Explore skills
Showing 49021–49050 of 71492 skills
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexW&B: log ML experiments, sweeps, model registry, dashboards.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexvLLM: high-throughput LLM serving, OpenAI API, quantization.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexAnalyze credential pooling operations and API reseller business models — economics, risks, detection patterns, and sustainability
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexDeep-dive framework for analyzing crypto tokens — market data, liquidity health, tokenomics, unlock schedules, and risk assessment. Combines on-chain data, API queries, and multi-source validation to generate actionable investment verdicts.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexAnalyze NFT projects for investment decisions — evaluate fundamentals, identify red flags, assess risk, and provide buy/hold/avoid recommendations
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexDiscover and analyze trending GitHub repositories from TrendShift and other sources — evaluate usefulness, extract learnings, and identify valuable skills/tools
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexExtract data from websites, including JavaScript-rendered SPAs and dynamic content
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexAudit social media accounts (TikTok, IG, etc.): scrape profiles, calculate engagement metrics, diagnose performance drops, interpret analytics screenshots.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexREST/GraphQL API testing with automated validation — test endpoints, validate responses, check status codes, and ensure API contracts
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexComprehensive workflow for contributing features to open-source IDE and coding tool projects
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexEvaluate and install ecosystem tools (Hermes plugins, skills, integrations) — assess complexity vs. benefit before installation, show examples for visual tools, and avoid "cloned but not configured" states.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexComprehensive workflow for contributing to open-source projects with quality checks
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexUse when creating new skills, editing existing skills, or verifying skills work before deployment
kevinnft/ai-agent-skills
Stars: 15Claude CodeCodexstribus/pygerengastos
Stars: 1Claude CodeCodexstribus/pygerengastos
Stars: 1Claude CodeCodexUse when designing, implementing, reviewing, or improving web and mobile UI/UX. Consults searchable design data for product patterns, styles, palettes, typography, accessibility, charts, icons, and common frontend stacks.
sidiangongyuan/codex-skills-library
Stars: 24Claude CodeCodexAccess Finland's Wilma school system from AI agents. Fetch messages, news, exams, and student data via the wilma CLI. Use when an agent needs to check school notifications, list upcoming exams, or summarize what needs parent attention.
kbarbel640-del/skills
Stars: 1Claude CodeCodexConvert meeting notes into owners, action items, decisions, and follow-up messages.
AGI-comming/functional-skill-creator
Stars: 256Claude CodeCodexCreate, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill directory into a functional skill structure.
AGI-comming/functional-skill-creator
Stars: 256Claude CodeCodexAssembles an alternative means and methods request as an argument rather than a form: establishes the prescriptive requirement that cannot be met and why, states the intent behind that requirement in the code's own words, sets out what is proposed and how it meets that intent, and gathers the evidence, the compensating measures and the conditions the applicant is willing to accept. Trigger on "alternative means and methods", "AMMR", "code modification request", "equivalency request", "we cannot meet this section, what now", "alternative-means-builder", or a prescriptive requirement named as unachievable with a request to make the case. Carries no code text, no precedent from other jurisdictions and no performance criteria; the requirement, its stated intent and any referenced standard all come from documents you supply. It does not approve anything, does not perform fire modelling or engineering analysis, and does not replace the fire protection engineer, the code consultant, or the Architect of Record.
DavidCho1999/archaiflow-skills
Stars: 1Claude CodeCodexTakes any requirement — a code section, a standard, an ordinance, a lease clause, an owner's design standard, a certification credit — and answers the question that comes before every other one: does this apply to this project at all. Works the six tests that decide it: is the document adopted or binding here, does the project fall inside its stated scope, has the trigger been met, does an exemption remove it, is this the edition that binds, and is something else more restrictive. Trigger on "does this apply to us", "is this section relevant", "do we have to comply with this", "they say this applies", "applicability-check", or a requirement quoted at you. Carries no text and no thresholds: every answer comes from the document you supply or the jurisdiction's own source. It does not interpret the requirement — `code-reader` takes it apart — and does not replace the code consultant or the Architect of Record.
DavidCho1999/archaiflow-skills
Stars: 1Claude CodeCodexTakes a citation somebody handed you — in a review comment, a consultant's report, a contractor's letter, a manufacturer's claim, or your own earlier drawing — and checks the three things that make it usable: does the document exist and in which edition, does the section number resolve inside it, and does the text actually say what it is being used to say. Reports which of the three could be verified and which could not, rather than a yes or a no. Trigger on "is this citation right", "check this code reference", "they quoted a section at us", "does this clause say that", "cite-check", or a section number pasted with a claim attached. Carries no code text: verification comes from the document you supply or from the jurisdiction's own published source, never from recall and never from a search result that is not the publisher. It does not interpret the clause — `explain-code` does — and does not replace the code consultant or the Architect of Record.
DavidCho1999/archaiflow-skills
Stars: 1Claude CodeCodex