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 71 of 301
- View details
test-generatorSkillAI & models
Generates and validates unit or integration tests based on real code contracts. Use when the user asks to add tests for functions, classes, or interfaces, fix test gaps for defects, improve coverage, generate regression cases, or refine test strategy; first reads existing tests and callers, does not
Ready to connect★ 842
- View details
zh-code-reviewerSkillAI & models
Chinese code review expert - generates detailed code review reports in Chinese
Ready to connect★ 842
- View details
zh-readmeSkillAI & models
Chinese README generator - analyzes the project first, then generates a high-quality README aimed at Chinese-speaking developers
Ready to connect★ 842
- View details
common-skillsSkillAI & models
Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.
Ready to connect★ 838
- View details
config-skillsSkillAI & models
Configuration module patterns for LlamaFarm. Covers Pydantic v2 models, JSONSchema generation, YAML processing, and validation.
Ready to connect★ 838
- View details
rag-skillsSkillAI & models
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.
Ready to connect★ 838
- View details
claude-authenticitySkillAI & models
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code belo
Ready to connect★ 830
- View details
meta-evalSkillAI & models
Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessin
Ready to connect★ 830
- View details
openjudgeSkillAI & models
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating grade
Ready to connect★ 830
- View details
prompt-regressionSkillAI & models
Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change hel
Ready to connect★ 830
- View details
rag-evalSkillAI & models
Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization,
Ready to connect★ 830
- View details
choosing-swarm-patternsSkillAI & models
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework an
Ready to connect★ 822
- View details
creating-agent-skills-skillSkillAI & models
Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules
Ready to connect★ 822
- View details
creating-skillsSkillAI & models
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples
Ready to connect★ 822
- View details
relay-80-100-workflowSkillAI & models
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes r
Ready to connect★ 822
- View details
review-fix-signoff-loopSkillAI & models
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict
Ready to connect★ 822
- View details
writing-agent-relay-workflowsSkillAI & models
Use when building multi-agent workflows with @relayflows/core. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, repairable verification gates, evidence-based completion, mandatory Claude-then-Codex fresh-eyes review/fix loops with test har
Ready to connect★ 822
- View details
audience-intelligenceSkillAI & models
Audience research module — builds six-dimension buyer personas (demographic, psychographic, behavioral, need-state, information, decision), Jobs-to-Be-Done maps, RFM/behavioral/lifecycle segmentation models, anti-personas with exclusion criteria, B2B buying-committee maps, and lookalike seed specs.
Ready to connect★ 814
- View details
brand-setupSkillAI & models
Create or update the brand profile every other skill reads — a quick 5-question or full 17-question interactive setup capturing identity, business model, industry and compliance markets, 4-dimension voice scales, channels, goals, and competitors, saved to ~/.claude-marketing/brands/{slug}/profile.js
Ready to connect★ 814
- View details
intelligence-reportSkillAI & models
Generate an intelligence briefing from the brand's compound intelligence base — total learnings with confidence distribution, cross-agent patterns by channel, audience, and objective, actionable playbooks synthesized from proven strategies, stale learnings flagged for revalidation, and a 0-100 compo
Ready to connect★ 814
- View details
loop-detectSkillAI & models
Detect and model the growth loops already compounding in a business — viral, content, data, paid, ecosystem, community — then quantify each loop's amplification factor, cycle time, and bottleneck, propose new loops, and rank investments by projected 12-month ROI with a sequenced implementation roadm
Ready to connect★ 814
- View details
narrative-trackerSkillAI & models
Track what AI engines (ChatGPT, Perplexity, Gemini, AI Overviews, Copilot) say about the brand, score responses against desired positioning, and flag misrepresentations, drift, and competitor narrative gains. Produces an alignment report, a narrative territory map, and a content strategy to correct
Ready to connect★ 814
- View details
switch-brandSkillAI & models
Switch the active brand profile for multi-client and agency work by running setup.py --switch-brand, after listing configured brands with the active one starred; confirms the new brand's industry, business model, and primary channel so subsequent outputs use its voice and compliance rules. Triggers
Ready to connect★ 814
- View details
CTF•AI/ML Attack & DefenseSkillAI & models
For AI/ML-related CTF challenges such as adversarial examples, model extraction, prompt injection, membership inference, training data poisoning, LoRA abuse, and LLM jailbreaks; trigger name: ctf-ai-ml
Ready to connect★ 808
- View details
cyrus-setup-githubSkillAI & models
Configure GitHub for Cyrus — gh CLI login and git config for PRs, with optional webhook setup to enable @mention responses in PR comments, automated rebases and merges, and auto-fixing based on CI failures (coming soon).
Ready to connect★ 807
- View details
cyrus-setup-launchSkillAI & models
Print a summary of the Cyrus setup and offer to start the agent.
Ready to connect★ 807
- View details
cyrus-setup-prerequisitesSkillAI & models
Check and install prerequisites for Cyrus — Node.js, jq, gh CLI, and the cyrus-ai npm package.
Ready to connect★ 807
- View details
cyrus-setup-repositorySkillAI & models
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
Ready to connect★ 807
- View details
debugSkillAI & models
Full debugging workflow — reproduce the bug with a failing test, perform root cause analysis, then implement a minimal fix.
Ready to connect★ 807
- View details
implementationSkillAI & models
Implement the requested changes. Write production-ready code, follow existing patterns, and run tests to verify your work.
Ready to connect★ 807
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.