agentsclimarketplace

The catalog

609,856 rows, by stacks then stars

  • Career review cycle

    p-m-p/career-skills/skills/career-review-cycle Skill

    no license2★ repo

    Manage your career performance across the full year cycle: set and track yearly goals, log daily work, generate brag documents, prepare for performance reviews and 1-on-1s, and build promotion cases. Use when the user mentions performance goals, OKRs, work logging, accomplishments, brag doc, self-assessment, annual review, mid-year review, 1-on-1 prep, promotion case, or promo doc. Also triggers on "what did I work on", "log my work", "review prep", "set my goals", "career goals", or "am I ready for promotion".

  • Clean code comments

    lifeodyssey/craftsmanship-skills/skills/clean-code-comments Skill

    no license2★ repo

    Use when deciding whether, how, or where to write code comments — applies Clean Code comment principles

  • 00 andruia consultant

    newmindsgroup/ai-agent-skills-library/dist/skills/00-andruia-consultant Skill

    2★ repo

    Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en español.

  • Luxin

    danielgwilson/luxin Skill

    2★

    AI image generation and editing for agents across text-to-image and image-to-image workflows, video generation, audio generation, and image-to-3D asset creation through one zero-setup hosted runtime. Use Luxin when an agent needs durable media URLs, recoverable jobs, model/cost inspection and stable JSON envelopes with capability-preserving parameters. Optional agent-funded credits work without a provider API key, OAuth app, local model or per-provider billing account.

  • Address and merge

    bmaltais/skills/address-and-merge Skill

    no license2★ repo

    Address all review feedback on an open PR, merge it, and clean up the branch. Use when the user says "address the feedback on PR N", "fix the review comments", "merge PR N", "address and merge", or "clean up after merging". Handles inline (line-level) and conversation-level review comments, runs the build/test suite, commits the fixes, pushes, squash-merges the PR, deletes the remote branch, deletes the local branch, and returns to main.

  • Campaign review

    celeryhq/simplified-ai/skills/campaign-review Skill

    2★ repo

    Prepare Simplified social drafts for client, stakeholder, or team review and manage approval-ready revisions. Use when the user asks to package selected or all drafts for approval, create and present a social review link or review bundle, collect a campaign for client review, inspect draft status, revise selected drafts, or prepare approved content for a later publishing step.

  • Ios architecture

    almasumdev/awesome-ios-agent-skills/.github/skills/architecture/ios-architecture Skill

    no license2★ repo

    Expert guidance on modern iOS application architecture using Clean Architecture, SwiftUI-first layering, and Swift Package Manager (SPM) feature modularization. Use this when asked about project structure, module graph, or DI.

  • Apply tdd loop en

    roebi/sw-dev-agent-framework/skills/apply-tdd-loop-en Skill

    no license2★ repo

    Applies the Test-Driven Development (TDD) cycle as an agentic loop of RED -> GREEN -> REFACTOR iterations until all requirements are covered or all existing code paths are tested. Use when a user or agent wants to write code strictly test-first, add missing tests to existing code, or drive a full TDD session for a module, class, or function. Activate for trigger phrases like: "apply TDD", "write this test-first", "do a TDD loop", "TDD cycle for", "drive TDD on", "red green refactor", or "add tests then implement".

  • Bank reconciliation

    gokulb20/crewm8-cfo-skills/skills/cash-treasury/bank-reconciliation Skill

    2★ repo

    Reconciles bank accounts and credit cards monthly — matches every transaction to the ledger, resolves exceptions, tracks uncleared items, and documents the process. Use when the user mentions bank reconciliation, transaction matching, reconciling accounts, GL cash balance not matching the bank, or asks about month-end reconciliation or corporate card reconciliation.

  • Agentmail lite

    fnord123/hermes-skills/agentmail-lite Skill

    2★ repo

    Manage an existing AgentMail inbox — read mail, send mail, reply, forward, organize via labels, and trash messages. Use when the user asks to check email, read a message, reply, send a new email, forward, search the inbox, trash/delete an email, mark a message read/unread, or organize via labels. Activate for any mention of agentmail.to or "@agentmail.to" or "the agent's inbox." This skill manages an inbox the user has already created; it does not create or delete inboxes.

