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: Productivity

2,697 results · page 88 of 90

  • adhdSkillProductivity

    Designed to assist users with ADHD (Attention Deficit Hyperactivity Disorder) by mitigating task paralysis, managing distractions, providing dopamine-driven progress tracking, and using executive-friendly visual formatting. Triggered by keywords or topics: - Focus/Distraction: "adhd", "fokus", "dist

    Ready to connect

    github.com/rudycity/superagent20 stars

    View details
  • agent-idea-feedSkillProductivity

    Turns concrete tasks from seven fixed public sources into a one-off or daily feed of interesting complete-task Agent ideas. Use when the user wants Agent ideas from Upwork-style marketplaces or chinese-independent-developer, especially when every source must contribute three concise, unseen ideas wi

    Ready to connect

    github.com/z2z23n0/idea-miner23 stars

    View details
  • alibaba-maestroSkillProductivity

    Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard

    Ready to connect

    github.com/vincentchuwaichow/vanguard-frontier-agentic23 stars

    View details
  • alibaba-maxcompute-dataworks-analystSkillProductivity

    Manage MaxCompute CU package governance, DataWorks scheduling, Quick BI reporting, and PAI ML platform. Optimize query cost and job scheduling efficiency for big data workloads.

    Ready to connect

    github.com/vincentchuwaichow/vanguard-frontier-agentic23 stars

    View details
  • CLI BridgeSkillProductivity

    Delegate tasks and collaborate with external AI CLI assistants (Codex, Claude Code, AGY, or custom binaries) via one-shot execution or persistent multi-turn sessions.

    Ready to connect

    github.com/rudycity/superagent20 stars

    View details
  • debug-loopSkillProductivity

    Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or emitting wrong tool calls.

    Ready to connect

    github.com/hoangsonww/forge-agentic-coding-cli22 stars

    View details
  • ferrox-quickSkillProductivity

    A small self contained task, with atomic commits and state tracking but no planning ceremony

    Ready to connect

    github.com/ferroxlabs/ferrox-factory22 stars

    View details
  • ferrox-requesting-code-reviewSkillProductivity

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    Ready to connect

    github.com/ferroxlabs/ferrox-factory22 stars

    View details
  • handoff-contextSkillProductivity

    Produces a prospective handoff package for another agent, model, or human dev to pick up the task where it left off — without context from the current session. Unlike session-summary (skill 31), which is retrospective: handoff-context builds an actionable briefing for whoever arrives blind. Trigger

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • karpathy-guidelinesSkillProductivity

    Behavioral rules to minimize common LLM coding pitfalls. Applies to all code creation, modification, review, and validation tasks.

    Ready to connect

    github.com/rudycity/superagent20 stars

    View details
  • maintain-project-ai-recordsSkillProductivity

    Initialize and maintain lightweight AI work records in a writable project. Use on the first substantive writable task and after meaningful milestones. Do not create records for read-only inspection or trivial answers.

    Ready to connect

    github.com/wildpigking/codex-project-skill-manager23 stars

    View details
  • manage-codex-skillsSkillProductivity

    Inventory, classify, route, catalog, relocate, or validate Codex skills and generate a skills menu. Use for skill-library organization or when Codex must find task-relevant skills. Classification, relocation, creation, revision, and promotion require user approval.

    Ready to connect

    github.com/wildpigking/codex-project-skill-manager23 stars

    View details
  • non-linear-debuggingSkillProductivity

    Triggered when the agent needs to debug complex errors, analyze obscure runtime failures, find subtle bugs, or trace system anomalies using non-linear, multidimensional hypothesis graphs, backward-forward triangulation, behavioral state inversion, and dynamic perturbation instead of slow sequential

    Ready to connect

    github.com/rudycity/superagent20 stars

    View details
  • oc-automateSkillProductivity

    Create, list, and manage scheduled tasks and automations. Use when the user asks to schedule something, set a reminder, create a recurring task, or manage existing automations. Trigger phrases: 'remind me', 'every hour', 'schedule', 'at 9am', 'recurring', 'automate', 'cron'.

    Ready to connect

    github.com/mfielding92/clawedback23 stars

    View details
  • orchestratorSkillProductivity

    Skill for the Tech Lead/Orchestrator of the development pipeline. Should be used at the start of every task and between relevant pipeline stages. Coordinates which skill to run and in what order, adapts the flow to the context, ensures no critical step is skipped, and maintains an overview of progre

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • parallel-dispatcherSkillProductivity

    Skill specialized in correctly parallelizing work via subagents — without falling into the skill-vs-agent trap. Use when you need to dispatch N vertical slices, N reviews, or N independent tasks in parallel, and when parallel reviewers/agents disagree about the same finding and the arbit decision

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • pr-babysitSkillProductivity

    The repeatable loop for watching a pull request until it is merged or closed, pairing webhook subscription with a scheduled self check-in so CI results, new pushes, and merge-conflict transitions are never missed; use when asked to watch, babysit, or autofix a PR, or right after creating one.

