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
17,237 results · page 190 of 575
- View details
genieSkillDev tools
Lets your agent route Genie questions, bugs, and planned work, resuming related wishes and handling simple requests directly.
Ready to connect★ 339
- View details
quickSkillDev tools
Lets your agent make small, low-risk code changes and get them deployed to dev within an hour.
Ready to connect★ 339
- View details
skill-auditSkillDev tools
Lets your agent audit your installed skills for overlap and staleness and recommend keep, merge, or retire actions.
Ready to connect★ 339
- View details
skill-creator-ultraSkillDev tools
Lets your agent turn an idea or workflow into a new reusable skill by asking questions and testing the result.
Ready to connect★ 339
- View details
wishSkillDev tools
Lets your agent turn a settled idea into a reviewed, executable plan with scope, criteria, and ordered steps.
Ready to connect★ 339
- View details
workSkillDev tools
Lets your agent carry out an approved task plan step by step, with workers, review, fixes, and completion checks.
Ready to connect★ 339
- View details
workflySkillDev tools
Lets your agent discover a procedure and turn it into a saved, verified workflow script.
Ready to connect★ 339
- View details
assumption-testSkillDev tools
Helps your agent test a risky technical assumption with a small experiment before building on it.
Ready to connect★ 337
- View details
change-quizSkillDev tools
Lets your agent summarize what changed in a coding session and quiz you before merging.
Ready to connect★ 337
- View details
content-parserSkillDev tools
Lets your agent extract and parse the content of any web page from a URL.
Ready to connect★ 337
- View details
creatorSkillDev tools
Lets your agent generate platform-ready content packages like articles and posts from a creator workflow.
Ready to connect★ 337
- View details
establishing-feasibility-firstSkillDev tools
Guides your agent to check whether an unproven compute-heavy plan is even feasible before committing to it.
Ready to connect★ 336
- View details
implementation-planSkillDev tools
Lets your agent write implementation plans that put likely-to-change decisions first and routine work last.
Ready to connect★ 337
- View details
preregistering-analysisSkillDev tools
Lets your agent lock in predictions and decision rules before running a confirmatory analysis or looking at outcome data.
Ready to connect★ 336
- View details
receiving-critical-reviewSkillDev tools
Guides your agent to verify and question critical feedback on analyses or manuscripts before making changes.
Ready to connect★ 336
- View details
reference-huntSkillDev tools
Lets your agent study an existing codebase or site you point to and copy its behavior into new code.
Ready to connect★ 337
- View details
reporting-and-archiving-findingsSkillDev tools
Helps your agent decide how to report completed analyses and archive the work so it can be reproduced.
Ready to connect★ 336
- View details
requesting-red-team-reviewSkillDev tools
Has a skeptical reviewer attack your agent's conclusions before it reports them as findings.
Ready to connect★ 336
- View details
setting-up-reproducible-analysisSkillDev tools
Sets up an isolated, reproducible analysis workspace with pinned environment, fixed seeds, and locked raw data.
Ready to connect★ 336
- View details
surveying-prior-workSkillDev tools
Lets your agent search past research to check methods, novelty, and effect sizes before starting an analysis.
Ready to connect★ 336
- View details
test-blindspotsSkillDev tools
Finds important behaviors your passing tests don't actually cover using focused exploratory checks.
Ready to connect★ 337
- View details
using-science-superpowersSkillDev tools
Sets up your agent to check for and use available skills before responding to any request.
Ready to connect★ 336
- View details
verifying-results-before-claimingSkillDev tools
Makes your agent run an analysis fresh and read the actual output before claiming any result.
Ready to connect★ 336
- View details
Echo Skill SampleSkillDev tools
Lets your agent echo back any input it receives as JSON for testing and debugging.
Ready to connect★ 335
- View details
releasing-softwareSkillDev tools
Guides your agent to safely tag and ship a release by verifying build artifacts before publishing a version.
Ready to connect★ 333
- View details
roborev-respondSkillDev tools
Lets your agent respond using the roborev-respond skill when you explicitly invoke it.
Ready to connect★ 333
- View details
scenario-to-tiktokSkillDev tools
Lets your agent turn a finished scenario planning exercise into a TikTok script.
Ready to connect★ 333
- View details
session-reflection-analysisSkillDev tools
Lets your agent review a finished session and share thoughts on how it went.
Ready to connect★ 333
- View details
strategy-diagnosisSkillDev tools
Guides your agent through structured questioning to diagnose business problems and strategic decisions.
Ready to connect★ 333
- View details
genshijinSkillDev tools
Lets your agent reply in ultra-short caveman-style speech to cut token usage by about 75% while staying technically accurate.
Ready to connect★ 332
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.
55,004 of the 55,435 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.