  • Instagram search

    gaojiaze2025/instagram-search Skill

    no license2★

    Search Instagram for keywords, hashtags, accounts, topics, products, brands, campaigns, locations, or trends, then browse the newest visible image posts/carousels, save full visible images into the current workspace, and summarize findings. Use when the user asks to find, research, monitor, review, collect examples from, browse latest/recent Instagram image content, or save Instagram post images for a keyword or hashtag. Skips Reels/video content by default.

  • Web taste

    sonhaicoder/web-taste-skill/skills/web-taste Skill

    2★ repo

    Anti-slop web frontend skill — AUTO-TRIGGER mọi web UI task. Force ship Kimi/Lovable-tier quality bằng 3 luật cứng: (1) Turn 1 emit Discovery Form lock brief TRƯỚC khi gen pixel (cho task lớn) hoặc apply quality bar (cho tweak nhỏ), (2) Turn 2 pick 1 trong 5 visual directions deterministic (OKLch palette + font + posture) hoặc extract brand-spec — KHÔNG freestyle, (3) Turn 3+ TodoWrite plan → live updates → 27 anti-pattern checklist + 5-dim critique + quality tier scoring → ship single artifact. AUTO-TRIGGER khi: chạm file .tsx/.jsx/.ts/.vue/.svelte/.astro/.html/.css/.scss/.tailwind, hoặc user nói "build/sửa/render/design/tạo/refactor" + "page/landing/UI/component/storefront/admin/site/web/trang/giao diện/style/theme", hoặc "design như Kimi/Lovable/Linear/Stripe/Apple/Monocle/Vercel/Notion". Bao gồm: 9 references (directions/discovery-form/anti-slop/critique/design-md-format/quality-tiers/hero-patterns/section-blueprints/motion-recipes), 8 starter design systems (Kimi, Lovable, Linear, Stripe, Apple, Monocle, Brutalist, Datadog). Distilled từ open-design (24K stars), taste-skill, impeccable.style, getdesign.md, kimi.com, lovable.dev, huashu-design, guizang-ppt. KHÔNG dùng cho: mobile (Flutter/iOS/Android/RN — dùng mobile-design), backend (API/DB), config/infra (CI/env/docker).

    The same file is in 1 other repository

  • Ui arsenal

    umararshad4/skill-arsenal/ui-arsenal Skill

    2★ repo

    Premium component-library expert for React + Next.js + Tailwind. Knows shadcn/ui, Radix, HeroUI, Magic UI, Aceternity, ReactBits, 21st.dev, Tailwind UI, Cult UI, Tremor, Recharts, TanStack Table — their install paths, doc URLs, decision boundaries, and how to fetch live component source. Use when the user asks to add/build/install a UI component, section, block, hero, pricing, navbar, footer, form, chart, table, dashboard, bento, marquee, dock, animated background, or asks "which library should I use for X", "pull this component from Y", "find a top-tier component for Z", or wants to integrate components from any of the listed libraries.

  • Regulatory guard

    vllnt/skills/regulatory-guard Skill

    2★ repo

    Audit a website or web app for strict compliance with applicable legislation across four domains — privacy (GDPR, CCPA, ePrivacy), accessibility (WCAG 2.2 AA, ADA, EAA), consumer & e-commerce (DSA, DMA, CCPA-sale, CAN-SPAM), and AI / content (EU AI Act, copyright, DMCA). Produces a tiered compliance report with cited evidence, severity, and concrete remediation steps. Use when releasing publicly, expanding to a new jurisdiction, or hardening before a regulator inquiry.

  • Decision coach

    olzn/skills/skills/decision-coach Skill

    2★ repo

    Coach a real decision to a better outcome, or stress-test reasoning you've already formed, using the frameworks from Annie Duke (Thinking in Bets, How to Decide), Philip Tetlock (Superforecasting), and Shane Parrish's Great Mental Models. Use when explicitly invoked — "use decision-coach", "help me decide X", "stress-test my thinking on Y", "coach me through this choice", "what mental model applies here". Does NOT auto-activate on every mention of a choice; engage it deliberately.

  • Ab test engineer

    IrfanSadiqRahat/constellation/agents/ab-test-engineer Skill

    no license2★ repo

    Power analysis, ramp plan, SRM checks, sequential testing.

