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
8,868 results · page 261 of 296
- View details
warpSkillAI & models
Warp Rust web framework using filters. Covers routing, filters, rejection, WebSocket, and TLS. Use for composable, type-safe Rust APIs.
Ready to connect
- View details
webpackSkillAI & models
Webpack module bundler. Covers configuration, loaders, plugins, optimization. Use when working with Webpack-based projects or migrating from Webpack.
Ready to connect
- View details
workSkillAI & models
Work a single OpenRisk issue end to end — read it, route it to the right agents, implement, test, secure, verify, open the PR. This is the main daily loop. One issue per session.
Ready to connect
- View details
agri-paperSkillAI & models
Multi-subagent manuscript system for agricultural science, written as a senior agricultural scientist of the relevant discipline: understand the field, frame questions, curate data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal-aware thr
Ready to connect
- View details
atrinik-guidance-maintenanceSkillAI & models
Audit and synchronize Atrinik AGENTS.md, skills, README, architecture, and contributor guidance after CLI, ownership, layout, safety, or validation changes and during daily, weekly, or other periodic drift reviews.
Ready to connect
- View details
bitrix-background-jobsSkillAI & models
CAgent, addBackgroundJob, Messenger brokers/queues. Use for deferred and async processing.
Ready to connect
- View details
bitrix-eventsSkillAI & models
Covers Bitrix event system — new model (Bitrix\Main\Event, EventResult, EventManager::addEventHandler, make:event, make:eventhandler) and old model (OnBefore*/OnAfter* hooks in CIBlock, CUser, CSale and other classic APIs). Applied when integrating modules, entity lifecycle hooks, publishing custom
Ready to connect
- View details
bitrix-modulesSkillAI & models
Covers creation and maintenance of a custom Bitrix module in /local/modules/<vendor>.<module>/ — CModule class, install/index.php, DoInstall and DoUninstall, install/version.php with $arModuleVersion, registration of events and agents during installation, module options (options.php), generation via
Ready to connect
- View details
bitrix-sprint-migrationSkillAI & models
Covers Bitrix module sprint.migration — Version migrations, HelperManager (Iblock/Hlblock/Option/Agent/…), builders (run), CLI migrate.php (add/ls/up/down/redo/mark), configs migrations.*.php, restartable batches, exchange dirs. Use when creating or applying DB/schema/content migrations, exporting i
Ready to connect
- View details
fact-check-promptSkillAI & models
Generates a systematic fact-checking checklist from a draft article, categorizing every verifiable claim by type and priority, with the specific verification question, recommended source type, and appropriate verification strategy for each — across six distinct claim categories with tailored methodo
Ready to connect
- View details
food-paperSkillAI & models
Multi-subagent manuscript system for food & nutrition science covering the whole research process: understand the field, frame research questions, curate and analyze data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal-aware throughout. I
Ready to connect
- View details
food-pipelineSkillAI & models
Master orchestrator for the whole food & nutrition research-to-publication workflow. Coordinates the specialist skills — each with its own subagent set — into one governed path: journal selection, research (food-research / food-deep-research), writing & analysis (food-paper), figures (food-figure),
Ready to connect
- View details
investor-brief-writerSkillAI & models
Writes a concise investor brief for a commercial media project, covering market opportunity, revenue model, production plan, and the investment case — structured for a private investor or media investment fund, not a broadcaster or arts council.
Ready to connect
- View details
ns-init-projectSkillAI & models
Initialize or rebrand a NowStack Mobile product. Use for repo bootstrap, product brief intake, site-config, AGENTS.md, landing, mobile copy, Convex env, and final validation.
Ready to connect
- View details
pm-opportunity-scoringSkillAI & models
Score and rank product opportunities objectively with the Pragmatic Institute Opportunity Scoring model — across distinctive competency fit, competitive landscape, investment level, and impact to buyers/users. Use when the PM asks which idea to pursue, "score these opportunities", prioritize project
Ready to connect
- View details
rkllamaSkillAI & models
RKLLama (RK3588 NPU LLM server) operations — pod CLI quirks, model layout, hardware pinning, and the silent-failure modes of `rkllama_client pull`.
Ready to connect
- View details
visual-identity-promptSkillAI & models
Writes a comprehensive visual identity prompt for a show, channel, or publication — a master brief that defines the complete visual language and can be used to art-direct any asset in the project's visual system.
Ready to connect
- View details
arbeitszeugnis-prueferSkillAI & models
Detailed, model-independent workshop/mega prompt for fully reviewing German simple, qualified, interim, service, and training references. Use for employee, law firm, HR/employer, and works council reviews. Guides via Quickstart through sources, roles, status-
Ready to connect
- View details
eventaservo-test-builderSkillAI & models
Create tests following project architecture guidelines. Use when creating tests for models, controllers, services, or any component.
Ready to connect
- View details
excalidraw-skillSkillAI & models
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describe_scene and get_canvas_screenshot to see its own work,
Ready to connect
- View details
fix-audit-issueSkillAI & models
Fix a single audit issue in a git worktree. Creates a feature branch, follows fix-bug procedure, and creates a PR. Designed for parallel execution by spawned agents.
Ready to connect
- View details
huggingface-gradioSkillAI & models
Build, test, and publish accessible Gradio interfaces for models and data workflows using reproducible Python environments.
Ready to connect
- View details
plan-review-output-formatSkillAI & models
Output format specification for plan review agents. Defines the
Ready to connect
- View details
pr-review-output-formatSkillAI & models
Output format specification for PR review agents. Defines the JSON
Ready to connect
- View details
referral-programSkillAI & models
Designs viral referral programs with incentive structures, sharing mechanics, and tracking. Covers one-sided, two-sided, tiered, and milestone models with viral coefficient calculations. Use when someone wants word-of-mouth growth, viral loops, invite programs, or says 'referral', 'viral loop', 'wor
Ready to connect
- View details
voice-callSkillAI & models
Start and manage agent-driven voice calls on macOS through the `voice_call` tool.
Ready to connect
- View details
work-item-review-output-formatSkillAI & models
Output format specification for work-item review agents. Defines the
Ready to connect
- View details
advisorSkillAI & models
Lets your agent give health guidance for adults 50+ and track labs in files for doctor visits.
Ready to connect
- View details
agentclash-agent-build-authorSkillAI & models
Use when creating, editing, validating, or readying AgentClash agent builds and build versions, including agent identity, spec JSON, prompts, model/runtime expectations, tool bindings, and version readiness.
Ready to connect
- View details
agentclash-challenge-pack-llm-judgesSkillAI & models
Use when configuring AgentClash LLM-as-judge scoring, judge prompts, rubrics, assertion/reference/n-wise modes, evidence inputs, scorecard dimensions, abstention behavior, and judge result interpretation.
Ready to connect
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.