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
9,018 results · page 217 of 301
- View details
gsd-set-profileSkillAI & models
Switch model profile for GSD agents (quality/balanced/budget/inherit)
Ready to connect★ 62
- View details
gsd-shipSkillAI & models
Create PR, run review, and prepare for merge after verification passes
Ready to connect★ 62
- View details
gsd-threadSkillAI & models
Manage persistent context threads for cross-session work
Ready to connect★ 62
- View details
gsd-ui-reviewSkillAI & models
Retroactive 6-pillar visual audit of implemented frontend code
Ready to connect★ 62
- View details
- View details
gsd-validate-phaseSkillAI & models
Retroactively audit and fill Nyquist validation gaps for a completed phase
Ready to connect★ 62
- View details
gsd-verify-workSkillAI & models
Validate built features through conversational UAT
Ready to connect★ 62
- View details
gsd-workstreamsSkillAI & models
Manage parallel workstreams — list, create, switch, status, progress, complete, and resume
Ready to connect★ 62
- View details
hr-aiSkillAI & models
Help HR managers, recruiters, and talent acquisition teams understand Artificial Intelligence (AI), Machine Learning (ML), Generative AI, LLM Engineering, AI Infrastructure, and modern AI product development workflows. Use when asked to explain AI engineering, screen AI engineers, understand machine
Ready to connect★ 62
- View details
hr-demand-planningSkillAI & models
Help HR leaders, workforce planners, and TA teams translate business strategy into headcount demand plans. Use when asked to build a headcount plan, forecast short-term hiring demand, model workforce demand, align HR capacity with business growth, create a staffing demand forecast, or plan headcount
Ready to connect★ 62
- View details
hr-organization-effectivenessSkillAI & models
Help HR leaders, HRBPs, and OD consultants assess and improve organizational effectiveness, including team health, operating model fitness, capability gaps, and organizational performance. Use when asked to assess org effectiveness, diagnose team performance issues, improve org health, run an OE dia
Ready to connect★ 62
- View details
hr-workforce-forecastingSkillAI & models
Help workforce planners build and maintain quantitative forecasts of headcount, attrition, and hiring demand. Use when asked to forecast headcount for next year, predict attrition trends, build a hiring demand forecast, model seasonal staffing needs, or improve the accuracy of our workforce forecast
Ready to connect★ 62
- View details
hr-workforce-planningSkillAI & models
Help HR managers with workforce planning and strategy. Use when asked to create a workforce plan, conduct a skills gap analysis, develop a succession plan, build workforce models, analyze headcount, forecast long-term workforce needs, develop workforce diversity strategies, or any workforce planning
Ready to connect★ 62
- View details
hr-workforce-scenario-planningSkillAI & models
Help workforce planners and HR leaders model multiple future workforce scenarios to stress-test plans against uncertainty. Use when asked to build workforce scenarios, model a best/worst case headcount plan, stress-test our workforce plan against [risk], plan for a hiring freeze or rapid growth scen
Ready to connect★ 62
- View details
improve-animationsSkillAI & models
Lets your agent audit a codebase's animations and write prioritized improvement plans without changing code.
Ready to connect★ 62
- View details
ito-trade-plannerSkillAI & models
Build a non-advisory prediction-market trade planning worksheet for Itô or venue workflows. Use to inspect venues, underliers, constraints, order prerequisites, and manual execution steps without placing trades or recommending positions.
Ready to connect★ 62
- View details
latency-critical-systemsSkillAI & models
Use for latency-sensitive systems such as realtime dashboards, market data, streaming agents, execution gateways, queues, caches, or HFT-like infrastructure where freshness and p95 latency matter.
