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 265 of 301
- View details
requirement-analysisSkillAI & models
Model a requirement/system: extract goals, scope, roles, rules, exceptions, dependencies from PRD, docs, bugs, code; outputs a structured model with clarifications. Not for: writing cases, strategy decisions, the pipeline. 建模需求/系统：从 PRD、文档、Bug、代码提炼目标/范围/角色/规则/异常/依赖。不用于：直接写用例、策略、流水线。
Ready to connect
- View details
review-agentSkillAI & models
A skill that reviews PR diffs or local diffs in Japanese, using `.agent/agents/reviewer.md` as the entry point. Used when the user asks for things like "レビュー" (review), "PR確認" (PR check), "差分確認" (diff check), "コードレビュー" (code review), "reviewer", or "レビュー指摘に対応" (address review comments). Also handles
Ready to connect
- View details
route-researcherSkillAI & models
Research mountain routes and generate comprehensive route beta reports for North American peaks, aggregating weather forecasts, avalanche conditions, daylight windows, trip reports, and access info from PeakBagger, SummitPost, WTA, AllTrails, and regional avalanche centers. Use when planning a climb
Ready to connect
- View details
senpai-status-checkSkillAI & models
Produce a fresh, read-only status report for a Senpai research track from GitHub, W&B, and the current agent's local controller state.
Ready to connect
- View details
stress-testing-agent-changesSkillAI & models
Attacks your own agent change, tool grant, dependency, model, or release on purpose, across risk types such as prompt injection, gaining extra power, unsafe output, and tool misuse, and records what you tried, what happened, and the leftover risk. Use when a change widens an agent's power, data acce
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
web-profileSkillAI & models
Web source profile for the generic researcher agent. Defines the
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
work-item-review-output-formatSkillAI & models
Output format specification for work-item review agents. Defines the
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
- View details
agentclash-prompt-eval-playgroundSkillAI & models
Use when scaffolding, validating, or running prompt eval YAML configs and managing playground experiments, test cases, and prompt variants via the AgentClash CLI.
Ready to connect
- View details
agentclash-scorecard-readerSkillAI & models
Use when interpreting AgentClash rankings, scorecards, replay timelines, artifacts, LLM judge results, or failure-review evidence into source-backed findings and next actions.
Ready to connect
- View details
agents-md-entrySkillAI & models
Evaluate an open source project's AGENTS.md and produce a corpus entry for the /agents-md directory. Use when adding a project to the directory, refreshing an existing entry, or running a batch of candidate repositories.
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
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
contextSkillAI & models
CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between
Ready to connect
- View details
diffusers-cliSkillAI & models
Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF Sandbox hardware via `--remote`, introspect a pipeline's input schema before calling it, or attach a LoRA at inference time. Prefer this over writing ad-hoc Pyth
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
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
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
qwik-docs-developmentSkillAI & models
Use when writing, modifying, or reviewing Qwik docs content or docs-site code under packages/docs, including docs routes, MDX content, generated LLM outputs, docs build behavior, or docs-specific e2e tests.
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
admet-predictionSkillAI & models
Turn a set of structures into absorption, distribution, metabolism, excretion, and toxicity estimates with ADMET-AI, and read them as a developability verdict rather than a table of numbers. Use this skill to run batch prediction over a library, interpret each endpoint against its DrugBank-approved
Ready to connect
- View details
antibody-engineeringSkillAI & models
Number antibody variable domains, annotate CDRs, and assess developability from sequence. Use this skill to apply IMGT, Kabat, Chothia, Martin, or AHo numbering with ANARCI, delimit CDRs and framework regions, scan for chemical liabilities (N-glycosylation sequons, deamidation NG, isomerisation DG,
Ready to connect
- View details
arbeitszeugnis-prueferSkillAI & models
Detailed, model-independent workshop/megaprompt for the complete review of German simple, qualified, interim, service, and training references. Use for employee, law firm, HR/employer, and works council reviews. Guides step by step via Quickstart through sources, roles, status
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.
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.