agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Prove first

    alessiomarcone/no-patch/plugins/no-patch/skills/prove-first Skill

    0★ repo

    Verify a reported coding issue before modifying the repository, then classify the result as confirmed, partial, no-patch, or blocked. Use for bug fixes, regressions, failing tests, performance or security claims, stale issues, and refactors justified as fixes. Do not use as a gate for explicit mechanical edits whose requested outcome does not depend on reproducing a defect.

  • Guhwoo

    partyfly/guhwoo Skill

    0★

    Drive the user's guhwoo cloud draft (a motion-rich web page / web artifact) from this agent via the `guhwoo` CLI. Use whenever the user wants to create a guhwoo draft from a local `.html`, open a draft in the editor, push code changes to a draft, or pull back what they changed visually, or references what they're looking at in the guhwoo editor ("the page I'm editing", "what I just changed", "this draft/hero/section", "make this…"). guhwoo is the visual editor (your eyes + the user's hands); you write the HTML. Also triggers on "create/open a guhwoo draft", "upload this page to guhwoo".

  • Code change impact audit

    RSXLX/code-change-impact-audit Skill

    no license0★

    Audit the full impact of feature work, bug fixes, and refactors across frontend, backend, mobile, APIs, databases, state, jobs, queues, CLI tools, native code, infrastructure, configuration, build, deployment, and localization. Use before implementation, during implementation, in code review, and before claiming completion whenever a code or contract change may affect more than the visible symptom. Discover and classify every direct and indirect consumer, then choose the smallest complete root-cause fix by reusing existing code and platform capabilities while avoiding speculative abstractions, dependencies, scaffolding, and unrelated edits. Verify affected behavior and report evidence and residual risk.

  • Optimize agent context

    Offwhite-Del/contextlean/plugins/contextlean/skills/optimize-agent-context Skill

    0★ repo

    Audit, benchmark, and safely optimize local AI Agent context, instructions, Skills, Context Packs, plugins, hooks, and cross-vendor configuration. Use when ChatGPT/Codex, Claude Code, or another CLI Agent starts with excessive or stale context, routes Skills poorly, repeats tool work, has conflicting rules, or needs evidence-backed before/after optimization with rollback. Do not use for ordinary code edits, model/provider tuning, or unsupported speed claims.

  • Fable

    mike-ai-de/fable-workflow-kit/skills/claude/fable Skill

    0★ repo

    Applies a Fable-style output optimizer for complex coding, writing, research, analysis, planning, and prompt engineering. Use when the user invokes /fable or asks for maximum quality from weaker models, rigorous reasoning, stronger prompts, verification, source discipline, or a structured high-output workflow.

  • Slide studio

    diegog956/slide-studio-suite/plugins/slide-studio-suite/skills/slide-studio Skill

    0★ repo

    Transform rough, unattractive, or incomplete PowerPoint decks into premium academic presentations for live talks, classes, and courses while preserving supplied text, images, data, citations, and meaning. Use when Codex must redesign or create a PPT/PPTX, research and apply a high-quality web template, audit or humanize slide copy, improve low-resolution assets, restructure the narrative, add purposeful PowerPoint transitions and click animations, or iterate an editable canonical deck without cluttering outputs.

  • Codex doctor

    sherlockGH-coder/codex-doctor/plugins/codex-doctor/skills/codex-doctor Skill

    no license0★ repo

    Audit and improve a Codex installation or project configuration. Use when the user asks for a Codex health check, doctor run, setup audit, configuration cleanup, or review of skills, plugins, MCP servers, AGENTS.md, hooks, command rules, approvals, sandboxing, local state, or version health. Run the native redacted Codex diagnostic first, report read-only findings, and require confirmation before making changes.

  • Blog engine

    dranshrad/groundledger/skills/blog-engine Skill

    0★ repo

    Groundledger long-form skill: CLEAR rubric, claim ledgers, adversarial Q-tests, grounding law (no fabricated stats), YMYL, Ship Scan, Cite Surface Audit, Freshness Drift, Graph Runner, Locale Lattice, Release Latch. Use for blog drafts, rewrites, SEO audits, citation checks, clusters, multilingual plans, or publish readiness on Claude Code, Cursor, or Cowork.

