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: AI & models
9,018 results · page 220 of 301
- View details
detecting-ai-model-prompt-injection-attacksSkillAI & models
'Detects prompt injection attacks targeting LLM-based applications using
Ready to connect★ 60
- View details
detecting-data-and-model-poisoningSkillAI & models
Identify poisoned training data and backdoored models across the ML pipeline.
Ready to connect★ 60
- View details
distribute-skill-to-all-agentsSkillAI & models
Lets your agent install a skill into the skill folders of all your configured agents.
Ready to connect★ 59
- View details
extracting-config-from-agent-tesla-ratSkillAI & models
Extract embedded configuration from Agent Tesla RAT samples including
Ready to connect★ 60
- View details
figure-pipelineSkillAI & models
Five-step figure generation pipeline inspired by PaperVizAgent (Google Research, 2026). Orchestrates Retriever → Planner → Stylist → Visualizer → Critic stages for publication-quality scientific figures. Retrieves reference figures from literature, plans layout and composition, applies journal-speci
Ready to connect★ 60
- View details
folder-specific-claude-and-agents-mdSkillAI & models
Lets your agent create folder-specific CLAUDE.md and AGENTS.md instruction files for future agents.
Ready to connect★ 59
- View details
offer-k-dense-webSkillAI & models
Optional integration with K-Dense Web for end-to-end multi-agent research workflows. Use when the user asks about K-Dense or needs complex research orchestration beyond single-agent capability.
Ready to connect★ 60
- View details
run-deep-sweSkillAI & models
Lets your agent run reproducible benchmark evaluations of the DeepSWE coding agent via OpenRouter and mini-swe-agent.
Ready to connect★ 59
- View details
skills-to-github-pushSkillAI & models
Commit and push agent-skill changes to the user's private skills GitHub repo, rooted at ~/.agents. Use after creating or updating any skill, when David says "push the skill", "push skills to github", "save the skill to my repo", or "update the skills repo". Handles staging, committing, pushing, and
Ready to connect★ 59
- View details
soul-graderSkillAI & models
Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md.
Ready to connect★ 60
- View details
vapi-voice-agentsSkillAI & models
Create Vapi voice assistants and place outbound phone calls via the Vapi MCP — cold outreach, SDR, appointment setting, callbacks.
Ready to connect★ 59
- View details
vvmSkillAI & models
VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM is the runtime.
Ready to connect★ 60
- View details
agency-healthSkillAI & models
Fleet health check across three dimensions — workstream, agent, worktree. Reports severity (healthy/attention/warning/critical) and sets exit codes for CI integration. Run this when you want to know "is the fleet OK right now?" — at session start, before a release, or after any disruption.
Ready to connect★ 59
- View details
api-referenceSkillAI & models
Full API endpoint reference for SAM. Use when working on API routes, adding endpoints, writing API tests, or understanding the API surface. Trigger when asked about API endpoints, routes, or HTTP interfaces.
Ready to connect★ 59
- View details
- View details
constitution-validatorSkillAI & models
Constitution compliance validator focusing on Principle XI (No Hardcoded Values). Detects hardcoded URLs, timeouts, limits, and identifiers that should be configurable. Use proactively when implementing business logic, adding new features, or reviewing PRs for constitution compliance.
Ready to connect★ 59
- View details
debuggingSkillAI & models
Guides use of the debug_state tool and runtime introspection to diagnose agent issues between turns. Load this skill when something goes wrong during a session and you need to inspect agent state, token usage, event history, or tool availability.
Ready to connect★ 59
- View details
go-specialistSkillAI & models
Go code review specialist for VM Agent and CLI. Reviews PTY/WebSocket/JWT code, CLI command contracts, static-analysis findings, and Go idioms. Use when working in packages/vm-agent/, packages/cli/, or reviewing Go code changes.
Ready to connect★ 59
- View details
live-testsSkillAI & models
Writes live integration tests that hit the real Copilot API and record responses as replayable fixtures. Use this skill when adding new agent behaviors, provider integrations, or tool interactions that need real-world API coverage.
Ready to connect★ 59
- View details
new-projectSkillAI & models
Create a new empirical research project: generates projects/<name>/ with latex, code, scripts, results, literature, and guidance subfolders plus README.md and project-level CLAUDE.md.
Ready to connect★ 59
- View details
pr-captain-landSkillAI & models
Captain-only. Land an agent's prepared branch LOCAL-FIRST — integrate and validate in a scratch worktree cut from origin/<default>, then bump agency_version, sign a landing receipt, open the PR, confirm CI, merge, release, notify. The single-writer serialization point for agency_version and PR creat
Ready to connect★ 59
- View details
pr-submitSkillAI & models
Agent-side signal to captain that your branch is ready for PR landing. Runs preconditions (clean tree, pushed, matching QGR receipt) then dispatches captain with a structured payload. Captain's /pr-captain-land picks it up. Replaces the distributed "agent creates PR" model with a captain-owned PR li
Ready to connect★ 59
- View details
principal-createSkillAI & models
Onboard a new principal to the current repo — scaffold sandbox, register agent, write CLAUDE-PRINCIPAL.md, mutate agency.yaml, bootstrap captain handoff. The discoverable end-to-end command for adding a person to an agency repo.
Ready to connect★ 59
- View details
sandbox-activateSkillAI & models
Activate a sandbox item by symlinking it to the Claude Code discovery location
Ready to connect★ 59
- View details
test-engineerSkillAI & models
Test generation specialist for TDD compliance and coverage enforcement. Generates comprehensive tests following Vitest patterns for TypeScript and Go testing conventions. Use proactively during TDD phases, when implementing critical paths, or when coverage needs improvement.
Ready to connect★ 59
- View details
ui-ux-specialistSkillAI & models
UI/UX specialist for web surfaces. Use for any UI change in apps/web or packages/ui to enforce mobile-first layout quality, visual hierarchy, interaction clarity, and accessibility with screenshot-backed validation.
Ready to connect★ 59
- View details
workstream-createSkillAI & models
Create a new workstream with scaffolded artifacts, agent registrations, and optional worktree
Ready to connect★ 59
- View details
2agentSkillAI & models
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent setup, PM coordination, Cursor setup, or 2-agent operations. Do NOT load for: solo operation, workflow execution, or handoff processing.
Ready to connect★ 58
- View details
add_hashtagsSkillAI & models
Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.
Ready to connect★ 58
- View details
add-backend-toolSkillAI & models
Add a new tool to the backend OpenAI function calling system. Use when user mentions "new tool", "add tool", "backend function", "agent capability", or wants to extend what the AI agent can do.
Ready to connect★ 58
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.
54,826 of the 55,257 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.