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
54,220 results · page 401 of 1,808
- View details
optimization-suggestSkillMonitoring & ops
Analyzes your agent's past sessions to suggest ways to cut costs, speed up work, and avoid errors.
Ready to connect★ 1k
- View details
pattern-detectSkillMonitoring & ops
Lets your agent find recurring workflow patterns and tool-use sequences in monitoring logs.
Ready to connect★ 1k
- View details
productivity-scoreSkillMonitoring & ops
Lets your agent calculate a productivity score from session metrics like completion rates, cache efficiency, and tool success ratios.
Ready to connect★ 1k
- View details
push-to-forked-prSkillMonitoring & ops
Lets your agent push your current code changes straight to an existing GitHub pull request that lives on a fork.
Ready to connect★ 1k
- View details
quick-statsSkillMonitoring & ops
One-line summary of key Agent Monitor metrics — active sessions, total cost from the pricing engine, events today from daily_events, top tool from tool_usage, and current model from the most recent session. Use for a fast at-a-glance check without leaving the terminal.
Ready to connect★ 1k
- View details
regression-alertSkillMonitoring & ops
Lets your agent compare reliability metrics between two periods and flag when error or tool-failure rates get worse.
Ready to connect★ 1k
- View details
regression-watchSkillSearch
Lets your agent spot when error rates, cache hits, session costs, and other metrics get worse over time.
Ready to connect★ 1k
- View details
release-guardSkillMonitoring & ops
Lets your agent run release-readiness checks on a repository before merging or releasing.
Ready to connect★ 1k
- View details
reliability-reportSkillMonitoring & ops
Lets your agent generate a reliability report from session outcomes, alerts, tool failures, and data freshness.
Ready to connect★ 1k
- View details
remote-collectionSkillMonitoring & ops
Lets your agent add, edit, test, and remove remote machines that collect coding history over SSH.
Ready to connect★ 1k
- View details
repo-onboardingSkillMonitoring & ops
Understand this repository quickly before making changes. Use for architecture discovery, ownership mapping, command selection, and initial implementation planning.
Ready to connect★ 1k
- View details
run-historySkillMonitoring & ops
Lets your agent look up past dashboard runs and check their start and end status.
Ready to connect★ 1k
- View details
session-cleanupSkillMonitoring & ops
Lets your agent find stale agent sessions and preview which ones would be permanently deleted before cleanup.
Ready to connect★ 1k
- View details
session-compareSkillMonitoring & ops
Lets your agent compare two sessions side by side, showing token usage, costs, and workflow complexity per model.
Ready to connect★ 1k
- View details
session-debugSkillCommunication
Lets your agent inspect and debug a session's event chain, agent hierarchy, and token usage.
Ready to connect★ 1k
- View details
session-reportSkillMonitoring & ops
Lets your agent generate a detailed session report covering token usage, costs, tool calls, and errors.
Ready to connect★ 1k
- View details
session-timelineSkillMonitoring & ops
Lets your agent view a timeline of a Claude Code session's events with durations, tool names, errors, and gaps.
Ready to connect★ 1k
- View details
ship-featureSkillDocs & knowledge
Guides your agent to implement a new feature end-to-end with verification and docs updates.
Ready to connect★ 1k
- View details
skill-inventorySkillMonitoring & ops
Lets your agent list installed skills and plugins and spot overlaps with your own skills.
Ready to connect★ 1k
- View details
slo-checkSkillMonitoring & ops
Lets your agent track service-level goals like session completion and error rates, then report the remaining error budget.
Ready to connect★ 1k
- View details
spend-forecastSkillDatabases & data
Lets your agent forecast Claude Code spending to the end of the week or month from daily usage trends.
Ready to connect★ 1k
- View details
sprint-summarySkillMonitoring & ops
Lets your agent summarize a sprint of Claude Code activity by project, cost, token efficiency, and velocity.
Ready to connect★ 1k
- View details
time-of-daySkillDatabases & data
Lets your agent analyze your coding session timestamps to find your most active and productive hours and days.
Ready to connect★ 1k
- View details
transcript-grepSkillSearch
Lets your agent search a Claude Code session transcript for a string or regex and show matching messages with context.
Ready to connect★ 1k
- View details
transcript-replaySkillCommunication
Lets your agent replay a Claude Code session transcript turn-by-turn with a summary of each message.
Ready to connect★ 1k
- View details
update-project-docsSkillDocs & knowledge
Keeps a repository's documentation automatically updated after code, config, or feature changes.
Ready to connect★ 1k
- View details
usage-trendsSkillDatabases & data
Lets your agent analyze Claude Code usage trends like session counts, token volumes, and tool usage over time.
Ready to connect★ 1k
- View details
webhook-managementSkillCommunication
Lets your agent set up, test, and manage webhook alert targets across chat and incident services.
Ready to connect★ 1k
- View details
weekly-reportSkillMonitoring & ops
Lets your agent compile a weekly report of usage trends, costs, token volumes, and tool activity from Agent Monitor data.
Ready to connect★ 1k
- View details
workflow-optimizerSkillMonitoring & ops
Lets your agent analyze how its multi-step workflows run and get suggestions to make them faster and more reliable.
Ready to connect★ 1k
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.
53,788 of the 54,220 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.