  • Orchestrating terminal agents

    frederico-kluser/orchestrating-terminal-agents Skill

    0★

    Controla o emulador de terminal kitty por script para orquestrar trabalho em paralelo — abre N abas dinamicamente, roda comandos nelas, digita em TUIs interativas, manda teclas especiais (Shift+Tab, ESC, Ctrl+C) e lê a tela de volta; e, em cima disso, dispara N agentes de código, cada um na sua git worktree e na sua aba, sabe quando cada um terminou (hook Stop → barreira) e dispara a wave seguinte nas mesmas abas, até a limpeza das worktrees. Use quando o pedido envolver "abrir N abas", "rodar X em paralelo", "vários agentes ao mesmo tempo", "uma worktree para cada", "digitar isso naquela aba", "mandar Shift+Tab/ESC para o Claude Code", "avise quando todos terminarem", "quando acabar, mande eles commitarem", ou automatizar qualquer TUI que não tenha flag de linha de comando equivalente. NÃO use para rodar um comando único e pegar a saída (Bash resolve), nem para multiplexar sessões que precisem sobreviver ao terminal (isso é tmux).

  • Exportdou agent tools

    kenny-shaw/exportdou-agent-tools Skill

    0★

    导出公开抖音视频的一级评论和可选回复到 CSV 或 Excel,查看视频信息与评论数量,预览评论用于用户反馈、舆情、选题或市场分析,并管理可恢复的异步导出任务。用户要求提取、导出、采集、下载、查看、总结或分析抖音评论、评论回复、用户反馈,或提供 Douyin 视频公开链接与分享文案时使用。

  • Fupeirong digital iching skill

    pnedfff/fupeirong-digital-iching-skill Skill

    0★

    Cast and interpret a Fu Peirong-style I Ching digital hexagram from three user-chosen three-digit numbers, using a deterministic calculator and a complete Chinese 64-hexagram/384-line database. Use when the user explicitly asks for 傅佩荣数字卦占卜、傅佩荣数字卦、数字卦占卜、三组三位数起卦、按数字问卦/解卦, or supplies three three-digit numbers for this method. Do not trigger for general I Ching history, unrelated numerology, or divination methods such as 梅花易数、铜钱卦、蓍草卦 unless the user explicitly wants this Fu Peirong method.

  • Pm

    jpoindexter/product-management-skills/skills/pm Skill

    0★ repo

    Route product-management work to the smallest relevant set of operational PM skills. Use when the user invokes /pm, asks a broad or ambiguous product question, needs help choosing a PM method, or requests discovery, strategy, positioning, pricing, metrics, experiments, prioritization, roadmaps, requirements, launch, stakeholder, AI-product, or product-review work.

  • Yoto icon maker

    sapochat/yoto-icon-maker Skill

    0★

    Use when creating custom track or chapter icons for Yoto Player or Yoto Mini. Explore a silhouette, rebuild it on a true 16x16 grid, preview it on black, and validate the upload-ready PNG.

  • Kickstart

    n02b3rt/Agent-Build-Kit/skills/kickstart Skill

    0★ repo

    Set up a new software project on solid foundations and keep it clean as it grows: git from the first minute (repo, branches, commit convention), a CLAUDE.md project constitution, a living architecture map of "where things live", a docs/ structure, and healthy-growth rules — so the project doesn't turn into a colossus on clay feet. Use THIS skill when the user: starts a new project / repo, says "nowy projekt", "zacznijmy projekt", "init", "setup projektu", "kickstart", "szkielet projektu", "scaffold a project", "boilerplate", "załóż repo", "new project", "set up a repo", "let's build this for real", "move from PoC to a real project", or starts coding something meant to live longer than one mock. It also configures a fixed repository language (kills "Ponglish") and removes any AI/tool authorship from commits and docs. This is NOT for one-off PoCs (use the `poc` skill) — it's for real, growing projects.

  • Cowsay

    kodexArg/cowsay/skills/cowsay Skill

    0★ repo

    Deterministic cowsay for AI agents (kodexArg). Renders replies through a bundled Python stdlib bin/cowsay with terminal-aware wrap and swappable ASCII art. Use when the user runs /cowsay, asks for cowsay mode, cowthink, modo vaca, change the cow, or switches art with /cowsay tux (or any stem from cowsay -l). Apply persistent switches with --set-cow.

  • Appnz hosting

    lee101/appnz-agent-skills/skills/appnz-hosting Skill

    0★ repo

    Deploy and operate open-source projects on app.nz. Use when an agent needs to publish a static site or server app, create or validate appnz.yaml, deploy an open model as a scale-to-zero Cog or RunPod worker, launch a cloud coding agent, connect the app.nz MCP server, or call the OpenAI-compatible model gateway with APP_API_KEY.

