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

16,833 results · page 278 of 562

  • paper.use_styleSkillDev tools

    Write or edit an academic CS paper following formal, evidence-driven, and structured writing style

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • pixi-vn-getting-startedSkillDev tools

    Use when setting up a new or existing project on @drincs/pixi-vn, wiring the main.ts entry point, or calling the top-level Game API (Game.init, Game.start, Game.onEnd, Game.addOnError, Game.onNavigate, Game.clear) — this is the entry point every Pixi'VN project needs before touching canvas, narratio

    Ready to connect★ 145

    github.com/drincs-productions/pixi-vn141 stars

    View details
  • pixi-vn-migrationSkillDev tools

    Use when upgrading an existing @drincs/pixi-vn project to a newer version, or when a runtime/type error matches a known breaking change. Covers every breaking change between versions with before/after code.

    Ready to connect★ 145

    github.com/drincs-productions/pixi-vn141 stars

    View details
  • pixi-vn-minigamesSkillDev tools

    Use when adding a minigame (snake, quiz, puzzle, timing/reaction game, ...) to a Pixi'VN visual novel — the `useMinigame` lifecycle hook pattern, using PixiJS directly on its own layer instead of `gameLayer`, hotkeys for controls, linking the minigame to a route, and why saving/restoring minigame st

    Ready to connect★ 145

    github.com/drincs-productions/pixi-vn141 stars

    View details
  • pixi-vn-narrationSkillDev tools

    Use when writing or editing Pixi'VN story content — defining labels (scenes) with newLabel, writing dialogue steps, adding player choices with newChoiceOption/newCloseChoiceOption, conditional/branching labels, or wiring up narration.call/jump/continue and Game.start to progress the story.

    Ready to connect★ 145

    github.com/drincs-productions/pixi-vn141 stars

    View details
  • pixi-vn-uiSkillDev tools

    Use when building game UI (menus, HUD, dialogue box, settings/save screens) on top of Pixi'VN with an external JS framework (React, Vue) or with plain PixiJS components — mounting HTML or PixiJS UI layers over the canvas, navigating between UI screens/routes, theming a shadcn/ui-based template, and

    Ready to connect★ 145

    github.com/drincs-productions/pixi-vn141 stars

    View details
  • post-merge-cleanupSkillDev tools

    Finish an already-merged branch. Proves the branch is contained in the fetched default, classifies leftover artifacts as unique / redundant / superseded, returns to a clean --ff-only default checkout, and deletes the merged local branch — every discard confirmed per item. Routed to by /ca:cleanup.

    Ready to connect★ 145

    github.com/arbiterforge/codearbiter145 stars

    View details
  • pytest.triage_github_unit_testsSkillDev tools

    Analyze and fix failure of tests in GitHub CI

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • pytest.triage_local_unit_testsSkillDev tools

    Analyze and fix failure of local tests

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • raytsystem-lintSkillDev tools

    Run deterministic integrity, provenance, projection, link, alias, operation, and secret checks over raytsystem. Use for LINT, health checks, pre-commit verification, stale projection diagnosis, broken evidence, or semantic review; never auto-fix canonical knowledge.

    Ready to connect★ 145

    github.com/romarayt/raytsystem-public-os140 stars

    View details
  • raytsystem-researchSkillDev tools

    Perform bounded source research for raytsystem and return provenance-rich evidence proposals without canonical writes. Use for RESEARCH, public fact gathering, source comparison, primary-source verification, or preparing evidence for a later INGEST; keep private corpus local unless scoped egress is

    Ready to connect★ 145

    github.com/romarayt/raytsystem-public-os140 stars

    View details
  • raytsystem-run-reviewSkillDev tools

    Independently review an raytsystem run, diff, contract, test result, or milestone checkpoint and return structured findings. Use for REVIEW, architecture/contracts/data-integrity/test critique, gate verification, or pre-promotion review; remain read-only and separate from the writer context.

    Ready to connect★ 145

    github.com/romarayt/raytsystem-public-os140 stars

    View details
  • raytsystem-saveSkillDev tools

    Stage a cited synthesis as a typed raytsystem DRAFT bundle and escaped preview. Use for SAVE, preserving a verified query answer, preparing a knowledge proposal, or creating a reviewable draft; never treat SAVE as canonical promotion or publication.

    Ready to connect★ 145

    github.com/romarayt/raytsystem-public-os140 stars

    View details
  • research_idea.brainstormSkillDev tools

    Brainstorm 5 new research ideas along the lines of existing ones

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • research_idea.check_redundantSkillDev tools

    Find and merge redundant or highly overlapping research ideas

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • research_idea.write_draft_paperSkillDev tools

    Write a conference paper draft from a research idea

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • room-playbookSkillDev tools

    Lightweight default rules for coordinating a Room conversation without confusing chat wakeups with durable WorkGraph responsibility.

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • run-reviewSkillDev tools

    Independently review an raytsystem run, diff, contract, test result, or milestone checkpoint and return structured findings. Use for REVIEW, architecture/contracts/data-integrity/test critique, gate verification, or pre-promotion review; remain read-only and separate from the writer context.

    Ready to connect★ 145

    github.com/romarayt/raytsystem-public-os140 stars

    View details
  • skill-authorSkillDev tools

    The authoring gate for new skills. Routed to when the user invokes /new-skill "<gap>". Five gated phases — gap evidence, scope, authoring, self-review against the v2 house style, routing integration. A new skill is not written until an existing one is proven not to cover the gap, and not shipped unt

    Ready to connect★ 145

    github.com/arbiterforge/codearbiter145 stars

    View details
  • skill.addSkillDev tools

    Add a rule to the set of rules

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • skill.add_architectureSkillDev tools

    Add a rule to the set of architecture rules

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • skill.consolidate_skillsSkillDev tools

    Consolidate and rename skills to be more appropriate

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • specs.writeSkillDev tools

    Write specification to implement a software component given user request

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • system.analyze_disk_space_useSkillDev tools

    Analyze disk usage to find the largest space consumers and reclaim options

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • testing.add_end_to_end_testsSkillDev tools

    Add end-to-end unit tests for CLI commands

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • testing.fix_input_output_varsSkillDev tools

    Fix the input / output variables of a test

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • testing.fix_mock_testsSkillDev tools

    Remove mocking approach from unit tests

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • testing.fix_unit_testsSkillDev tools

    Apply the conventions usually not followed in the unit test

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • testing.reorderSkillDev tools

    Reorganize Python test classes and functions to match the order of the code they test

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • testing.update_test_outcomesSkillDev tools

    Update the outcome of unit tests

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    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.

53,585 of the 54,017 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.

See how to connect your AI