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 26 of 301
- View details
hunt-deserializationSkillAI & models
Guides your agent to find insecure deserialization flaws like Java gadget chains and Python pickle bugs in a target.
Ready to connect★ 4k
- View details
hunt-dispatchSkillAI & models
Loads the right attack skill set for a security hunt after a mode like red team or web app testing is chosen.
Ready to connect★ 4k
- View details
hunt-http-smugglingSkillAI & models
Lets your agent test websites for HTTP request smuggling flaws where proxies and servers disagree on request boundaries.
Ready to connect★ 4k
- View details
hunt-ntlm-infoSkillAI & models
Lets your agent probe internet-facing Windows servers for NTLM responses that leak internal network details.
Ready to connect★ 4k
- View details
hunt-samlSkillAI & models
Lets your agent analyze SAML and SSO logins for attack patterns like signature wrapping and comment injection.
Ready to connect★ 4k
- View details
hunt-sstiSkillAI & models
Lets your agent test web apps for server-side template injection flaws across many template engines.
Ready to connect★ 4k
- View details
osint-methodologySkillAI & models
Guides your agent through a 5-stage open-source intelligence process for mapping and assessing an organization's external attack surface.
Ready to connect★ 4k
- View details
recon-scope-triageSkillAI & models
Lets your agent sort recon results so only assets truly owned by your test target get tested.
Ready to connect★ 4k
- View details
redteam-mindsetSkillAI & models
Teaches your agent red-team testing discipline so it questions conservative assumptions and avoids missing vulnerabilities.
Ready to connect★ 4k
- View details
redteam-report-templateSkillAI & models
Gives your agent a template for writing client-facing red-team reports with findings structured as observations, impact, and recommendations.
Ready to connect★ 4k
- View details
report-writingSkillAI & models
Helps your agent write clear, well-scored bug bounty reports with templates, CVSS scoring, and a pre-submit checklist.
Ready to connect★ 4k
- View details
triage-validationSkillAI & models
Walks your agent through a 7-question validation gate and checklist before it writes a security finding report.
Ready to connect★ 4k
- View details
qcSkillAI & models
Runs five AI reviewers in parallel to check your code changes before they pass.
Ready to connect★ 4k
- View details
upgrade-modelSkillAI & models
Lets your agent switch the AI chat model between fast and good across backend and frontend.
Ready to connect★ 4k
- View details
address-issueSkillAI & models
Guides your agent through triaging, reproducing, and fixing a GitHub issue step by step.
Ready to connect★ 4k
- View details
disk-reductionSkillAI & models
Lets your agent free up disk space on the Mac by clearing Rust build residue and other space hogs.
Ready to connect★ 4k
- View details
orchestratorSkillAI & models
Lets your agent run a big multi-part task by delegating pieces to sub-agents and checking their work.
Ready to connect★ 4k
- View details
agentic-workflowsSkillAI & models
Lets your agent create, debug, and upgrade agentic workflows by routing requests to the right prompts.
Ready to connect★ 4k
- View details
archestra-dev-backendSkillAI & models
Use when adding or changing Archestra backend routes, models, services, API request/response schemas, endpoint permissions, or OpenAPI/codegen for the generated API client.
Ready to connect★ 4k
- View details
archestra-dev-bench-analysisSkillAI & models
Map-reduce a finished archestra-bench run into a Tier-1/Tier-2 improvement report using Claude subagents (same analysis as the Rust analyzer, no API key).
Ready to connect★ 4k
- View details
archestra-dev-interactions-migrationsSkillAI & models
Use BEFORE writing or running any Drizzle migration that touches the `interactions` table (or any other very large, write-hot table). The interactions table is the platform's biggest, append-heavy table — every LLM proxy call writes a row — so a careless migration can take a write-blocking lock and
Ready to connect★ 4k
- View details
archestra-dev-llm-providersSkillAI & models
Use when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants.
Ready to connect★ 4k
- View details
offensive-active-directorySkillAI & models
Lets your agent run Active Directory attack techniques like reconnaissance and credential abuse during red team engagements.
Ready to connect★ 4k
- View details
offensive-bluetooth-bleSkillAI & models
Guides your agent through Bluetooth Low Energy attack techniques like GATT enumeration, sniffing, and relay-based man-in-the-middle testing.
Ready to connect★ 4k
- View details
offensive-cicd-pipelineSkillAI & models
Teaches your agent how CI/CD systems like GitHub Actions and Jenkins can be attacked, for security testing.
Ready to connect★ 4k
- View details
offensive-dependency-confusionSkillAI & models
Teaches your agent how dependency confusion and namespace attacks work across package ecosystems.
Ready to connect★ 4k
- View details
offensive-deserializationSkillAI & models
Lets your agent learn how to exploit insecure deserialization flaws in Java, PHP, .NET, Python, Node.js, and Ruby apps.
Ready to connect★ 4k
- View details
offensive-fuzzingSkillAI & models
Teaches your agent how to run fuzzing campaigns to find software bugs, from picking targets to triaging crashes.
Ready to connect★ 4k
- View details
offensive-lateral-movementSkillAI & models
Teaches your agent credential-based and remote execution attack techniques for authorized red team engagements.
Ready to connect★ 4k
- View details
offensive-lorawan-sub-ghzSkillAI & models
Teaches your agent how LoRaWAN and sub-GHz radio attacks work, from key reuse to replaying garage door remotes.
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.