  • Advise agent orchestration skills

    the-long-ride/skill-master/skills/advise-agent-orchestration-skills Skill

    2★ repo

    Use when a human wants to design, evaluate, or improve AI agent skills for planning, routing, multi-agent collaboration, evaluators, handoffs, parallel work, task decomposition, or agent workflow control

  • Market research

    minqiyang/skills-from-scratch/examples/market-research Skill

    2★ repo

    Use this for repeatable market, competitor, company, product, or industry research tasks that require structured findings, source checking, and reusable research standards.

  • Agency automations

    Skryx-L-A/project-kit/skills/agency-automations Skill

    2★ repo

    Builds the RUNNING automations a local-business/agency actually delivers — speed-to-lead, database reactivation, reviews & referrals — wiring webhooks, SMS/email messaging, follow-up sequences, and booking into a live system. Project-kit sub-skill loaded by new-project routing, or composed by build-business, whenever the user wants to DELIVER and RUN automations (not just plan them). Defaults to n8n; can drop to a custom api-backend or an existing GHL-style SaaS. Compliance (TCPA, A2P 10DLC, CAN-SPAM, GDPR, Google review policy) is enforced, not optional.

  • Workflow

    Vironnimo/vbot/examples/extensions/workflow_command/skills/workflow Skill

    2★ repo

    Turn a stated objective into a concise execution sequence and carry it through.

  • Proven python

    shanwije/proven-python/skills/proven-python Skill

    2★ repo

    Python engineering-discipline guardrails for writing, refactoring, testing, and reviewing Python code. Enforces test-driven development, full type coverage, small readable functions, PEP 257 docstrings, configuration over hardcoding, deliberate design, and a green toolchain (ruff, mypy, pytest) before any task is treated as finished. Use this whenever you are about to write, change, debug, test, package, or review Python code, set up a Python project, or decide whether Python code is done, even if the user never says the words "best practices", "clean code", "TDD", "type hints", or "design patterns".

  • Recipe pr review

    shinpr/pr-review-skill/plugins/pr-review/skills/recipe-pr-review Skill

    2★ repo

    Reviews GitHub PRs with Claude Code or Codex reviewers on deterministic PR snapshots, repository quality criteria, and configurable posting. Use when asked to review a PR URL, re-review a PR, post PR comments, or create a PR review quality profile.

  • Research arena

    hanxinzhang/research-arena/.agents/skills/research-arena Skill

    2★ repo

    Use when the user wants to run or extend Research Arena, an LLM-native research community protocol with competing Researchers, an Integrity Checker, Referees, revision, and an Editor/Publisher decision. Trigger for agent-based research workflows, peer-review simulation, manuscript/revision rounds, OASIS demo runs, or adding new Researcher/Referee agents.

  • Codex dev native

    shengyy/agent-skills/skills/codex-dev-native Skill

    2★ repo

    Full loop for delegating development tasks to the OpenAI Codex CLI on the official Codex plugin's native codex-companion engine. Claude orchestrates (decompose, isolate, dispatch, accept, review, merge); codex only implements under a workspace-write sandbox where writes are confined to its cwd and network is on. The native engine owns launch / background / status / result / cancel / same-thread resume, so Claude never hand-rolls dispatch or reconnect. Use when the user says "delegate" / "hand it to codex" / "have codex implement|build <task>" / "fan out several codex tasks", or runs /codex-dev-native. This is the native-engine sibling of codex-dev (which runs on the omegacode engine) — prefer this one when the official codex plugin (codex@openai-codex) is installed. For review/consultation only use gstack-codex; for a bare one-off rescue with no acceptance/merge loop, the plugin's /codex:rescue is enough.

  • Api security

    pop123-ux/agent-security-skills/skills/api-security Skill

    2★ repo

    Production-grade security Agent Skills (SKILL.md) for Claude Code, Claude agents & OpenClaw: OWASP API Top 10 patterns + authentication/authorization patterns.

  • Audit gnadd

    AlexHagemeister/gnadd/skills/audit-gnadd Skill

    2★ repo

    Read-only GNADD alignment audit: load workflow principles, scrutinize context files for describe-vs-track violations, perform a shallow git/workflow check, and return a severity-grouped report with minimal proposed fixes. Nudges /new-issue-gnadd for remediation slices; never edits files or creates issues. Use when the user asks to audit GNADD alignment, review workflow hygiene, check project context files, or find describe-vs-track violations.