  • Codex project organizer

    GleckusZeroFive/codex-project-organizer Skill

    0★

    Audit and organize a local software workspace for reliable Codex use: AGENTS.md discovery, instruction ownership, project live state, global versus project skills/MCP/hooks, Git boundaries, custom parent/subagent roles, cross-agent handoff, and cold-start or compaction recovery. Use when initializing a project for Codex, cleaning up scattered agent rules or memory, diagnosing lost global instructions/skills/MCP, adding or repairing AGENTS.md, configuring subagents, or preparing a repo/workspace for repeatable work across sessions.

  • Engineering ownership

    GangWooLee/engineering-ownership/plugins/engineering-ownership/skills/engineering-ownership Skill

    0★ repo

    Use when someone is changing software they will have to live with, and the reasoning would otherwise survive only in this conversation. Covers setting up an engineering process in a repository that has none, starting work whose design is expensive to reverse, picking up work another person left unfinished, deciding whether a change is ready to merge, handing work over, and recovering why an existing decision was made before overturning it. Trigger on phrasings like 'set this repo up properly', 'take this over', 'continue the previous work', 'is this ready to merge', 'hand this off', 'why was it built this way' - and on the situation itself even when the user does not ask for process: a repository with no engineering setup, an unfinished diff, an .engineering/contract.json, or a decision record the requested change would contradict. Consult it before writing the code, not after. For diagnosing a single failure, a debugging skill fits better.

  • Capability scout

    misty1999sd/capability-scout Skill

    0★

    Discover and select the best matching skill, plugin, MCP server, library, template, or complete open-source project for the current workspace problem. Use GitHub and open-source evidence, inspect compatibility and safety, then propose or perform a gated installation or isolated reference archive.

  • Ai support radar

    butevecom-commits/ai-support-radar Skill

    no license0★

    Discover AI-startup support in China by city/region — subsidies, compute/model/corpus vouchers (算力券/训力券/模型券/语料券), AI industrial parks, incubators, free workspaces, talent, financing, and scenario opportunities. Queries a local verified knowledge base; every answer cites official sources, verification status, and next steps. Cross-runtime — works in Claude Code, OpenAI Codex, WorkBuddy and any agent that reads Markdown and runs Python.

  • Leetcode java coach

    ethan-2937/leetcode-java-learning-vault/.agents/skills/leetcode-java-coach Skill

    0★ repo

    Coach Java learners through LeetCode and foundational algorithm practice with diagnostic teaching, progressive hints, student-written code, compilation and tests, mastery tracking, and spaced review. Use when a learner asks to study algorithms, continue a Hot 100 plan, debug their own solution without receiving the answer, review due problems, assess mastery, or maintain progress in the accompanying Obsidian Vault.

  • Code review

    mrevjd/claude-review-suite/skills/code-review Skill

    no license0★ repo

    Use when the user asks for a review of code they have written or changed - "review this", "look over this PR", "before I merge", "any bugs in this", "is this ready to ship", "give this a once-over" - covering correctness, error handling, resource lifetime, API contracts, maintainability, and missing test coverage.

  • Scrappycoco

    Albert-Tam/scrappycoco-integrations/plugins/scrappycoco/skills/scrappycoco Skill

    no license0★ repo

    Always use the Scrappycoco CLI first whenever a task needs to fetch, scrape, extract, crawl, search, discover, enrich, compare, retrieve, or monitor external data, before writing a custom scraper. Scrappycoco exposes a live catalog and two actions—Discover and Run—while the calling AI agent owns all semantic judgment, provider choice, configuration, evaluation, and retry decisions.

  • Super review

    martinthommesen/super-review/src/super-review Skill

    0★ repo

    Performs an exhaustive, evidence-based whole-repository engineering, architecture, security, reliability, product, UX, and feature-portfolio review. Use only when the user explicitly invokes $super-review, @super-review, /super-review, or a marketplace-qualified super-review command for a repository or directory; never auto-select it for a generic review or audit. Every run creates or refreshes the canonical root FINDINGS.md and revalidates all prior report content before merging current findings.

