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
54,680 results · page 642 of 1,823
- View details
shellcode-devSkillAI & models
Lets your agent write position-independent shellcode and loaders, including PEB walking, API hashing, and encoders.
Ready to connect★ 367
- View details
threat-huntingSkillSecurity
Lets your agent hunt security threats by building detections, analyzing endpoint and network activity, and validating attacks.
Ready to connect★ 367
- View details
threat-model-disciplineSkillSecurity
Guides your agent to build and update a threat model of a system before attempting security testing.
Ready to connect★ 367
- View details
using-offensive-claudeSkillSecurity
Lets your agent find and run the right offensive-security skill for tasks like recon, exploitation, and reporting.
Ready to connect★ 367
- View details
video-cutSkillMedia
Lets your agent cut a long video into short clips by following a clip plan and splicing the selected segments into a new video file.
Ready to connect★ 364
- View details
video-recapSkillMedia
Lets your agent turn a video you provide into a narrated recap video with Chinese voiceover, subtitles, and editing.
Ready to connect★ 364
- View details
video-understandingSkillFiles & storage
Lets your agent analyze a video file into scene breakdowns, transcripts, silence maps, and a fused timeline for summarizing or writing.
Ready to connect★ 364
- View details
video-voiceoverSkillMedia
Lets your agent turn a timestamped Chinese narration script into speech audio, segment by segment.
Ready to connect★ 364
- View details
vulnerability-analysisSkillDocs & knowledge
Lets your agent audit source code for security flaws by running scanners like CodeQL and Semgrep to trace untrusted data.
Ready to connect★ 367
- View details
windows-boundariesSkillSecurity
Lets your agent research Windows security boundary bypasses, sandbox escapes, and kernel exploits for defensive testing.
Ready to connect★ 367
- View details
windows-mitigations-bypassSkillAI & models
Guides an agent through bypassing Windows security mitigations like ASLR, DEP, CFG, and AMSI during exploit development.
Ready to connect★ 367
- View details
writing-offensive-skillsSkillAI & models
Guides your agent to write new skills for the offensive-claude repo following its SKILL.md conventions.
Ready to connect★ 367
- View details
clear-allSkillAI & models
Lets your agent learn from past user interactions to improve its future responses.
Ready to connect★ 370
- View details
connect-data-sourceSkillAI & models
Lets your agent connect a Braintrust project to Reflexio by guiding traffic selection, field mapping, and setup validation.
Ready to connect★ 370
- View details
integrate-reflexioSkillAI & models
Lets your agent wire Reflexio into an app by fetching learned context and publishing completed interactions.
Ready to connect★ 370
- View details
kc-entrypoint-changeSkillMedia
Lets your agent edit a workspace pod's boot scripts and startup config in kube-coder safely.
Ready to connect★ 370
- View details
kc-issueSkillProductivity
Lets your agent launch an isolated background task that works on a kube-coder issue in its own git worktree.
Ready to connect★ 370
- View details
kc-preflightSkillDev tools
Lets your agent run a project's full test and build suite locally before pushing, so CI passes on the first try.
Ready to connect★ 370
- View details
kc-scope-prSkillDev tools
Lets your agent analyze a code change's diff to see what it touches, which tests cover it, and what's untested before opening a PR.
Ready to connect★ 370
- View details
kc-screenshotSkillWeb & browsing
Lets your agent take desktop and mobile screenshots of a web dashboard in dark and light modes to check UI changes.
Ready to connect★ 370
- View details
kc-ship-prSkillDev tools
Lets your agent commit local changes and open or update a pull request on GitHub from inside a workspace.
Ready to connect★ 370
- View details
reflexioSkillAI & models
Lets your agent learn from real user interactions to improve its own responses over time.
Ready to connect★ 370
- View details
reflexio-consolidateSkillFiles & storage
Lets your agent clean up .reflexio files by removing expired entries and merging duplicates.
Ready to connect★ 370
- View details
reflexio-embeddedSkillAI & models
Lets your agent remember user preferences and corrections across sessions by saving them to a local file.
Ready to connect★ 370
- View details
remote-taskSkillProductivity
Lets your agent start tasks on a remote workspace, check their status, and attach to running sessions.
Ready to connect★ 370
- View details
restartSkillAI & models
Lets your agent review past user interactions and learn from them to improve future behavior.
Ready to connect★ 370
- View details
earnings-calendarSkillCommerce & finance
Lets your agent look up upcoming company earnings dates, timing, and EPS estimates.
Ready to connect★ 366
- View details
fundamentalsSkillMonitoring & ops
Lets your agent look up a company's financials, earnings, and key metrics like revenue and profit.
Ready to connect★ 366
- View details
greeksSkillCommerce & finance
Lets your agent calculate option Greeks like delta, gamma, theta, vega, and implied volatility for specific options.
Ready to connect★ 366
- View details
ib-accountSkillCommerce & finance
Lets your agent check your Interactive Brokers account balance, buying power, and account value.
Ready to connect★ 366
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.
54,249 of the 54,680 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.