  • Agent finder

    realtyapi/realtyapi-skills/skills/agent-finder Skill

    2★ repo

    Use when the user wants to find or evaluate real estate agents in an area or for a property — search agents, pull their profile, recent listings/sales, and reviews, then return a vetted shortlist. Triggers on "find a realtor in …", "who are the top agents for …", "who listed this house", "best selling agents near …", "agent reviews for …".

  • Vensim skill

    1837620622/vensim-system-dynamics-skill/skills/vensim-skill Skill

    2★ repo

    Use when the user needs Vensim/system-dynamics CLD/SFD modeling, .mdl sketch audit/repair/layout, simulation, nodata diagnosis, scenario comparison, or charts for coursework, policy, management, population, or supply-chain models.

  • Superdesign

    enisakarsu/all-design-skills-for-vibecoder/skills/superdesign Skill

    no license2★ repo

    SuperDesign CLI ile UI tasarımları üret ve iterasyonla geliştir. Mevcut bir sayfayı/component'i yeniden tasarlarken, yeni sayfa tasarımı oluştururken, tasarım varyasyonları üretirken veya kullanıcı 'superdesign' dediğinde kullan. Önce SuperDesign'de tasarım üretir, kullanıcı onayından sonra kod yazar.

  • Tech route maker

    Stephen-studying/tech-route-maker Skill

    2★

    Create evidence-grounded editable technical route diagrams for research and engineering projects. Use when the user asks to draw, generate, visualize, render, export, or revise a technical route diagram, research route, paper method framework, publication figure, thesis proposal route, engineering system route, software or agent workflow, pipeline, architecture roadmap, process diagram, editable PPTX/SVG/Draw.io/Mermaid/HTML diagram, or copyable Draw.io XML code. Supports implicit invocation when the user asks for route diagrams and explicit invocation with $tech-route-maker.

  • A11y

    tufantunc/review-pro/core/skills/a11y Skill

    2★ repo

    Accessibility audit of changed UI code: semantic HTML, ARIA correctness, focus management, keyboard support, contrast, name/role/value. Conditionally dispatched when the diff touches interactive UI. Use for accessibility review, a11y, ARIA, focus or keyboard-nav audit of a diff.

  • Instagram clone

    ImYourBoyRoy/Portable_Web_toolkit/skills/instagram-clone Skill

    2★ repo

    Clones a public Instagram profile into feed.json and local media for Astro portfolio sites. Use when building Instagram galleries without Meta API tokens, setting INSTAGRAM_USERNAME, seeding static fallbacks, refreshing after 429 rate limits, or auditing feed.json.

  • Ad creative analysis

    fjilvvi/growthlens/skills/ad-creative-analysis Skill

    2★ repo

    Break down ad creatives (image, video, or copy) into hook, angle, awareness level, offer, format, and persuasion devices, then judge what's working and how to improve or remix them. Use when the user shares an ad, an ad-library link, or competitor creatives and asks to "analyze this ad", "break down the creative", "what's the angle/hook", "why does this ad work", or "give me variations to test".

  • Data engineering discipline

    grimaldost/craft-collection/plugins/engineering-discipline/skills/data-engineering-discipline Skill

    2★ repo

    Discipline guardrails for data-engineering work with downstream consumers — activate at the START of the task, before writing code, because silent semantic drift is the dominant risk. Activate on: migrating or porting a pipeline (e.g. "migrate this Spark pipeline to the new warehouse"), refactoring a transform, backfilling or replaying history, evolving a schema (add / rename / retype / drop a column), creating a new dataset — or a metadata / catalog / lineage emitter whose output a separate tool loads — that has consumers, designing or reviewing a data contract, reshaping a tool / API response payload a client depends on, writing tests for a pipeline, generating pipeline code with an LLM, and investigating a consumed dataset that misbehaves — "the numbers changed / look different", or a table/extract that "ran but didn't update / is stale / isn't refreshing / the watermark didn't advance". The test for activation: could this change the columns, dtypes, row or group cardinality, null behavior, semantics, or freshness of a dataset — or the fields, types, or closed vocabularies of a tool/API payload — that something or someone else reads? If so, this skill applies — pin the contract, verify the observable source, and check parity on real data. Do NOT activate for pure exploratory analysis with no downstream consumer, throwaway notebooks, or non-data software work.

