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: Monitoring & ops
2,353 results · page 1 of 79
- View details
lark-okrSkillMonitoring & ops
Lets your agent work with Lark apps like messaging, docs, sheets, calendar, mail, and tasks from the command line.
Ready to connect★ 17k
- View details
run-trainSkillMonitoring & ops
Lets your agent run training jobs from the rigorpilot skill toolkit.
Ready to connect★ 487
- View details
caveman-statsSkillMonitoring & ops
Lets your agent cut token usage by about 65% by responding in short, simplified caveman-style language.
Ready to connect★ 105k
- View details
agent-evalSkillMonitoring & ops
Lets your agent compare coding agents head-to-head on your own tasks with pass rate, cost, time, and consistency metrics.
Ready to connect★ 256k
- View details
architecture-decision-recordsSkillMonitoring & ops
Lets your agent record architecture decisions as numbered ADR documents in your repo with context, alternatives, and rationale.
Ready to connect★ 256k
- View details
claude-devfleetSkillMonitoring & ops
Lets your agent plan coding projects and run multiple coding agents in parallel, then track their progress and reports.
Ready to connect★ 256k
- View details
cost-trackingSkillMonitoring & ops
Lets your agent report Claude Code token usage, spending, and budgets from a local cost log.
Ready to connect★ 256k
- View details
dashboard-builderSkillMonitoring & ops
Lets your agent build monitoring dashboards for Grafana or SigNoz by organizing metrics around real operator questions.
Ready to connect★ 256k
- View details
django-celerySkillMonitoring & ops
Helps your agent add and manage background jobs, scheduled tasks, and async processing in Django apps using Celery.
Ready to connect★ 256k
- View details
github-opsSkillMonitoring & ops
Lets your agent triage GitHub issues, manage PRs, debug CI failures, prepare releases, and watch security alerts.
Ready to connect★ 256k
- View details
growth-logSkillMonitoring & ops
Lets your agent write structured learning notes after hard tasks or failures, extracting reusable patterns instead of diary entries.
Ready to connect★ 256k
- View details
healthcare-cdss-patternsSkillMonitoring & ops
Guides your agent in building clinical decision support code for drug interaction checks, dose validation, and clinical scoring.
Ready to connect★ 256k
- View details
dart-log-failure-parserSkillMonitoring & ops
Lets your agent extract and interpret failure details from Dart and Flutter test logs.
Ready to connect★ 179k
- View details
flutter-pr-checks-finderSkillMonitoring & ops
Lets your agent find failing checks on a Flutter pull request and get the LUCI log links.
Ready to connect★ 179k
- View details
internal-commsSkillMonitoring & ops
Lets your agent write internal communications like status reports, newsletters, and FAQs in your company's formats.
Ready to connect★ 176k
- View details
caveman-setupSkillMonitoring & ops
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
Ready to connect★ 105k
- View details
eng-runbookSkillMonitoring & ops
Lets your agent pull up an engineering runbook with service overviews, alerts, dashboards, on-call info, and incident steps.
Ready to connect★ 95k
- View details
html-ppt-knowledge-arch-blueprintSkillMonitoring & ops
Lets your agent read a written incident review of a data bug with root cause, fix, and follow-ups.
Ready to connect★ 95k
- View details
html-ppt-testing-safety-alertSkillMonitoring & ops
Lets your agent present a hospital data-governance briefing covering patient-data risk, controls, accountability, and board approval.
Ready to connect★ 95k
- View details
weekly-updateSkillMonitoring & ops
Lets your agent produce a weekly metrics report with key numbers, one anomaly, and the decision it requires.
Ready to connect★ 95k
- View details
observability-and-instrumentationSkillMonitoring & ops
Guides your agent to add logging, metrics, tracing, and alerting to code so production behavior can be seen and diagnosed.
Ready to connect★ 94k
- View details
babysitSkillMonitoring & ops
Lets your agent keep watching a pull request until its comments, reviews, and CI checks are all resolved.
Ready to connect★ 94k
- View details
error-monitoringSkillMonitoring & ops
Guides your agent through setting up error monitoring and checking that production failures get detected.
Ready to connect★ 74k
- View details
cli-cost-usageSkillMonitoring & ops
Lets your agent view AI cost breakdowns, token usage, and call logs, filtered by provider, model, or date.
Ready to connect★ 64k
- View details
cli-healthSkillMonitoring & ops
Lets your agent check server health, component status, and live metrics from the command line.
Ready to connect★ 64k
- View details
cli-mcpSkillMonitoring & ops
Lets your agent check server status, list tools, and view audit logs from the command line.
Ready to connect★ 64k
- View details
cli-policy-auditSkillMonitoring & ops
Lets your agent inspect audit logs, access policies, and telemetry from the command line, filtered by user or time.
Ready to connect★ 64k
- View details
cli-providersSkillMonitoring & ops
Lets your agent manage provider connections: list, add, test, and validate providers, rotate API keys, and view metrics.
Ready to connect★ 64k
- View details
cli-routingSkillMonitoring & ops
Lets your agent create, update, and delete routing combos, test strategies, and inspect metrics from the CLI.
Ready to connect★ 64k
- View details
omni-combos-routingSkillMonitoring & ops
Lets your agent create and test traffic routing strategies like round-robin, weighted, and fallback chains.
Ready to connect★ 64k
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.
52,524 of the 52,958 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.