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: Dev tools
16,976 results · page 497 of 566
- View details
omcustom:fsdSkillDev tools
Full Self Driving — autonomous release loop that processes all auto-dev-eligible GitHub issues until none remain, by repeatedly running /pipeline auto-dev then /homework.
Ready to connect
- View details
- View details
- View details
- View details
- View details
omcustom:sauron-watchSkillDev tools
Full R017 verification (5+3 rounds) before commit
Ready to connect
- View details
- View details
omcustom:webSkillDev tools
Control and inspect the built-in Web UI (packages/serve) — start, stop, status, open
Ready to connect
- View details
- View details
openharmony-downloadSkillDev tools
Interactive OpenHarmony source code download with mirror selection (GitCode/Gitee/GitHub), environment checking, branch selection, and real-time progress. Use when user requests:"下载 OpenHarmony", "download OpenHarmony", "下载源码", "获取源码", "拉取代码", "clone openharmony", or "repo init".
Ready to connect
- View details
- View details
- View details
optimizing-codeSkillDev tools
Improve code performance without changing behavior. Use when code fails latency/throughput requirements. Covers profiling, caching, and algorithmic optimization.
Ready to connect
- View details
orwells-rulesSkillDev tools
Apply George Orwell's 6 rules for clear, honest, and unpretentious writing from "Politics and the English Language" (1946). Use when the user asks for Orwell's rules, George Orwell style, cutting dead metaphors and clichés, eliminating jargon and Latinate words, converting passive to active voice, o
Ready to connect
- View details
paddingtonSkillDev tools
Write exceedingly polite, earnestly kind prose in the voice of Paddington. Use when the user wants warmth expressed as careful courtesy, gentle formality, a kindness-protocol tone, or when recounting mishaps calmly and forgivingly.
Ready to connect
- View details
pipeline-guardsSkillDev tools
Safety constraints and quality gates for pipeline and workflow execution
Ready to connect
- View details
plain-languageSkillDev tools
Write in plain language per the US Plain Writing Act of 2010 and the Plain Language Action Network. Use when the user wants clearer, simpler, shorter writing; wants to improve readability; writes public-facing or government-style content; or asks to "plain English" or "simplify" a draft.
Ready to connect
- View details
port-upstreamSkillDev tools
Analyzes upstream fork PR changes and ports selected items into the local branch. Use when checking upstream PRs, porting upstream changes, or planning selective upstream integration.
Ready to connect
- View details
post-mortemSkillDev tools
Runs an honest retrospective on a past decision, scoring it against the success criteria and concerns set beforehand.
Ready to connect
- View details
post-release-followupSkillDev tools
Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues
Ready to connect
- View details
posture-scriptSkillDev tools
Use when the user wants a complete script to check, audit, report, harden, export, or remediate Microsoft 365, Intune, Entra, or Graph posture offline.
Ready to connect
- View details
pr-auto-improveSkillDev tools
Opt-in post-PR analysis and improvement suggestions for code quality enhancement
Ready to connect
- View details
pre-generation-arch-checkSkillDev tools
Pre-generation architecture check — detect R006 separation-of-concerns and compilation metaphor violations before code generation begins
Ready to connect
- View details
prep-major-releaseSkillDev tools
Prepare the repo for a major release — review/update README.md so it stays compelling, and review the demo scenarios + screenshot scenes, proposing and applying any new/different/fewer screenshots (the maintainer captures them after).
Ready to connect
- View details
prepare-conference-manuscriptsSkillDev tools
Use when preparing, drafting, revising, polishing, rebutting, auditing, anonymizing, packaging, or checking a conference manuscript, abstract, appendix, supplement, rebuttal, author response, camera-ready paper, or conference statistical or evaluation report for AAAI, ICLR, ACL, CVPR, ICML, NeurIPS,
Ready to connect
- View details
prepare-journal-manuscriptsSkillDev tools
Use when preparing, drafting, revising, polishing, auditing, or packaging a journal manuscript, abstract, statistical or evaluation report, cover letter, editor-facing submission pack, data availability statement, peer-review response, revise and resubmit package, clean manuscript, marked manuscript
Ready to connect
- View details
product-strategySkillDev tools
YC-style product strategy assessment with forced questions and CEO scope modes — adapted from gstack /office-hours pattern
Ready to connect
- View details
professor-triageSkillDev tools
Analyze GitHub issues against current codebase and perform automated triage with priority assessment
Ready to connect
- View details
provocationSkillDev tools
Extract movement from a statement known to be false. Use when nobody can see past an obvious answer.
Ready to connect
- View details
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.
54,082 of the 54,514 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.