  • Composer dependency triage

    ArtemProshkovskiy/laravel-maintenance-skills/skills/composer-dependency-triage Skill

    2★ repo

    Laravel-native dependency triage advisor. Turns `composer outdated` and `composer audit` output into a prioritized, advise-only ACTION PLAN — and, crucially, recommends maintained REPLACEMENTS for abandoned packages, the case where Composer itself usually just prints "No replacement was suggested". Use when the user wants to audit Composer dependencies, decide what to update, find abandoned or vulnerable packages, or check dependencies before a Laravel upgrade — e.g. "audit my composer dependencies", "what should I update", "are any of my packages abandoned", "is it safe to bump this", "triage dependencies before upgrading Laravel". Reads composer.json / composer.lock and real tool JSON as ground truth (never invents versions or CVEs), focuses on DIRECT dependencies, checks PHP/Laravel compatibility before recommending majors, and emits a Do-now / Do-carefully / Defer plan. Advise-only: never edits files.

  • Company investment research skill

    bingofreedom/company-investment-research-skill Skill

    2★

    Analyze a company, stock, business line, industry position, moat, long-term competitiveness, financial quality, valuation, peer comparison, competitive attack paths, bear cases, pre-mortems, and long-term tracking indicators. Use for evidence-based company research in Codex or Claude Code. Do not use for direct buy/sell recommendations, position sizing, or technical-chart trading calls.

  • Mm atlassian design

    m2kky/mm-design-systems/skills/mm-atlassian-design Skill

    2★ repo

    MM Design Systems premium package for Atlassian Design System principles for spacing, typography, color, and layout to guide all UI and design decisions.

  • Accessibility gate

    logicleap-labs/claude-plugins/plugins/accessibility-gate/skills/accessibility-gate Skill

    2★ repo

    Use before declaring a UI change done, fixed, working, ready, or shipped. Forces a real accessibility pass across keyboard flow, focus visibility, accessible names, contrast, reduced motion, and the platform's native semantics.

  • Curry skills

    shuhaolin63-hash/curry_skills Skill

    2★

    库里投篮技术训练体系。Invoke when user asks about Curry shooting technique, One Motion, shooting form, Brandon Payne training, or wants to learn/improve shooting skills.

  • Dowsing

    raphaelxie/dowsing Skill

    2★

    梅花易数失物占(Lost Item Divination)专用技能。当用户丢失物品、找不到东西、宠物走失、请求失物占时使用。触发词:失物、丢了、不见了、找不到、失物占、找东西、走失、宠物、lost item、dowsing、寻物。

  • Skill navigator

    fxyadela/skill-navigator Skill

    2★

    Use this skill when the user is unsure which local Codex skill to use, asks for skill recommendations, wants a guided route through available skills, or wants to turn a vague task into the right skill invocation. It maps the user's task to one or more installed skills and gives a copy-ready next prompt.

  • Qa testing kit

    SoftwareOneHN/qa-testing-kit Skill

    2★

    Comprehensive QA Testing Kit for Manual & Automation Testing — supports Playwright, Selenium, Appium. Generates test cases, automation scripts, stable locators, test data, and analyzes flaky tests. Use when the user mentions: testing, QA, automation, playwright, selenium, appium, test cases, manual testing, locator, page object, test data, flaky tests, API testing, RBT, framework, testng, jira, xray, or asks to generate/run/fix tests.

  • Atlas agent

    wpfbcr/AtlasAgent/skills/atlas-agent Skill

    2★ repo

    Plans global travel itineraries with multi-plan comparison, day-by-day schedules, multi-currency budgets, visa/diet/transport guidance, and PDF export. Use when the user asks for trip planning, vacation itinerary, travel guide, 行程规划, 旅游攻略, or holiday planning for any destination worldwide.

  • Shop scout

    prikotov/shop-scout Skill

    2★

    Мини-исследование закупки — найти товар на российских маркетплейсах (Ozon, Wildberries, Yandex.Market), сравнить цены/рейтинги/отзывы, отсеять мусорные отзывы и подозрения на подделку, выбрать самый дешёвый оригинал и самый рекомендуемый (баланс цена/качество). Использовать, когда пользователь просит «найти подешевле», «сравнить цены», «где купить», «стоит ли брать», «не подделка ли» для конкретного товара. Результат — CSV + Markdown-отчёт в папку проекта.