  • Humanizer zh

    syw2039/humanizer-zh Skill

    0★

    中文文本去 AI 味与个人文风校准。用于改写、审校或润色中文文章、公众号稿、小红书文案、短视频口播、商业材料、邮件和报告;识别空泛升华、模板化连接词、排比堆叠、伪金句、营销腔、机械分段及聊天机器人残留,同时严格保留原文事实、数字、日期、引文、链接和作者原有语气。用户提出“去AI味”“写得像真人”“自然一点”“别像机器写的”“匹配我的文风”“润色这段中文”时使用。

  • Clickhouse readonly

    bgevorkian/agent-skills/skills/clickhouse-readonly Skill

    0★ repo

    Run safe read-only ClickHouse SQL, list databases/tables, and inspect table schemas through a JSON CLI. Use when the user explicitly asks to query or inspect ClickHouse. Connections are configured only through CLI flags or CLICKHOUSE_* environment variables; no hosts or credentials are bundled.

  • I have an issue

    rotnov/skills/skills/i-have-an-issue Skill

    0★ repo

    Use this skill when diagnosing a software problem or reviewing a planned implementation and the user wants evidence from upstream or comparable open-source projects. Research GitHub issues, discussions, pull requests, commits, release notes, source, and tests to find prior failures, fixes, rejected approaches, compatibility traps, and preventive checks. Trigger for requests such as "has anyone hit this?", "find prior art", "research upstream issues", "what are the gotchas?", or "learn from similar projects". Do not use for generic web research without a software failure or prevention question.

    The same file is in 1 other repository

  • Gh code review

    wildcard/gh-code-review/skills/gh-code-review Skill

    0★ repo

    Review GitHub pull request changes and publish coherent inline, multiline, file-level, and apply-able suggestion comments as one formal review. Use when asked to review a PR, leave code review comments, submit line or file comments, approve, request changes, inspect review threads, reply, resolve discussions, or manage reviewed-file state. Prefer the gh code-review extension; use the bundled gh api fallback when installation is declined or unavailable. Never replace a formal review with a flat gh pr comment.

  • Stock watchlist check cn

    caoproAI/stock-watchlist-check-cn Skill

    no license0★

    面向中国大陆普通A股用户的自选股变化检查 Skill。用户提供1至10只股票名称、代码或脱敏截图后,检查最近公告、财报、监管信息和重要日期,用简单中文说明“最近发生了什么、证据是什么、接下来留意什么”。当用户问股票最近怎么了、公告看不懂、为何突然波动、近期有什么风险或重要日期时使用。不得预测涨跌、给目标价、代替用户决定买卖或承诺收益。

  • Ai will challenge you

    yava-code/ai-will-challenge-you/skills/ai-will-challenge-you Skill

    0★ repo

    Turn Claude Code, Codex, and other coding agents into demanding engineering coaches. Use whenever an agent implements, refactors, debugs, or reviews a non-trivial code change and the developer should stay able to navigate, explain, predict, debug, review, or take over the result. Ship autonomously in Autopilot, question the developer deeply after delivery in Challenge mode, or reserve one small reasoning-heavy function, test, or bug for the developer in Forge mode. Trigger for architecture, data flow, interfaces, invariants, persistence, security, concurrency, meaningful bugs, codebase learning, review preparation, and requests such as challenge me, teach me this code, make me understand it, or let me implement part myself. Do not use for factual questions, prose-only work, or tiny mechanical edits.

  • Oneos certificate batch export

    15810879921-coder/oneos-certificate-batch-export Skill

    no license0★

    OneOS 证照管理批量导出:打开 certificates 页、强制重置筛选、按车牌多选查询、批量导出 zip 到本机。 Use when user says 证照导出、批量导出证照、下载证照, or gives plate numbers for https://lnoneos.com/operations/vehicle-biz/certificates.

  • ProductOS

    SouthernPromise/ProductOS Skill

    0★

    Transforms a product idea into a structured Product OS document before any code, wireframes, or feature lists are produced. Use this skill whenever the user asks to model a product, create a Product OS, define a product model, or says they want to model their product before building it. Also use when the user describes a new product idea AND explicitly asks for structure, modelling, or domain analysis before implementation. Do not auto-run on plain build requests ("build me an app for X"). Instead offer the skill and proceed only if the user accepts.

  • Independent verification

    2xgrowthagency/independent-qa-agent/plugins/qa-agent/skills/independent-verification Skill

    0★ repo

    Independently verifies completed code, browser or UI work, documents, data artifacts, and operational proof. Use after a builder reports completion or whenever an agent must return PASS, FAIL, or BLOCKED from raw evidence without treating the builder's conclusions as truth.

