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 400 of 1,808
- View details
cost-reportSkillMonitoring & ops
Lets your agent generate cost and token usage reports broken down by model, provider, source, and session.
Ready to connect★ 1k
- View details
cwd-rollupSkillMonitoring & ops
Lets your agent summarize AI coding sessions per project folder with counts, cost, tokens, and last-active times.
Ready to connect★ 1k
- View details
dag-mapSkillDatabases & data
Lets your agent visualize the parent-child agent orchestration tree for a session, including depth and fan-out.
Ready to connect★ 1k
- View details
daily-budget-checkSkillMonitoring & ops
Run a daily spend check-in against a daily budget on the Agent Monitor dashboard — today's spend vs the daily target, pace through the day, and the projected overage if the current pace holds. Uses /api/pricing/cost and /api/sessions (grouped by started_at = today). Use for a quick daily spend check
Ready to connect★ 1k
- View details
dashboard-statusSkillMonitoring & ops
Lets your agent check dashboard health, session counts, and data freshness.
Ready to connect★ 1k
- View details
data-exportSkillDatabases & data
Lets your agent export its session and usage data as JSON, CSV, or Markdown files for backup or reporting.
Ready to connect★ 1k
- View details
debug-live-issueSkillMonitoring & ops
Lets your agent debug production-like issues in a repo using disciplined evidence gathering.
Ready to connect★ 1k
- View details
delegation-auditSkillMonitoring & ops
Lets your agent audit which models handled which subagents and spot wasted or failing delegations.
Ready to connect★ 1k
- View details
endpoint-probeSkillDatabases & data
Lets your agent check each API endpoint of an Agent Monitor install and report status, latency, and reachability.
Ready to connect★ 1k
- View details
error-propagationSkillMonitoring & ops
Lets your agent trace where errors started in a multi-agent run and how they spread between agents.
Ready to connect★ 1k
- View details
error-scanSkillMonitoring & ops
Lets your agent scan recent Claude Code sessions for errors and rank failures by tool and model.
Ready to connect★ 1k
- View details
event-traceSkillMonitoring & ops
Trace the full event chain for one Claude Code session into an ordered timeline of every event type with tool_name and summary, highlighting gaps, out-of-order events, and failures. Reads /api/events?session_id= and /api/sessions/:id from the Agent Monitor dashboard. Use when debugging what a sessio
Ready to connect★ 1k
- View details
executive-reportSkillDatabases & data
Lets your agent generate a stakeholder report summarizing sessions, analytics, costs, alerts, and workflows.
Ready to connect★ 1k
- View details
file-headersSkillFiles & storage
Makes your agent add the project's copyright and authorship header to every source file it creates or edits.
Ready to connect★ 1k
- View details
fleet-runsSkillMonitoring & ops
Lets your agent list and summarize recent fleet runs with per-agent status details from on-disk run journals.
Ready to connect★ 1k
- View details
health-checkSkillDatabases & data
Run comprehensive health checks on the Claude Code Agent Monitor system. Validates dashboard API, database, WebSocket, hooks, and disk usage. Use to verify the monitoring setup is working correctly.
Ready to connect★ 1k
- View details
history-portabilitySkillDatabases & data
Lets your agent import coding assistant history and move monitoring datasets between machines with backups and restore.
Ready to connect★ 1k
- View details
hook-diagnosticsSkillMonitoring & ops
Lets your agent diagnose hook setup and event flow issues when events don't show up in the monitoring dashboard.
Ready to connect★ 1k
- View details
hook-failure-auditSkillMonitoring & ops
Lets your agent audit whether tool and session hooks ran correctly by checking monitor data for missing or stuck events.
Ready to connect★ 1k
- View details
hook-inventorySkillMonitoring & ops
Lets your agent list configured hooks and flag ones that post to the network or run arbitrary commands.
Ready to connect★ 1k
- View details
hook-setupSkillMonitoring & ops
Lets your agent check and install CCAM monitoring hooks for Claude Code or Codex and verify nothing else was overwritten.
Ready to connect★ 1k
- View details
i18n-paritySkillDocs & knowledge
Checks that localized content like UI keys, wiki pages, and READMEs stay consistent across all supported languages.
Ready to connect★ 1k
- View details
live-watchSkillMonitoring & ops
Lets your agent poll monitoring stats repeatedly to show live changes in sessions, agents, events, and connections.
Ready to connect★ 1k
- View details
mcp-maintainerSkillMonitoring & ops
Lets your agent update, configure, and troubleshoot the repository's server runtime and its tool policies.
Ready to connect★ 1k
- View details
mcp-operationsSkillMonitoring & ops
Lets your agent set up and fix the local MCP server, including config, connectivity, domains, and safety settings.
Ready to connect★ 1k
- View details
mcp-serverSkillMonitoring & ops
Lets your agent set up, launch, and troubleshoot the monitoring server used with Claude Code and similar tools.
Ready to connect★ 1k
- View details
memory-reviewSkillFiles & storage
Lets your agent review and inspect its saved memory files across projects and flag stale or oversized facts.
Ready to connect★ 1k
- View details
model-mixSkillMonitoring & ops
Lets your agent break down Claude Code usage by model family, showing token shares, cost shares, and wasteful expensive-model spots.
Ready to connect★ 1k
- View details
model-savingsSkillMonitoring & ops
Lets your agent estimate dollars saved by routing Claude Code work to a cheaper model family.
Ready to connect★ 1k
- View details
monthly-reviewSkillDatabases & data
Lets your agent build a monthly report of your AI usage, covering sessions, costs, tokens, and completion rates.
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.