ 19k
- View details
reduce-similaritiesSkillFiles & storage
Lets your agent scan Rust files to find duplicated functions and types that could be merged.
Ready to connect★ 19k
- View details
rustSkillDev tools
Guides your agent when editing the Rust code of the ccusage CLI, covering crate layout, visibility rules, and pricing data.
Ready to connect★ 19k
- View details
rust-binary-sizeSkillDev tools
Guides your agent in measuring and shrinking the size of a Rust executable when Cargo profiles or dependencies change.
Ready to connect★ 19k
- View details
adding-a-triggerSkillCloud & infra
Guides your agent through adding a new trigger type to Windmill across backend, frontend, and CLI.
Ready to connect★ 18k
- View details
ai-chatSkillAI & models
Gives your agent guidance for improving the Windmill AI chat copilot, covering tools, prompts, and context handling.
Ready to connect★ 18k
- View details
ai-evalsSkillDev tools
Lets your agent write and run benchmark test cases to check AI-generated scripts and workflows.
Ready to connect★ 18k
- View details
cli-commandsSkillDev tools
Lets your agent run and debug Windmill CLI commands, including inspecting job history and fixing failed jobs.
Ready to connect★ 18k
- View details
local-reviewSkillSecurity
Lets your agent review the current PR or branch diff for bugs, security issues, and AGENTS.md compliance.
Ready to connect★ 18k
- View details
local-review-codexSkillAI & models
Lets your agent run the same CI pull request code review on your local unpushed work before you push.
Ready to connect★ 18k
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.