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
9,019 results · page 27 of 301
- View details
offensive-mobileSkillAI & models
Guides your agent through mobile app penetration testing on Android and iOS, from static analysis to runtime bypasses.
Ready to connect★ 4k
- View details
offensive-network-attacksSkillAI & models
Lets your agent run network attack techniques like ARP spoofing and DNS poisoning for penetration testing.
Ready to connect★ 4k
- View details
offensive-reportingSkillAI & models
Guides your agent through writing penetration test and red team reports with structured findings and CVSS scores.
Ready to connect★ 4k
- View details
offensive-sstiSkillAI & models
Teaches your agent how to find and exploit template injection flaws in web apps across many template engines.
Ready to connect★ 4k
- View details
offensive-supply-chainSkillAI & models
Teaches your agent how software supply chain attacks work, from reconnaissance through exploitation.
Ready to connect★ 4k
- View details
offensive-wpa-enterpriseSkillAI & models
Teaches your agent how to identify and attack WPA-Enterprise Wi-Fi networks, including evil-twin setups to capture login credentials.
Ready to connect★ 4k
- View details
offensive-zigbee-thread-matterSkillAI & models
Gives your agent techniques to sniff and attack Zigbee, Thread, and Matter smart-home networks using common USB dongles.
Ready to connect★ 4k
- View details
software-lifecycleSkillAI & models
Teaches your agent how this project organizes work through proposals, decisions, specs, and postmortems.
Ready to connect★ 4k
- View details
generate2dspriteSkillAI & models
Lets your agent generate 2D game sprites and animation sheets, like pixel-art characters, spells, and props, from a text request.
Ready to connect★ 4k
- View details
export-microfeed-themeSkillAI & models
Initialize or export a microfeed theme from a saved instance into an independent local repository, then install, validate, test, and preview it safely. Use when a coding agent is asked to initialize, export, copy, fork, inspect, or begin developing the active or a specific installed theme from a mic
Ready to connect★ 4k
- View details
council-verdictsSkillAI & models
Starter: interpret a council run's verdict artifacts — quorum, dissent, cross-lab validity, and what to do next
Ready to connect★ 4k
- View details
debate-kickoffSkillAI & models
Starter: frame a decision as a multi-model debate — picks sides, seats providers, and launches /octo:debate with a well-formed motion
Ready to connect★ 4k
- View details
flow-deliverSkillAI & models
Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)
Ready to connect★ 4k
- View details
flow-discoverSkillAI & models
Multi-AI research using available external providers (Double Diamond Discover phase)
Ready to connect★ 4k
- View details
flow-parallelSkillAI & models
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
Ready to connect★ 4k
- View details
flow-specSkillAI & models
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
Ready to connect★ 4k
- View details
octopus-architectureSkillAI & models
Review system architecture, simplify boundaries, or compare interface designs from repository evidence
Ready to connect★ 4k
- View details
octopus-researchSkillAI & models
Thorough research across multiple sources — use for complex topics needing broad synthesis
Ready to connect★ 4k
- View details
provider-healthSkillAI & models
Starter: one-screen provider health summary — availability, auth method, version drift, and cost posture for every seatable provider
Ready to connect★ 4k
- View details
skill-agent-topologySkillAI & models
Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels slow or agents agree without adding signal
Ready to connect★ 4k
- View details
skill-auditSkillAI & models
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Ready to connect★ 4k
- View details
skill-authoringSkillAI & models
Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in this plugin
Ready to connect★ 4k
- View details
skill-content-pipelineSkillAI & models
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
Ready to connect★ 4k
- View details
skill-copilot-providerSkillAI & models
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
Ready to connect★ 4k
- View details
skill-cost-projectionsSkillAI & models
Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns
Ready to connect★ 4k
- View details
skill-councilSkillAI & models
Run a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff.
Ready to connect★ 4k
- View details
skill-coverage-auditSkillAI & models
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
Ready to connect★ 4k
- View details
skill-debateSkillAI & models
Structured multi-provider AI debates between Claude and available advisors — use for critical decisions
Ready to connect★ 4k
- View details
skill-debugSkillAI & models
Debug a reproducible symptom with a bounded feedback loop and original-scenario verification
Ready to connect★ 4k
- View details
skill-decision-supportSkillAI & models
Present options with trade-offs for informed decision-making — use when choosing between approaches
Ready to connect★ 4k
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.
54,764 of the 55,196 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.