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: AI & models

9,017 results · page 280 of 301

  • grim:council:guild:codingSkillAI & models

    Coding Guild: Grimoire-led engineering group chat with Abathur and Cleo for codebase, promptbase, maintenance, and systems evolution.

    Ready to connect

    github.com/mindgoblinstudios/grim-tome25 stars

    View details
  • grim:council:guild:ops:abathur-evolverSkillAI & models

    Abathur (Evolver): Recursive self-improvement for agents and their tools, skills, and workflows. Tests changes to how the system observes, reasons, executes, evaluates, and learns.

    Ready to connect

    github.com/mindgoblinstudios/grim-tome25 stars

    View details
  • grim:council:guild:ops:cleo-code-maidSkillAI & models

    Cleo (Code Maid): Cleanup, deduplication, organization, and polish for code, docs, and prompts. Removes clutter and dead material while preserving intended behavior.

    Ready to connect

    github.com/mindgoblinstudios/grim-tome25 stars

    View details
  • grim:dev:mentor-reviewSkillAI & models

    Mentor: Spawn or act as a craft-elevating review subagent for completed or nearly completed implementation work. Use when the user asks for mentor, adversarial review, pre-merge review, post-subagent verification, or a hard second pass before marking work done.

    Ready to connect

    github.com/mindgoblinstudios/grim-tome25 stars

    View details
  • grim:dev:three-minions-in-a-trench-coatSkillAI & models

    Three Minions in a Trench Coat: manual-only multi-model coding council that runs three top Minion routes in parallel, compares their answers, and synthesizes the best final answer.

    Ready to connect

    github.com/mindgoblinstudios/grim-tome25 stars

    View details
  • grim:terface:installSkillAI & models

    Guided install of Grimoire's Tome: explain the install model, walk the user through cloning, copying, or symlinking the parts they want, and hand off to council onboarding. Manual invocation only.

    Ready to connect

    github.com/mindgoblinstudios/grim-tome25 stars

    View details
  • handoff-noticeSkillAI & models

    Use when: publishing a durable repository-local handoff notice with a short verifiable locator, or resolving that locator in a later person, agent, or session context.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • implementation-layeringSkillAI & models

    Use when: creating or evolving a project-agnostic implementation layering model for a feature, capability, product workflow, research workflow, infrastructure change, or system improvement. Builds layers from minimum working unit proof to progressive hardening using value/cost layer-boundary heurist

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • interrogationSkillAI & models

    Use when: running one-question-at-a-time interviews with pluggable modes, evidence-backed prompts, and artifact updates after each answer.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • inventorySkillAI & models

    Use when: installing or maintaining a repository-local compiled knowledge inventory that lets agents ingest once, index, tag, query, lint, and reuse context across sigils.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • lab_interpreterSkillAI & models

    Use this skill when the user shares lab test values (血常规, 血生化, 甲功, 凝血 etc.) and asks what they mean, whether they are normal, or what action to take. Triggered by phrases like "帮我看看化验单", "我的血红蛋白偏低是什么意思", "这个指标正常吗". Primarily used by report_agent; also available to clinic_agent when symptoms co-occur

    Ready to connect

    github.com/wananing/smart-health-assistant25 stars

    View details
  • math-modeling-growthSkillAI & models

    Turns a real project's stage results, decisions, evidence, failure records, and current progress into plain, step-by-step, actionable learning explanations and post-competition growth reports. Use when the user asks to review a project, understand what they learned, explain a decision, generate a po

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • math-modeling-paperSkillAI & models

    Skill for evidence-constrained paper writing in math modeling competitions. Covers paper structure, body text, abstract, semantic placement of citations, canonical LaTeX, figure/table narrative, appendix/README, and in-paper AI disclosure. Formal numbers only consume the Solver Result Certificate; i

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • medication_calculatorSkillAI & models

    Use this skill when the user asks about medication dosing, how much of a drug to take based on their weight or age, or when a pharmacy_agent or clinic_agent needs to verify safe dosage ranges. Triggered by phrases like "我体重60公斤该吃多少剂量", "儿童用量怎么算", "这个药的最大剂量是多少", or "按体重算应该用多少". Supports weight-based

    Ready to connect

    github.com/wananing/smart-health-assistant25 stars

    View details
  • modeling-abstract-finalizerSkillAI & models

    Final abstract consistency check against current Result Certificates and Paper Handoff. Does not create new scientific claims.

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • modeling-behavior-refactorSkillAI & models

    Contestant-scale code simplification. Simplify unnecessary engineering structure while preserving mathematical/numerical behavior; any executable hash change requires result/evaluator regression.

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • modeling-paper-compressorSkillAI & models

    Conditional paper length control. Run only when an explicit page limit is exceeded or the user asks to compress; preserve core claims, formulas, figures and evidence.

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • modeling-repair-regressionSkillAI & models

    Targeted repair/regression coordinator. After a confirmed defect is fixed by its owner, rerun the smallest affected downstream checks and behavior comparisons.

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • modeling-solution-auditorSkillAI & models

    Final cross-artifact audit using upstream Result Certificates and Paper Handoff. Detect inconsistencies and route them to the correct owner without creating a new scientific registry.

    Ready to connect

    github.com/mantou6666/math-modeling-agent-flow25 stars

    View details
  • multi-backendSkillAI & models

    Advanced: Backend-focused multi-model workflow (Research → Ideation → Plan → Execute → Optimize → Review), Codex-led.

    Ready to connect

    github.com/luohaothu/everything-codex24 stars

    View details
  • multi-executeSkillAI & models

    Advanced: Multi-model collaborative execution. Acquires prototypes from external models, then refactors and implements production-grade code.

    Ready to connect

    github.com/luohaothu/everything-codex24 stars

    View details
  • multi-frontendSkillAI & models

    Advanced: Frontend-focused multi-model workflow (Research → Ideation → Plan → Execute → Optimize → Review), Gemini-led.

    Ready to connect

    github.com/luohaothu/everything-codex24 stars

    View details
  • multi-workflowSkillAI & models

    Advanced: Full multi-model collaborative development workflow (Research → Ideation → Plan → Execute → Optimize → Review) with quality gates.

    Ready to connect

    github.com/luohaothu/everything-codex24 stars

    View details
  • rbac-abac-designerSkillAI & models

    Designs Role-Based and Attribute-Based Access Control models, permission bitmasks, and multi-tenant boundary checks.

    Ready to connect

    github.com/codebygarv/ai-skills24 stars

    View details
  • review-guidelinesSkillAI & models

    Additional code review guidelines specific to this codebase. Auto-loaded by the review agent during PR reviews to enforce project conventions.

    Ready to connect

    github.com/youdotcom-oss/dx-toolkit25 stars

    View details
  • robot-talksSkillAI & models

    Run a multi-agent parallel investigation to identify cross-layer tensions

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • skill-evolveSkillAI & models

    A meta skill that automatically improves the corresponding SKILL.md based on feedback received after skill execution. Use it when a skill is wrong or missing something, or to record newly learned pitfalls.

    Ready to connect

    github.com/leeyudok/agents-scaffold25 stars

    View details
  • skill-transcriptorSkillAI & models

    Use when: converting a complete, coherent skill, prompt, command, or workflow into an Arcanum-compliant sigil package.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • snippetsSkillAI & models

    Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.

    Ready to connect

    github.com/launchdarkly/ai-tooling25 stars

    View details
  • subagent-strategySkillAI & models

    Use when deciding whether work merits a governed multi-agent dispatch and, when it does, proposing, tension-checking, confirming, registering, running, closing, and observing that dispatch through repository-local bindings.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 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.

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.

See how to connect your AI