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
9,019 results · page 80 of 301
- View details
your-skill-nameSkillAI & models
Replace with when the AI should activate this skill. Be pushy — cover multiple phrasings so the AI activates for a wide range of user prompts.
Ready to connect★ 659
- View details
content-refinement-agentSkillAI & models
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devi
Ready to connect★ 655
- View details
section-writing-agentSkillAI & models
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2,
Ready to connect★ 655
- View details
evotown-dispatch-completeSkillAI & models
Report Evotown dispatch job completion after the agent finishes real work.
Ready to connect★ 648
- View details
evotown-handoffSkillAI & models
Queue a cross-agent or cross-team handoff through the Evotown control plane.
Ready to connect★ 648
- View details
geo-gap-fixerSkillAI & models
Audit how often LLMs recommend your brand vs competitors and generate a GEO action plan.
Ready to connect★ 642
- View details
pricing-finderSkillAI & models
Tell it what your product is (URL or description) and it finds 5 competitors globally, fetches their actual pricing pages, extracts every tier and price point, and returns a complete pricing intelligence report: the dominant pricing model in your space, a benchmark price table, feature gate analysis
Ready to connect★ 642
- View details
architecture-feature-firstSkillAI & models
Use when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.
Ready to connect★ 637
- View details
developing-genkit-dartSkillAI & models
Lets your agent build and test Dart apps that use Firebase's Genkit AI toolkit.
Ready to connect★ 637
- View details
firebase-aiSkillAI & models
Use when setting up firebase_ai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
Ready to connect★ 637
- View details
flutter-app-architectureSkillAI & models
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).
Ready to connect★ 637
- View details
flutter-change-notifierSkillAI & models
Use when setting up ChangeNotifier models, providing them to the widget tree, consuming state with Consumer or Provider.of, or optimizing rebuilds.
Ready to connect★ 637
- View details
unit-test-generatorSkillAI & models
Automatically generate unit tests based on source code, supporting multiple languages and testing frameworks.
Ready to connect★ 635
- View details
bayesian-intrinsic-growth-valuationSkillAI & models
Use a Bayesian intrinsic-growth valuation model to evaluate whether a company's market value sufficiently, excessively, or insufficiently prices its real 3-5 year growth. Use when the user asks for Bayesian valuation, intrinsic growth rate, implied growth, growth-hypothesis probabilities, FOMO versu
Ready to connect★ 631
- View details
commentSkillAI & models
Draft (and after approval, post) a reply on a claude-desktop-extra GitHub issue in this project's house voice - short, factual, friendly, no self-blame and no speculation - ending in one copy-pasteable command block that asks the reporter for the evidence we still need. Invoke as "/comment <issue nu
Ready to connect★ 623
- View details
fresh-upstreamSkillAI & models
For claude-desktop-extra - wipe any existing extracted Claude Desktop bundles and extract a fresh, CLEAN, UNPATCHED copy of the latest official Claude Desktop Linux .deb into ./tmp/ for patch analysis. Fetches + GPG/SHA256-verifies the latest .deb if missing or stale, then extracts app.asar via asar
Ready to connect★ 623
- View details
linuxSkillAI & models
Linux compatibility reference for the claude-desktop-extra project (repackaging Anthropic's official Claude Desktop Linux .deb and patching its app.asar for the distros Anthropic does not ship). Use when working on Linux support, session managers, distros, Computer Use input/screenshot backends, gli
Ready to connect★ 623
- View details
updateSkillAI & models
For claude-desktop-extra - handle a new upstream Claude Desktop version end-to-end: build, fix failing patches, diff old vs new JS for new platform gates, audit feature flags + ion-dist + platform gates, update baseline docs + CHANGELOG, bump .upstream-version, then commit. Mirrors issue #145 / UPDA
Ready to connect★ 623
- View details
light-idea-generationSkillAI & models
Light research pipeline, step 3 · idea generation: takes a vague direction/data/literature and does **structured divergence** (prompted system generation, not generic brainstorming) → produces **layered candidate ideas that are both worth doing and feasible** (moonshot ambitious / solid / safe fallb
Ready to connect★ 621
- View details
light-patent-disclosureSkillAI & models
Prepare evidence-backed patent invention disclosure materials for attorney or patent-agent review. Use when the user asks for 专利点挖掘, 技术交底书, 现有技术/查新记录, claim/patent-point support mapping, invention disclosure drafts, patent figures, or a handoff package for a software/research/project invention. This
Ready to connect★ 621
- View details
robotic_grounding_runSkillAI & models
Generates the exact command to run the robotic_grounding floating-hand (Sharpa Wave / Dex3) pipeline — retargeting, dummy-agent smoke tests, RL training, and evaluation. Use this skill whenever the user wants to RUN something in robotic_grounding and needs the right command: "how do I run a smoke te
Ready to connect★ 618
- View details
ai-sdkSkillAI & models
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, or tools, (2) Want to build AI agents, chatbots, or text generation features, (3) Have questions about AI providers (OpenAI, Anthrop
Ready to connect★ 617
- View details
herdr-orchestrationSkillAI & models
Orchestrate Claude and Codex worker TUIs from a controller agent — one worker per named herdr tab, driven over the herdr socket CLI.
Ready to connect★ 617
- View details
testing-bossSkillAI & models
Testing doctrine for tests that reveal bugs instead of passing for the wrong reason — spanning software and LLM/AI systems. Use when authoring or reviewing tests, adding a mock, deciding where a test belongs, letting a coding agent generate tests, triaging flaky CI, designing an eval suite for an LL
Ready to connect★ 617
- View details
to-promptSkillAI & models
Turn code, issues, or context into a handoff brief for another LLM — full context, zero prescribed solution, written to docs/prompts/. Use when packaging a bug fix, an improvement, or a feature request for an external LLM to implement. Don't use for prompts that already prescribe an implementation,
Ready to connect★ 617
- View details
tweetsmash-apiSkillAI & models
Uses the TweetSmash REST API to fetch bookmarks, inspect labels, and add or remove labels from saved tweets. Use when integrating TweetSmash into scripts, agents, workflows, cron jobs, or internal tools that need bookmark retrieval, filtering, pagination, or label management. Do not use for direct b
Ready to connect★ 617
- View details
ui-craftSkillAI & models
Craft floor for user-facing UI that refuses AI slop. Use when designing or building a new visible surface (component, page, dashboard, form, dialog, empty/loading/error state), reviewing or refactoring an existing one, or shaping an AI/agent interface (chat, streaming, citations). Not for backend, i
Ready to connect★ 617
- View details
wire-devtoolSkillAI & models
Wire an existing devtool package into host apps (LLD, LLM, web-tools) and optionally create bindings
Ready to connect★ 617
- View details
yc-applySkillAI & models
Guides a founder through the full Y Combinator batch application end-to-end. A 10-phase workflow that captures the live YC form, profiles the founders, stress-tests the idea via an embedded grill loop, runs a mandatory 5-agent parallel external research pass on the startup, drafts every form field w
Ready to connect★ 617
- View details
nw-ab-critique-dimensionsSkillAI & models
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Ready to connect★ 610
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.
54,764 of the 55,196 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.