  • Consumer dispute assistant

    JerryNee/consumer-dispute-agent-skill/skills/consumer-dispute-assistant Skill

    2★ repo

    Build consumer dispute case packs for refunds, billing errors, subscription cancellation failures, duplicate or unauthorized charges, ecommerce/service complaints, chargeback preparation, and complaint escalation. Use when a user wants an agent to organize evidence, draft merchant support messages, prepare payment dispute statements, create regulator/BBB/state attorney general complaint drafts, or plan safe follow-up workflows. Do not use for legal advice, court representation, fabricated evidence, harassment, threats, or autonomous filing/sending without explicit user confirmation.

  • Api design

    piyushzala158/agent-skills/api-design Skill

    2★ repo

    Design, review, and refactor HTTP APIs. Use when Codex works on REST endpoints, resources, HTTP methods, status codes, error response formats, pagination, filtering, idempotency, versioning, authentication boundaries, or API consistency across services.

  • Autoskills

    B143KC47/autoskills Skill

    2★

    Use when the user asks "what skill should I use for X", "find a skill for X", or "is there a skill that can...", asks to search online for skills, points at a repo/folder and asks which skills apply, is starting a problem (research, fine-tuning, evaluation, deployment, UI, debugging, etc.) where an existing skill could help, or is finishing work in which a recommended skill was used (to record whether it helped).

  • Agent collaboration protocol

    agi-connect/agent-collaboration-protocol/skills/agent-collaboration-protocol Skill

    2★ repo

    Use when coordinating multiple AI agents, coding assistants, teams, repos, or users through a vendor-neutral shared filesystem protocol. ACP schema v2 requires protocol.json, events.jsonl, proposal.md, review.md, decisions.md, readiness.md, conclusion.md, a declared Markdown primary deliverable under deliverables/, deliverable lifecycle events, strict phases, readiness gates, SHA-256 freeze checks, and validator checks.

  • Examples

    Arakiss/galdr/examples Skill

    2★ repo

    Summarize a git repository's recent changes and write them to a Markdown file. Use it when asked for a «change summary», «quick changelog», «what changed in the repo», or to dump git state to a file. Parameters: the repository and the output path.

  • Skill 01 wallet management

    vaquarkhan/web3-agent-skills/skills/skill-01-wallet-management Skill

    2★ repo

    Manages Web3 wallets including HD derivation, ERC-4337 account abstraction, multi-sig (Safe), and social recovery. Use when creating wallets, signing transactions, managing keys, or configuring smart accounts.

  • Skillopt skill writer

    Waylish/skillopt-skill-writer Skill

    2★

    Create, improve, and validate agent skills using a SkillOpt-inspired workflow: scored evidence, bounded add/delete/replace edits, validation gates, rejected-edit memory, and compact deployable SKILL.md artifacts. Trigger when the user says "write a skill", "create a Codex skill", "make a Claude skill", "turn this workflow into a skill", "optimize this skill", "improve SKILL.md", "skill quality", "best_skill.md", "use SkillOpt", "validation-gated skill", "write a skill for writing skills", "写skill", "创建Codex技能", "优化技能", "技能文档", "写一个 skill", "把流程变成skill", or provides a repeatable workflow that should become a reusable agent procedure.

  • Arca comprobantes

    buanzo/agentic-skill-arca-comprobantes/skills/arca-comprobantes Skill

    2★ repo

    Usar para flujos ARCA/AFIP RCEL de comprobantes en Argentina: emitir facturas, notas de crédito de cancelación, descargar emitidas, indexar, buscar, validar y vincular con skills bancarios.

  • Git attribution

    bcmyguest/assisted-by/skills/git-attribution Skill

    no license2★ repo

    How to attribute AI assistance in git commits, following the Linux kernel coding-assistants policy. Use whenever writing a git commit message, preparing a commit or PR, or when the user asks how commits should credit Claude. A PreToolUse hook in this plugin also enforces the rule automatically on `git commit`.