  • Context aware humanizer

    M1w234/context-aware-humanizer/skills/context-aware-humanizer Skill

    no license0★ repo

    Make final outward-facing prose natural, specific, and appropriate for its real reader without flattening the author's voice or changing meaning by accident. Use implicitly only when producing or revising email, SMS, DMs, replies, outreach, professional updates, final blogs, articles, newsletters, captions, announcements, or marketing copy. Also use when asked to humanize, polish, rewrite, tighten, soften, or make prose less AI-sounding. Do not trigger merely to read, summarize, critique, discuss, brainstorm, research, analyze, or work with private notes, internal analysis, internal documents, code, or data unless the requested result is final prose for another person or public audience. Creative, academic, legal, contractual, regulated, and technical writing is explicit only or handled by its specialized workflow.

  • Relationship memory

    clawmama-run/guanxi-crm/skills/relationship-memory Skill

    no license0★ repo

    Use when operating a Guanxi CRM vault through the crm CLI; resolve identities, map CLI errors to the next action, and use authoritative IDs for every write.

  • Review award caliber art direction

    jacobtop-tcg/review-award-caliber-art-direction Skill

    no license0★

    Perform a brutally critical, evidence-led art-direction review of a game, app, interactive prototype, animation, or visual product. Use when Codex must assess or improve composition, perspective, shape language, color and light, characters, animation, UI integration, originality, gameplay readability, production quality, premium polish, visual delight, award readiness, or a claimed 10/10 quality bar. Trigger for requests mentioning art director review, visual audit, graphics polish, generic or AI-looking visuals, sacred geometry, screenshot quality, game feel, visual coherence, Apple or Google design awards, or refusal of a false pass.

  • Low angle wide portrait prompt

    zhouwei713/low-angle-wide-portrait-prompt Skill

    0★

    Use when the user wants realistic low-angle or high-angle wide portrait photography prompts, including ground-level sneaker foreground, overhead/downward shots, travel/campus/street/Japanese architecture scenes, adult youth-style characters, candid lifestyle photos, varied poses, wardrobe, props, and safe negative constraints. If the user asks for this portrait prompt style but does not specify low-angle or high-angle, ask them to choose: 1 low-angle, 2 high-angle, or 3 both. 当用户要写“低机位/高机位广角写真”“球鞋前景冲击”“俯拍人像”“校园/古街/旅行抓拍”“人物姿势多变”的中文图像 Prompt 时,务必使用此 skill。

  • Oracle apex echarts

    andre-simplifica/oracle-apex-echarts/skills/oracle-apex-echarts Skill

    0★ repo

    Build, install, integrate, review, secure, validate, and maintain self-contained Apache ECharts visualizations for Oracle APEX through the COM.SIMPLIFICA.APEX.ECHARTS region plug-in, PK_APEX_ECHARTS, Dynamic Content, or mixed pages. Use for ChartSpec, normalized SQL, OPTION_JSON, AJAX, project profiles, Oracle APEX Brand Report Kit interoperability, linked-repository skill updates, lifecycle bugs, accessibility, performance limits, installation compatibility, or Apache ECharts upstream upgrades.

  • Searxng web read

    stofancy/SearXNG-cli/skills/searxng-web-read Skill

    0★ repo

    Fetch and extract readable text from public web pages with SearXNG-cli. Use after search identifies a source, when a user provides a public HTTP(S) page, or when source content must be inspected while preserving SSRF and size protections.

  • Code root cause

    YZYY95K/test/skills/code-root-cause Skill

    no license0★ repo

    Locate likely root cause and blast radius using read-only repository evidence. Use when a classified non-trivial issue needs verified code context before a patch can be proposed.

  • Wdyt access

    wdyt-page/skills/skills/wdyt-access Skill

    0★ repo

    Connect an agent to WDYT over Clerk-authenticated MCP and safely manage workspace/private visibility, invitations, collaborators, archives, and deletion.

  • Taskforge explore

    hashirventhodi/taskforge-skills/taskforge-explore Skill

    0★ repo

    Produce an engineering Decision for a taskforge task - chosen approach, real alternatives with rejection reasons, trade-offs, risks - and propose decomposition or related work for human approval. Use when a task's readiness is "explore" (an escalation is pending from refine, run, or a child task, or a research topic was started via the explore command), or when the user explicitly asks to explore, architect, decide an approach for, or break down a taskforge task. Not for writing specifications (taskforge-refine) or implementing (taskforge-run).