    Ready to connect

    github.com/vincentchuwaichow/vanguard-frontier-agentic23 stars

    View details
  • program-routerSkillProductivity

    Decide the minimal composition of plugins, skills and, when necessary, declarative programs for a task. Use before improvising a pipeline or when the user asks which skill, plugin, workflow or program to use. Trigger on: "qual skill", "qual plugin", "qual program", "qual workflow", "roteie e

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • promptSkillProductivity

    Use ONLY when the user explicitly asks to improve a prompt aimed at an AI: "improve my prompt", "fix this prompt", "how should I ask for this", "make this prompt better". A prompt pasted to be answered or executed is a task, not a rewrite request: do that task instead. About prompts for an AI, not a

    Ready to connect

    github.com/mehrad-dm/mastermind23 stars

    View details
  • running-checksSkillProductivity

    Apply when about to run pnpm typecheck, lint, lint:fix, test, format, build, coverage or bench in any package, when deciding when in a task to run one, and whenever you find yourself waiting on a check's output. Esposter rules for running any check — every check goes out with run_in_background true

    Ready to connect

    github.com/esposter/esposter23 stars

    View details
  • sota-async-concurrencySkillProductivity

    State-of-the-art rules for writing and auditing asynchronous and concurrent code across runtimes (Python asyncio, JS/Node, Go, Rust, JVM). Use when building anything with async/await, threads, processes, event loops, task groups, channels, or queues — and when auditing existing code for race conditi

    Ready to connect

    github.com/martinholovsky/sota-skills23 stars

    View details
  • sota-mobileSkillProductivity

    State-of-the-art mobile engineering for building and auditing iOS and Android applications. Use when the task involves mobile apps in any form — native (Swift, SwiftUI, Kotlin, Jetpack Compose), cross-platform (React Native, Flutter, Kotlin Multiplatform), Swift as a language — Swift 6 strict concur

    Ready to connect

    github.com/martinholovsky/sota-skills23 stars

    View details
  • unreal-gasSkillProductivity

    Expert guide for Unreal Engine 5.x Gameplay Ability System (GAS) C++ development. Covers AbilitySystemComponent, GameplayAbilities, GameplayEffects, Attributes/AttributeSets, GameplayTags, GameplayCues, AbilityTasks, prediction/replication, and common patterns. Use when the user asks about GAS, game

    Ready to connect

    github.com/maystudios/claude-skills23 stars

    View details
  • wizardSkillProductivity

    8-phase implementation methodology with built-in verification at each stage. Use for implementing features, fixing complex bugs, or any task where quality matters. Use when the user says "wizard mode", "do this properly", "production quality", or "full workflow".

    Ready to connect

    github.com/mfielding92/clawedback23 stars

    View details
  • yolo-modelsSkillProductivity

    Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocabulary or promptable

    Ready to connect

    github.com/ultralytics/skills23 stars

    View details
  • api-contractSkillProductivity

    Use when generating an OpenAPI 3.1 API contract from requirements, user stories, or domain models. Applies a pluggable API standard (Zalando by default) as hard constraints to produce complete, validated YAML specs ready for code gen, test gen, mocks, and SDKs. Activate for tasks involving API desig

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • ase-okf-referenceSkillProductivity

    Not a selectable skill. Inert reference data invoked only by another skill's explicit agent-skill-engineering-reference/v1 provider call. It answers no user request, performs no user task, and must never be chosen to satisfy a user's question on any subject. When a user's request matches this data's

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • bitrixSkillProductivity

    Core-first Bitrix / 1C-Bitrix / Битрикс / БУС / boxed Bitrix24 expertise. Use when a task mentions or a repo contains Bitrix markers: `www/bitrix`, `/bitrix`, `/local`, `bitrix/modules`, components/templates, `CIBlock*`, `CUser`, `CModule`, `Loader::includeModule`, `Bitrix\Main`, D7, legacy `C*`, ин

    Ready to connect

    github.com/poliklot/bitrix-agent-skill22 stars

    View details
  • compare-hypothesesSkillProductivity

    Compare competing hypotheses on a decision-shaped question using an ACH-style evidence matrix (hypotheses × evidence-for/against). Dispatches per-hypothesis parallel retrieval on Claude Code (one `evidence-retriever` subagent per hypothesis — the +81% parallelizable-task case from multi-agent resear

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • factory-flashingSkillProductivity

    Use when working on the SEC.3 factory-flashing pipeline — provisioning per-device keys into an STM32 at manufacture (app/services/factory_flashing/, lib/tasks/factory.rake): the one-pass silicon UID→DID derivation [FW.54], the wrong-board guard, UID collision → quarantine, the six Flash key blocks a

    Ready to connect

    github.com/alexey-lukin/silken_net22 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.

53,789 of the 54,221 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