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 234 of 296
- View details
p14g-beauty-systemSkillAI & models
Aesthetic training system—systematic accumulation and calibration of aesthetic standards, human-AI collaboration workflows, and standard evolution mechanisms
Ready to connect
- View details
p14h-beauty-prefaceSkillAI & models
Preface and core thesis — when everything can be generated, aesthetic leadership becomes the core competitive advantage
Ready to connect
- View details
- View details
- View details
p2d-convergence-decisionSkillAI & models
AI-Native product methodology — a practical Skill for goal convergence and product decision-making.
Ready to connect
- View details
- View details
p6b-arbiter-mode-designerSkillAI & models
Arbiter Mode Designer. Designs business models centered on "truth as a service": providing verifiable, authentic information and judgment so users can trust that every number is real. Based on the 'AI Certainty Business Model' concept card.
Ready to connect
- View details
p6c-insurance-mode-designerSkillAI & models
Insurance model designer. Designs business models centered on "guaranteed outcomes": provides guarantees for AI output results, with compensation or free service if errors occur. Based on the《AI确定性商业模式》concept card.
Ready to connect
- View details
p6d-prediction-arbitrage-designerSkillAI & models
Prediction arbitrage designer. Designs business models centered on "surpassing human predictive ability": arbitrating in domains where AI prediction outperforms humans, converting predictive advantage into business value. Based on the "AI Certainty Business Model" concept card.
Ready to connect
- View details
p7a-data-flywheel-builderSkillAI & models
Data Flywheel Builder. Based on the 'AI Native Marketing & Growth' data flywheel concept card, it helps product teams evaluate and build a self-reinforcing data flywheel: usage → data → model → product → more users → more data.
Ready to connect
- View details
p7b-intent-prediction-designerSkillAI & models
Intent prediction marketing designer. Based on the intent prediction marketing concept card from "AI Native Marketing & Growth", helps products upgrade from "audience targeting" to "individual foresight" — delivering relevant content before users explicitly express their needs.
Ready to connect
- View details
p7c-predictive-retention-designerSkillAI & models
Predictive retention designer. Based on the predictive retention concept card from 'AI Native Marketing and Growth', it helps products upgrade from 'win-back after churn' to 'prevention before churn' — proactively intervening before users churn.
Ready to connect
- View details
p7e-customer-loopSkillAI & models
An operational skill for the 'AI Native Product Methodology' — Customer Loop.
Ready to connect
- View details
p8a-rax-risk-assessorSkillAI & models
RAX Risk Assessor. Based on the RAX framework (Risk, Ambiguity, eXposure) from "User Experience in the AI Era", it systematically assesses the risk, ambiguity, and exposure level of AI products, helping product teams identify and manage user experience risks.
Ready to connect
- View details
p8b-trust-tier-designerSkillAI & models
Trust tier designer. Based on the trust tier theory from "User Experience in the AI Era", designs trust tier systems for AI products so users can gradually build trust in AI.
Ready to connect
- View details
Proofpoint Essentials Org ManagementSkillAI & models
Proofpoint Essentials organization lifecycle: get an org and its domains, activate/deactivate, delete, manage domains, toggle features, adjust licensing allocation, change package/subscription tier, and mint an Odin-based SSO token for console handoff.
Ready to connect
- View details
Proofpoint Essentials User ManagementSkillAI & models
Proofpoint Essentials mailbox user management within a customer org: list, get, create (including batch create), update, and delete mailbox-protected users.
Ready to connect
- View details
Proofpoint URL DefenseSkillAI & models
Proofpoint URL Defense fundamentals: URL rewriting (v2/v3 formats), click-time analysis and verdicts, and manual/API decoding of rewritten URLs back to their originals.
Ready to connect
- View details
realistic-long-chat-validationSkillAI & models
Run a realistic many-turn OpenMates CLI chat to validate Gemini routing, generated artifact quality, repeated compression checkpoints, and publish a successful run as an example chat
Ready to connect
- View details
Restore-Test VerificationSkillAI & models
Whether a backup is actually recoverable rather than merely present: the ranked hierarchy of restore evidence (actual restore performed, full boot/virtualization verification, screenshot verification, spot-check restore drill, no evidence at all), adequate test cadence per data-criticality tier, and
Ready to connect
- View details
review-ticketSkillAI & models
Triage a ticket or ticket set before work starts — compare it against the codebase and save a review covering verdict, feature walkthrough, and only the high-cost questions worth raising.
Ready to connect
- View details
run-nx-checksSkillAI & models
Run nx format, lint, test, and build on affected or specified projects, then fix unambiguous failures
Ready to connect
- View details
Standards Drift DetectionSkillAI & models
Detecting configuration drift against an established baseline: CIPP standards checks and Best Practice Analyser results, Liongard change detections and inspection timelines, the three conditions that make a diff real drift rather than noise, the signals that separate intentional or authorized change
Ready to connect
- View details
sub-agent-sandboxingSkillAI & models
Use when delegated work needs runtime guardrails — constrain sub-agents with loop detection, circuit breakers, and escalating sandbox levels before accepting their output
Ready to connect
- View details
- View details
verify-understandingSkillAI & models
Verify the engineer is ready to implement a feature — a teach-back conversation over a .TICKET-REVIEW.md where they explain the feature in their own words and the agent probes and corrects.
Ready to connect
- View details
agent-developmentSkillAI & models
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or
Ready to connect
- View details
build-mcp-serverSkillAI & models
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development
Ready to connect
- View details
ccSkillAI & models
Sync cc-settings with Claude Code upstream (maintainer) or update a local Claude Code or Codex install (user). Triggers "sync with claude code", "changelog sync", "update cc-settings", "refresh my install".
Ready to connect
- View details
consolidateSkillAI & models
Audit and prune rules, skills, and learnings to cut context bloat. Triggers "consolidate", "clean up rules", "what's redundant", or degraded agent performance from oversized instructions.
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.