Loading…
Showing 10051–10080 of 10089 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| google-shoppingmanifoldmcp/marketing-skillsWhen the user sells products online and wants them found on Google Shopping and free listings, in AI Mode and AI Overviews product results, or in ChatGPT, Gemini and Perplexity shopping answers. Holds dated, sourced findings a model lacks (ChatGPT took most product picks from merchant feeds from July 2026 and dropped Instant Checkout, Google removed free listings from European search in September 2026 and turned native checkout on by default for Shopify stores, the review floors for stars, the 2026 feed attributes) and how to read live Shopping prices, sellers and reviews. Also use when the user mentions Google Shopping, Merchant Center, a product feed, free listings, price comparison, who sells our product cheaper, price competitiveness, product reviews or star ratings, seller ratings, product structured data, ChatGPT shopping, the Agentic Commerce Protocol, UCP, agentic checkout, or a Shopping plan. Amazon goes to amazon, bids and campaigns to paid-ads, brand answers in AI to ai-search, web rankings to seo. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| manifold-get-startedmanifoldmcp/marketing-skillsWhen the user is new to the Manifold marketing skills, asks where to start, or wants to set up or update the context every other skill reads first. Writes .agents/product-marketing.md (the business type, what it sells, the customers, competitors, positioning, customer language, proof, goals, accounts and what to track) for any kind of business, from B2B software to a shop, a local service, an app, a creator or a nonprofit, drafting from the site and asking only for the gaps. Then recommends the two or three skills that fit the goal, and the first job to do in each, with what it costs. Also use when the user mentions getting started, I just installed this, which skill should I use, what can Manifold do, product or marketing context, describe my business, ICP, target audience, brand voice, or update our context after a pivot, a new competitor or a price change. A growth plan built on real data goes to growth-strategy. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| cross-reviewcoder-xieshijie/dev-skillsCross-reviews an existing change (MR/PR, branch or commit range) with two independent reviewers, a fresh subagent and a model from another family through its CLI, who then cross-examine each other's findings; you settle one ledger and fix the confirmed findings when asked. Use when the user asks for a cross review (交叉 review, 交叉审查) of a change. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| plan-for-agentscoder-xieshijie/dev-skillsCreates, revises or checks a complete plan for agents to execute, turning requirements and confirmed decisions into an approach, steps, outputs and acceptance evidence. Use for implementation, research, content creation, data processing and similar tasks. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| wx-miniapp-wmpfxegeng/wx-miniapp-skills微信小程序(PC 端) WMPF 自动化调试与安全评估工具链的搭建、使用与 AI 自动化渗透。覆盖「偏移自动提取 → Frida 注入 → CDP 代理 → DevTools 调试 → e0e1-wx 自动化扫描 → MCP 工具链 → AI 渗透」,集成 WMPFDebugger + e0e1-wx + wmpf-offset-adaptation + miniapp-cdp-mcp。当任务涉及"对已授权微信小程序做自动化测试/强开 F12/CDP 调试/反编译抓接口/微信版本更新后取偏移/用 MCP 让 AI 做自动化渗透(抓接口、扫密钥、断点逆向加密)"时使用。关键约束:必须是 Node 20 LTS + frida 锁 @16.6.6,否则 NODE_MODULE_VERSION/ESM 不兼容;MCP 侧必须 pin mcp<2(FastMCP 兼容)。 | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| fetchseokhoonj/krx-openapiFetch one day of KRX market data from the KRX Open API, by the same readable names the Python client uses. Holds no logic of its own -- it calls the krx-openapi package's CLI (`krx fetch <group> <name> <date>`) and shows the result to the user. Needs a group + method (find them with the list skill) and a trade date. Trigger phrases: KRX 시세 가져와, KRX 일별 데이터, 코스피 전종목 시세, KRX 지수 조회, 국채 시세, fetch KRX data, KRX daily prices, KOSPI stocks on a date, KRX index for. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| listseokhoonj/krx-openapiList the KRX Open API's services -- the groups and the readable method names each is called by -- offline and without a key. Holds no logic of its own -- it calls the krx-openapi package's CLI (`krx list`) and shows the result to the user. Use this to turn a concept (코스피 지수, 국채) into the `group name` pair the fetch skill needs. Trigger phrases: KRX 서비스 목록, 무슨 KRX 데이터 있어, KRX 뭐 조회 가능, list KRX services, what KRX data is there, KRX groups and methods. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| dagx-agi-kerneldankofly/perfectifyImprove and verify agent work after repeated failures, in dependency-heavy tasks, or when optimization claims need baseline and regression evidence. Use for DAGx/Perfectify requests, failed retries, risky multi-step work, or requests to verify an improvement. Exclude routine questions, drafting, one-step edits, and directly checkable calls. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| wildberries-mcpilyautov/wildberries-mcp-ruПодключить Wildberries к ИИ-ассистенту и работать с кабинетом продавца прямо из чата. Ставит MCP-сервер `wildberries-mcp-ru`: 307 методов официального API, каталог ищется обычными словами, у каждого метода класс доступа, запись требует подтверждения. Используй, когда человек хочет автоматизировать работу с кабинетом, собрать аналитику по продажам или разобраться с API. Триггеры: «подключи wildberries», «api wildberries», «вб через api», «выгрузи продажи с вб», «остатки на wildberries», «карточки wb», «wildberries mcp». | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| llm-handoverAximande/agent-skillsHandover prêt à copier-coller pour passer la main d'une conversation LLM à un autre LLM ou agent (Codex, Cursor, ChatGPT, Gemini, session Claude fraîche) : état + intention + décisions + prochaine action, vérifié par un agent frais qui ne voit que le handover. Deux modes : repo (le destinataire a le clone) et standalone (chat sans accès fichiers). Use when: « prépare un handover / handoff », « je passe sur X », fin de session à continuer ailleurs, ou /llm-handover. Uniquement sur demande explicite. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| spec-liteAximande/agent-skillsUne page de critères d'acceptation avant de vibecoder — spec-kit compressé à la seule étape « specify », moteur grilling. Chaque critère est observable et formulé pour que proof-run l'exécute tel quel ; la spec est vérifiée par un agent frais qui ne voit qu'elle, puis vit dans le repo (table d'état remplie au proof-run, relue par ship-check). Use when: « fais une spec », « qu'est-ce qu'on construit exactement ? », avant de démarrer un projet ou une feature vibecodée, ou /spec-lite. Uniquement sur demande explicite. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| elutiongdonninelli/elutionRun a timer-bound research loop with subagents, BM25 memory, and Yukon measuring. Use for optimization work that iterates until a deadline. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| sample-skillSdinzsh/PowerHou53Template procedural skill demonstrating agentskills.io standard and Powerhouse 3 progressive disclosure loading. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| gpt-series-reasoning-styleJadeYingWah/gpt-series-reasoning-style交付验收与多智能体协作纪律(防假完成)。Use when 涉及数字验算、代码交付、多Agent协作、需要防假完成的任务;or when user says "做完了帮我查/看看对不对/验收"、派发子任务或多个AI分工。约束交付是否真实,不单独设定创意质量满意标准(见 DISCIPLINE 完成档位 C1/C2)。小改/一句话问答不加载。 | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| caveman-statsGktuOktay/autonomous-agencyShow real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| cavecrewGktuOktay/autonomous-agencyDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output". | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| forwardniharnm/grok-bridgeSend a user-authorized, scoped task from Codex, Claude Code, Cursor, Antigravity, or Muse Code to a specific Grok Bot and inspect its result. Use when the user asks for Grok Bot delegation. Requires the separately installed grok-bridge and community gbot CLIs. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| runniharnm/grok-bridgeDelegate a bounded task to Codex, Claude Code, Cursor, Antigravity, or Muse Code on the current execution host through grok-bridge. Use when the user asks another coding CLI to review or implement work. Requires the chosen CLI, its login, and an explicit repository path on that host. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| grok-bridgeniharnm/grok-bridgeDelegate a user-authorized task between Grok Bot and Codex, Claude Code, Cursor, Antigravity, or Muse Code through the shared Grok Bridge CLI, then verify the result and continue. Use for an explicit cross-agent handoff, not Grok Build or ordinary xAI API requests. Requires separate CLI installation and destination access. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsMane087/skill-routerUse when two or more independent tasks can run without shared state or sequential dependencies. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| writing-skillsMane087/skill-routerUse when creating a new skill, editing an existing one, or verifying that a skill works. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| minimalMane087/skill-routerThe smallest manifest a skill can declare. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| myceliumoliverweissl/context-gardenDecide whether to spawn subagents (one, or several in parallel) to search, investigate or edit, and brief them well; passes finding notes between agents so they don't redo the same exploration. Use before delegating to an agent and after an agent reports findings. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| seedbankoliverweissl/context-gardenMaintain a small, generated AGENTS.md of repository facts (build commands, conventions, invariants, past mistakes) that were rediscovered often or were costly to get wrong. Use at task start to check cached facts, and at task end to log and promote what you had to dig for. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| weederoliverweissl/context-gardenMeasure and reduce a Skill's token footprint (always-loaded description + on-trigger SKILL.md body) without regressing routing accuracy or losing instructions. Use when a SKILL.md feels oversized, repeats rules, or has a vague description that might mis-route. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| dsh-preset-authoringhackerFish/awesome-dsh-skillsAuthor or edit a DeepSeek Harness agent preset (agent.cordis.yml + optional preset.yml) with verified row structure, id rules, install location, and validation against a real harness install. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| dsh-skill-adapterhackerFish/awesome-dsh-skillsConvert a public portable SKILL.md into a DSH-compatible skill with verified discovery paths, tool mapping, provenance checks, and safe fallbacks. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| concise0xyph3r/CONCISECuts prose filler from agent responses - trailing summaries, restated context, hedging, over-long preambles, oversized code comments - while leaving code logic, analysis depth, and correctness fully intact. Use when the user says "be concise", "concise mode", "cut the fluff", "stop summarizing", "less filler", or asks for shorter responses. Works on any Agent Skills compatible tool (Claude Code, Cursor, Copilot, Codex, Gemini CLI, and others) - installed via `npx skills add 0xyph3r/CONCISE`. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| __SKILL_NAME__dse120071750/m8m-harness-builderM8M 3.1 product skill whose closed native source compiles into a displayable, executable milestone workflow. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |
| m8m-mcp-connection-builderdse120071750/m8m-harness-builderAuthor reusable MCP connection context and usage guides locally, then deliver an authorized installation to the configured M8M tenant's persistent server installer. Use for new connections or explicit version changes. | Stars: 5 | Updated | Claude CodeCodex | Unverified | Install |