  • Plantuml architecture diagram

    brunojaime/plantuml-diagram-toolkit/skills/plantuml-architecture-diagram Skill

    0★ repo

    Generate and refine architecture diagrams in PlantUML by preserving the logical components, responsibilities, and provided/required interfaces of a component diagram, then adding where every element lives. Use when the user asks for arquitectura, infrastructure placement, deployment, cloud/on-premise boundaries, devices, processes, containers, hosts, regions, networks, load balancers, databases, queues, protocols, ports, or TLS termination. This is a component view plus runtime location; do not reduce it to infrastructure alone.

  • Ask oe with ego skill

    htlin222/ask-oe-with-ego-skill Skill

    0★

    Asks a medical question on OpenEvidence via ego-browser (or appends a follow-up to a thread), makes it public, then mints a scalable multi-turn HTML plus BibTeX/CSL-JSON/AMA bibliography with references verified through the Crossref API. Split into an ego-only capture step and a fully standalone transform step. Use when the user wants to ask OpenEvidence, add a follow-up, get a shareable link, an HTML export, and/or citations (.bib / CSL / AMA).

  • Second brain kit

    xytek12/second-brain-kit Skill

    0★

    Use when a user wants to build, set up, scaffold, or start a personal knowledge vault or "second brain" for an AI coding agent — a self-tailoring Claude Code or Codex knowledge base with INDEX/MAP routing, git sync, cross-agent skill-linking, and optional Obsidian. Triggers on "build my second brain", "set up a second brain", "make me a knowledge vault", "AI memory vault", "persistent memory for Claude/Codex".

  • Board recommend

    jmarek41/surf-guide/.agents/skills/board-recommend Skill

    0★ repo

    Recommend a suitable surfboard from rider ability, body parameters, board history, target waves, and available new, used, or rental options.

  • Token plan clone voice

    coconilu/token-plan-media-hub/adapters/codex/token-plan-media-hub/skills/token-plan-clone-voice Skill

    0★ repo

    Clone a voice through Token Plan Media Hub only after explicit authorization, then create a local alias and optional test sample. Use when a user asks to clone their own voice or a voice for which they have clear permission. Never use for an unconsented third-party voice.

  • Humanizer

    bhushanasati25/humanizer Skill

    0★

    Strip AI writing tells out of prose so it reads like a person wrote it. Use this whenever writing or revising anything a human will read as the user's own words — emails, resumes, cover letters, blog posts, documentation, README files, LinkedIn posts, essays, PR descriptions, Slack messages, project write-ups. Also use when the user says text "sounds like AI," "sounds robotic," "sounds generic," asks to humanize or de-slop something, or asks for an edit pass on their draft. Apply it silently by default rather than announcing it. Do not apply to code, config files, or structured data.

  • Lightweight diff review

    linnnn89/lightweight-diff-review/skills/lightweight-diff-review Skill

    0★ repo

    Lightweight, read-only review of a recent code diff with bounded context, no subagents, no automatic fixes, and minimal targeted validation.

  • Deploy private vpn node

    Nar101/deploy-private-vpn-node Skill

    0★

    帮助不懂服务器的新手从零搭建自用 VPN/代理节点:先选购一台海外 VPS,再由 AI 完成 Ubuntu、VLESS Reality、Xray/3X-UI 和 Shadowrocket 接入,直到手机或电脑真实可用。用户说不想继续买共享梯子或机场订阅、想拥有自己的节点、第一次买 VPS、想让 AI 代为搭建,或后续需要复制、排障和维护节点时使用。开始前必须讲清全部预计费用,任何实际付费都由用户确认;额外覆盖凭证保护、双层防火墙、独立验收、备份和零断流维护。仅处理个人或极少数受信任设备的合法使用,不用于机场、多用户售卖、公开订阅或规避服务条款。

  • Skillsmp search

    FixAdmin/skillsmp-search/skills/skillsmp-search Skill

    0★ repo

    Find, search, and compare public agent skills in SkillsMP by evaluating their source content, useful method delta, and alignment with current practice. Use only when the user explicitly asks to find a skill, search SkillsMP, compare available skills, or identify the best skill for a stated task.