  • Api and interface design

    codexskills/agent-forge/skills/api-and-interface-design Skill

    no license2★ repo

    Design stable, evolvable APIs and interfaces using contract-first methodology, rigorous boundary validation, and versioning strategies that respect Hyrum's Law.

  • Cka drill

    nmdra/cka-lab/.agents/skills/cka-drill Skill

    no license2★ repo

    CKA Drill — Socratic exam proctor and cluster-state grader for Certified Kubernetes Administrator (CKA) practice. Use this skill when the user asks for a practice question, drill, grill me, test me, exam scenario, or wants to be quizzed on any CKA topic (RBAC, ETCD, Networking, Storage, Upgrades, Troubleshooting, Gateway API, Workloads). Also triggers on phrases like "give me a scenario", "test my knowledge on X", "CKA practice", "score my answer", or "did I do this correctly". This skill runs timed Socratic drills and objectively grades cluster state — do NOT use cka-neko for this.

  • Api contract review

    tunahanaliozturk/secure-dotnet-skills/skills/api-contract-review Skill

    2★ repo

    Use when reviewing the design of a REST/HTTP API in ASP.NET Core — resource modeling, status codes, error shape, idempotency, versioning, pagination, and OpenAPI accuracy — before it ships.

  • Triathlon coach

    HenrikBrehm/triathlon-coach-skill/skills/triathlon-coach Skill

    2★ repo

    Analyzes triathlon and endurance training data pulled from connected fitness MCP servers (Garmin, Strava, Coros, Polar, Suunto, Wahoo, Whoop, Oura, intervals.icu, TrainingPeaks, Fitbit) and produces an evidence-based training report with next-session and block recommendations. Use when the user asks about triathlon, training analysis, 'how is my fitness' or 'how is my form', 'what should I train today', a weekly training report, swim/bike/run volume or balance, race preparation, or Garmin/Strava/Coros data analysis. Also use for German requests such as 'Formstand', 'Trainingsanalyse', 'was soll ich heute trainieren', or 'Wochenbericht'. Computes CTL/ATL/TSB, ACWR, monotony, intensity distribution, and recovery status deterministically via a bundled script, reports in the user's conversation language, names every data gap, and applies hard safety guardrails.

  • Pm skill

    LechuanWANG/pm-skill/pm-skill Skill

    no license2★ repo

    PM-first delivery style for AI products. Use when Codex is building, iterating, reviewing, or explaining AI-backed products in the user's PM style, especially API-backed products, Agent workflows, Harness design, prompt/context architecture, product UI, technical architecture, feature iteration, GitHub prototype research, or project-local LLM Wiki knowledge maintenance.

  • Loop engineering

    VioletScar-Hui/Build_Great_Loop/loop-engineering Skill

    2★ repo

    Author a NEW, ready-to-run prompt or harness for a long-running iterative agent after its goal and load-bearing decisions are settled. Use for iterate-until-passing, multi-session, self-verifying, research, coding, or bulk processing loops that need state, stop conditions, and recovery. If intent is still unsettled, use loop-spec first. If a harness already exists and the user wants it improved or diagnosed, use loop-review first. Use loop-eval for test design, loop-ops for scheduling/unattended operation, and loop-retro after a real run. The deliverable is the smallest sufficient paste-ready harness, not the task itself. Trigger only when the user explicitly wants a reusable loop prompt/harness; direct requests to fix, run, or iterate on the task itself are ordinary execution. Requests that include actual scheduling/operation are led by loop-ops; when called by loop-ops, return only the per-run prompt.

  • Dify agent builder

    xxzxzmai-droid/dify-builder-skills/dify-agent-builder Skill

    no license2★ repo

    Build a ready-to-import Dify Chatflow agent (a .yml DSL file) from a plain-language request. Use this whenever the user wants to create, build, design, or generate a Dify agent / chatbot / 智能体 / 工作流 / chatflow / DSL — e.g. "做一个能查知识库回答制度问题的Dify智能体", "帮我生成一个上传文档就分析的助手", "build me a Dify customer-service bot that calls an HTTP API", "make a multimodal agent that reads images". Trigger even when the user does not say the word "DSL" or "yml" — any request to produce a usable Dify agent counts. The skill designs a structured blueprint and runs a deterministic engine to emit valid Dify 0.3.0 Chatflow YAML the user can import directly.