Ready to connect★ 62
- View details
Legal Abductive ReasoningSkillAI & models
A legal abductive reasoning skill for generating and evaluating the most plausible explanatory hypotheses when evidence is incomplete or facts are ambiguous. Combines Mill's Five Methods (agreement, difference, joint method, residues, concomitant variation) for structured causal inference. Triggered
Ready to connect★ 62
- View details
Legal Conflict ResolutionSkillAI & models
This skill is triggered when an AI agent encounters the following situations during legal reasoning: (1) multiple legal provisions apply to the same facts (overlapping provisions); (2) contradictions or inconsistencies among different pieces of evidence (evidence conflicts); (3) a case involves mult
Ready to connect★ 62
- View details
logistics-exception-managementSkillAI & models
Codified expertise for handling freight exceptions, shipment delays, damages, losses, and carrier disputes. Informed by logistics professionals with 15+ years operational experience. Includes escalation protocols, carrier-specific behaviors, claims procedures, and judgment frameworks. Use when handl
Ready to connect★ 62
- View details
Normative Validity ReviewSkillAI & models
This skill is triggered when an AI agent retrieves a specific legal provision during legal reasoning and needs to verify its validity. Trigger conditions include but are not limited to: 1. Before the agent cites any legal provision as a basis for reasoning; 2. When a user provides a legal provision
Ready to connect★ 62
- View details
oss-post-prSkillAI & models
Handle PR review feedback - understand reviewer comments, research their concerns, and help the user address them. The LLM explains what reviewers want and why; the user decides how to respond and writes the code. Use when you receive review comments on a submitted PR. Not for opening the PR in the
Ready to connect★ 62
- View details
oss-submit-prSkillAI & models
Submit a pull request following the repo's contribution guidelines. Reviews the diff, checks for common rejection reasons, and helps the user write their own PR description. The LLM reviews. the user writes. Use when implementation is complete and tests pass. Not for responding to review comments af
Ready to connect★ 62
- View details
Other Legal ResearchSkillAI & models
This skill is triggered when the agent needs to retrieve supplementary legal information beyond statutes, judicial interpretations, and typical cases. This includes, but is not limited to: legislative background materials (draft explanations, deliberation reports, legislator press Q&A), regulatory c
Ready to connect★ 62
- View details
patent-analysisSkillAI & models
A structured preliminary analysis tool for Chinese invention and utility model patents. This skill should be used when the user needs to break down or interpret claims, compare patent protection scopes, conduct product infringement comparison, equivalent analysis, stability and invalidation risk ana
Ready to connect★ 62
- View details
planning-voice-agent-user-interviewsSkillAI & models
Plan a round of user interviews conducted by PostHog''s AI voice agent (a "robo interviewer") — the automated voice-agent interview product. Captures a UserInterviewTopic (who to target, what to ask, framing context, question list) and calls user-interview-topics-create. ONLY trigger when the user c
Ready to connect★ 62
- View details
research-agentSkillAI & models
Use for current web/X research, library/API verification, competitive analysis, source-backed technical decisions, or updating docs with recent facts.
Ready to connect★ 62
- View details
scanning-experiments-with-replay-visionSkillAI & models
Provisions a Replay Vision scanner scoped to one experiment's exposed sessions: sets `experiment_targeting` so the API derives the person-scoped exposure filter server-side, templates a prompt that stays comparable across variants, sizes credit spend against the experiment's own population, and crea
Ready to connect★ 62
- View details
second-brain-chat-importSkillAI & models
Triage an exported chat history into what to ingest, what to archive and what to delete, with a privacy pass first. Use this skill when the user has exported their Claude or ChatGPT history, asks to import old conversations, or asks what in their chat archive is worth keeping. Do NOT use for ingesti
Ready to connect★ 62
- View details
second-brain-projectSkillAI & models
Set up or update a project in the vault: the four-stage folder pipeline, a project-scoped CLAUDE.md with one goal, and links to the concept pages it depends on. Use this skill when the user starts something new they will work on over time, says "create a project", "set up a folder for X", or asks to
Ready to connect★ 62
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.
54,826 of the 55,257 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.