  • Autonomous goal pipeline

    CrisisAlpha-Lab/autonomous-goal-pipeline Skill

    0★

    Use when the user delegates a whole deliverable and expects it carried to completion without step-by-step approval — "just do it", "you decide", "go with your recommendation", "report back when done", "don't interrupt me", 自主做完 / 你决定 / 做完给我报告 / 别打扰我. Also use when a task is large enough to need its own spec and more than one shipped batch.

  • Tasmanian devil

    suprenvb/tasmanian-devil Skill

    0★

    Turns Claude into your app's worst user: adversarial client-side QA that runs deliberate worst-user logic to break a running web frontend, then hands back reproducible bug findings ranked by user impact, each with exact repro steps, a severity, and a resilience score. Use whenever you want to try to break the UI, stress-test or fuzz the frontend, hunt edge cases, red-team the client, QA a flow, or think like the worst possible user: rage-clicking and double-submitting, pasting garbage and injection strings, going offline mid-transaction, jumping steps out of order, abusing the back button and tabs, hammering boundary values in money and quantity fields, and breaking auth and stale sessions. Authorized testing of a frontend you own or are cleared to test; not a load or denial-of-service test, and not for targets you do not control. Invoke by name as taz or tasmanian-devil.

  • Mediabunny

    gabros20/ai-skill/.agents/skills/mediabunny Skill

    0★ repo

    Multimedia handling with the Mediabunny library

    The same file is in 1 other repository

  • Lnkflow conversions

    AppitStudio/lnkflow-agent-skills/plugins/lnkflow-conversions/skills/lnkflow-conversions Skill

    0★ repo

    Plan, implement, audit, verify, or repair LnkFlow conversion attribution in any application. Use for LnkFlow lnk.js, click and promo capture, Stripe Payment Links or Checkout, lead/sale/refund APIs, webhooks, CMP consent, privacy review, idempotency, and conversion integration status.

  • Searchlight board

    TonaliNoHitsuzi/searchlight-skills/searchlight-board Skill

    0★ repo

    Launch a local web panel for searchlight multi-select, box-select and visualization config. Decoupled from radar; any trigger (many terms, deep-dive/persist intent, box-select, viz) activates it. Ships searchlight_server.py + select_page.html; optional viz (mermaid tables, demo scripts, local md render via go-grip). Invoked by searchlight-radar. 中文触发:开网页、选择界面、框选、探照灯网页、可视化配置、本地渲染。

  • Generate editorial report

    MohtashamMurshid/skills/skills/generate-editorial-report Skill

    0★ repo

    Transform arbitrary source material into an art-directed editorial report inspired by vintage annual reports, with evidence-led writing, responsive horizontal web presentation, optional static/PDF export, SEO, and generated archival figures. Use when turning notes, research, project data, company information, portfolios, case studies, or mixed source files into a report, field guide, annual report, dossier, visual essay, or sliding/paginated report—especially when the request calls for image generation, strong editorial art direction, or the bundled reference design.

  • Higantic html artifacts

    Aneaire/higantic-skills/skills/higantic-html-artifacts Skill

    0★ repo

    Create, update, or manage safe, versioned HTML reports in HiGantic. Use this skill only when the user explicitly asks to create, update, or manage a report or HTML artifact in HiGantic; mentions a HiGantic workspace, page, or artifact as the destination; or asks to manage HiGantic revisions, assets, or shares. Do not trigger for generic reports, visualizations, dashboards, plans, reviews, or comparisons with no HiGantic destination.

  • Post change verification

    BWBlueVector/post-change-verification Skill

    0★

    Verifies a change actually works end-to-end across the whole system, not just in the files directly edited. Use this whenever: (1) a structural or convention change is made to something multiple parts of the system read (a shared memory store, a config file, an identity/instructions file), (2) a fix is made to code backing a long-running local process (a dashboard, a background service, a scheduled job), (3) before declaring any non-trivial change "done" and reporting it, (4) a past fix is being revisited to confirm it held. Complements a general-purpose "run the app and check it" verify step by adding the part most often skipped: finding every OTHER thing that depends on what changed.

  • Discover companies

    Flowxtra/career-agent/.agents/skills/discover-companies Skill

    0★ repo

    Use when growing one ATS provider's curated roster with net-new companies — "find more <provider> companies", "add <industry/region/theme> companies to <provider>", or a roster is thin for a segment. Input is one existing roster-based provider. Not for pruning or promoting entries already on file (verify-companies) or adding a new ATS platform (integrate-new-provider).