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
58,207 results · page 1250 of 1,941
- View details
alcatchupspecSkillProductivity
Lets your agent load AlignFirst task history and run the specification protocol.
Ready to connect★ 86
- View details
aldescriptionSkillDev tools
Lets your agent run the AlignFirst description protocol to produce structured descriptions.
Ready to connect★ 86
- View details
alignfirstSkillDev tools
Lets your agent follow structured problem-solving protocols for writing specs, plans, and catchup notes.
Ready to connect★ 86
- View details
alignfirst-openclaw-playbookSkillCommunication
Lets your agent route chat messages to the right channel or working thread and follow shared rules.
Ready to connect★ 86
- View details
almergeSkillDev tools
Lets your agent run the AlignFirst merge protocol for combining code changes.
Ready to connect★ 86
- View details
alplanSkillDev tools
Lets your agent run the AlignFirst planning protocol to plan work before building it.
Ready to connect★ 86
- View details
- View details
alspecSkillDev tools
Lets your agent write and follow a structured specification before building software.
Ready to connect★ 86
- View details
application-funnelSkillDev tools
Lets your agent screen leads through an application form before booking sales calls for high-ticket offers.
Ready to connect★ 84
- View details
ascii-graphicSkillDev tools
Lets your agent generate dark ASCII banner graphics for launch assets.
Ready to connect★ 86
- View details
audit-snapshotSkillAI & models
Lets your agent package a change's prompt history, code diff, and compliance artifacts into an audit archive.
Ready to connect★ 86
- View details
audit-snapshot-microSkillMonitoring & ops
Lets your agent create a lightweight audit snapshot recording a change's diff hash and test result.
Ready to connect★ 86
- View details
auto-paperSkillDev tools
Lets your agent use the auto-paper research workflow through its documented Harness aliases.
Ready to connect★ 86
- View details
auto-paper-argumentSkillDev tools
Lets your agent use the auto-paper-argument instructions to help build and check arguments in research papers.
Ready to connect★ 86
- View details
auto-paper-citationSkillDev tools
Lets your agent automatically add citations to papers using the auto-paper-citation harness instructions.
Ready to connect★ 86
- View details
auto-paper-dataSkillDev tools
Lets your agent follow the auto-paper-data instructions by routing through the visible Harness aliases.
Ready to connect★ 86
- View details
auto-paper-figureSkillDev tools
Lets your agent generate figures for research papers automatically.
Ready to connect★ 86
- View details
auto-paper-hardenSkillDev tools
Lets your agent apply paper-hardening instructions from a shared research harness source.
Ready to connect★ 86
- View details
auto-paper-intakeSkillDev tools
Lets your agent follow the auto-paper-intake instructions through the harness's visible aliases.
Ready to connect★ 86
- View details
auto-paper-layoutSkillDev tools
Lets your agent apply the auto-paper-layout instructions to format research papers automatically.
Ready to connect★ 86
- View details
auto-paper-patchSkillDev tools
Lets your agent apply patches to research papers automatically through a harness workflow.
Ready to connect★ 86
- View details
auto-paper-researchSkillDev tools
Lets your agent run an automated research workflow that gathers and organizes information into papers.
Ready to connect★ 86
- View details
auto-paper-responseSkillDev tools
Lets your agent follow the auto-paper-response instructions for handling research paper responses.
Ready to connect★ 86
- View details
baseline-reproSkillDev tools
Lets your agent run baseline reproduction tasks through the Harness research harness.
Ready to connect★ 86
- View details
beanSkillProductivity
Lets your agent work a task in repeated evidence-gathering loops, revising its conclusions until findings converge.
Ready to connect★ 86
- View details
blind-spotSkillDev tools
Lets your agent analyse a sprint plan and point out what it has overlooked.
Ready to connect★ 86
- View details
calibrateSkillDev tools
Lets your agent score past predictions against actual outcomes to see how accurate they were.
Ready to connect★ 86
- View details
calibration-reportSkillMonitoring & ops
Lets your agent summarize how accurate its time estimates were by reviewing the time log.
Ready to connect★ 86
- View details
campaignSkillDev tools
Lets your agent run long, self-directed research tasks that persist across sessions under an agreed plan.
Ready to connect★ 86
- View details
changeSkillDev tools
Lets your agent write changelogs, deprecation notices, and migration guides — a change claude agent for release docs.
Ready to connect★ 86
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
58,207 of the 58,207 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 workspace 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.