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
70,704 results · page 1608 of 2,357
- View details
monte-carlo-storage-cost-analysisSkillFiles & storage
Lets your agent analyze a data warehouse to find stale, unused, or redundant tables and their storage costs.
Ready to connect★ 94
- View details
monte-carlo-troubleshoot-agent-tracesSkillMonitoring & ops
Lets your agent troubleshoot AI agent alerts and traces, like eval score drops or latency spikes.
Ready to connect★ 94
- View details
night-watchSkillAI & models
Pre-flight for leaving agents running unattended: pin the done predicate, the wake mechanism, the verifier, the budgets, the trail, and the escalation gates, then hand off to the matching long-run playbook. Use for /night-watch, 'set up an overnight run', 'I'm going to bed, set this up', 'run this w
Ready to connect★ 94
- View details
no-stupid-testsSkillFiles & storage
Spawn Test Butcher on the scoped test files, trim tests that are not worth keeping, then write the real tests it flags as missing. Use for /no-stupid-tests, 'stupid tests', 'slop tests', 'butcher the tests', or before review of any diff that adds or changes tests.
Ready to connect★ 94
- View details
peteySkillAI & models
Peter's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for petey, `/petey` or request to work in this style
Ready to connect★ 94
- View details
proof-planSkillDev tools
Write the proof before the code: turn a brief or feature request into the checks that will show it works on the real surface, with the evidence each check saves. Use for /proof-plan, 'how will we know it works', 'define done', 'verification plan', or after /grill and before building anything.
Ready to connect★ 94
- View details
push-ingestionSkillMonitoring & ops
Guides your agent through writing scripts that push data metadata, lineage, and query logs into Monte Carlo.
Ready to connect★ 94
- View details
rewrite-thisSkillCommunication
Rewrite text in my voice, ready to paste into Slack.
Ready to connect★ 94
- View details
serial-debugSkillSearch
Lets your agent debug serial devices by listing ports, reading and writing serial data, and controlling RTS/DTR lines.
Ready to connect★ 93
- View details
setup-peteySkillAI & models
Install or verify Petey's tracked Pi model routing. Use when setting up Petey, changing role routing, or checking role models after a Pi restart.
Ready to connect★ 94
- View details
toolkit-skill-authorSkillAI & models
Lets your agent write new skills for the mc-agent-toolkit, checking naming rules and registering them properly.
Ready to connect★ 94
- View details
tune-monitorSkillDatabases & data
Lets your agent analyze a Monte Carlo data monitor and suggest config changes to cut down alert noise.
Ready to connect★ 94
- View details
typescript-monorepoSkillDocs & knowledge
Lets your agent follow best practices for TypeScript monorepos using this typescript claude skill.
Ready to connect★ 94
- View details
unifi-network-diagnosticsSkillDev tools
Peter's UniFi home-network investigation. Family Room Apple TV Netflix buffering, U6 Pro RF utilization, ASUS interference tests, WAN health, and switch link problems. Use only when explicitly invoked (/skill:unifi-network-diagnostics).
Ready to connect★ 94
- View details
unoplat-code-confluence-cliSkillDocs & knowledge
Lets your agent analyze code repositories and generate AGENTS.md docs, including opening pull requests with them.
Ready to connect★ 94
- View details
agent-compat-syncSkillFiles & storage
Lets your agent link Claude and Codex instruction files so a repo works with both agents.
Ready to connect★ 93
- View details
arch-designSkillSecurity
Lets your agent think through system architecture before coding, covering goals, components, failures, security, and trade-offs.
Ready to connect★ 92
- View details
ceoSkillProductivity
Lets your agent act as the CEO Claude skill that reviews a mail federation and spawns middle managers on schedule.
Ready to connect★ 93
- View details
chrome-devtools-storybookSkillWeb & browsing
Lets your agent test Storybook components in Chrome by opening each story page automatically.
Ready to connect★ 93
- View details
claude-5-best-practiceSkillAI & models
Guides your agent to pick the right Claude 5 model tier and settings for cost-effective, reliable results.
Ready to connect★ 93
- View details
clean-my-loopSkillFiles & storage
Lets your agent audit and clean the memory files and prompts that feed its recurring task loops.
Ready to connect★ 93
- View details
cobra-viperSkillDocs & knowledge
Guides your agent in building command-line apps with the Cobra and Viper libraries.
Ready to connect★ 93
- View details
create-storybook-docsSkillDocs & knowledge
Lets your agent create Claude Skill-quality Storybook stories and docs for Spark UI components.
Ready to connect★ 93
- View details
english-swe-dailySkillCommunication
Coaches your agent to help you practice and improve English for software engineering chats, standups, and meetings.
Ready to connect★ 93
- View details
fileflow-pathologizeSkillFiles & storage
Guides your agent to safely move, copy, rename, and sanitize file paths when writing Go code.
Ready to connect★ 93
- View details
free-my-cpuSkillCloud & infra
Lets your agent audit and reduce CPU load on slow servers using the free claude skill for diagnostics.
Ready to connect★ 93
- View details
free-my-diskSkillFiles & storage
Lets your agent audit a full Mac or Linux disk and safely reclaim space using this free claude skill.
Ready to connect★ 93
- View details
gitxSkillAI & models
Lets your agent turn messy code changes into clean Git commits, branches, and GitHub pull requests.
Ready to connect★ 93
- View details
gpt-5-6-best-practiceSkillAI & models
Helps your agent pick the right GPT-5.6 model tier and reasoning effort to get good results at lower cost.
Ready to connect★ 93
- View details
grafana-best-practiceSkillCloud & infra
Lets your agent review, improve, and deploy Grafana dashboards and alert rules using this grafana claude skill.
Ready to connect★ 93
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
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.
68,574 of the 70,704 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 workspace 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.