agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Sci manuscript architect

    Liangshuntao/sci-manuscript-architect Skill

    1★

    Use for biomedical SCI manuscript strategy and writing from study materials, including field positioning, motivation and gap analysis, innovation taxonomy, contribution-level estimation, submission-level strategy, evidence-aware claim control, corpus-based style profiling, IMRAD blueprinting, figure architecture, reviewer audit, journal checklist, and LaTeX-safe manuscript checks.

  • GitHub skill publisher

    chemny/GitHub-skill-publisher Skill

    1★

    Use this skill when the user wants to publish, update, package, document, or synchronize an agent skill to GitHub. It captures a single-skill-per-repository workflow, bilingual README writing style, GitHub repository creation, commit/push updates, publish readiness checks, Codex/Claude Code/OpenClaw compatibility checks, portability checks, and security review for public skill repositories.

  • Engineering review

    brenbuilds1/skills/skills/engineering-review Skill

    1★ repo

    Code review stance for serious engineering changes. Use when asked to review a diff, PR, commit, branch, patch, architecture change, migration, implementation, or test plan for bugs, regressions, missing tests, operational risk, security/privacy issues, and maintainability problems that could actually hurt users.

  • Config file versioning

    dragon-fish/config-file-versioning Skill

    1★

    给小型本地配置文件设置自动版本备份,便于回滚被覆写/误改。当用户希望给某几个 config 文件(如 ~/.ssh/config、~/.zshrc、应用 dotfile 等)加版本史/防覆写/可一键回滚时使用。统一架构:separate-git-dir + 白名单 .gitignore + 操作系统级文件监听 + 自动 commit 脚本。一个被保护的 config 域 = 一个独立小仓库。原生支持 macOS(launchd),Linux/其他可参照同思路换用 systemd path unit / inotifywait / gitwatch 实现监听层。

  • Mdc workflow

    nbhhdd/mdc-workflow/skills/mdc-workflow Skill

    1★ repo

    Initialize or upgrade a project's Multi-Document Co-driven (MDC) workflow system. Use when the user asks to "set up MDC", "initialize document workflow", "create project docs system", "set up TS-Protocol", "create multi-document agent workflow", "建立文档工作流", "初始化文档体系", "搭建 MDC", or wants to establish a structured documentation-driven development system. Also triggers when user describes document-code desync problems or wants reusable AI collaboration standards.

  • Audit security

    designgrappler/agent-os/claude/skills/audit-security Skill

    1★ repo

    Scans a project for security vulnerabilities, hardcoded secrets, insecure patterns, and dependency risks.

  • Fable fuse

    hondrytravis/skills/skills/fable-fuse Skill

    1★ repo

    Fable-Fuse 元学习框架。仅当用户显式调用 Fable-Fuse、/fable-fuse、 fable-fuse、寓言熔断框架、认知熔断器,或明确要求使用这个 skill 时触发。 不从普通学习、解释、速成、理解类请求中自动推断触发。用于在被明确调用后, 帮用户避免无限追溯底层细节、完美主义式深挖、或原地打转收益递减。 完整践行 Fable-Fuse v1.5:实用优先、限时回溯、寓言降维、费曼四层验收、认知债务偿还。 角色:认知熔断器 + 寓言翻译官 + 债务记账员。 不适用:执行明确编程任务、代码调试、文件操作等日常开发场景—— 这些场景下保持正常对话,不切换学习模式。

  • Autoresearch

    eliransu/digital-brain/skills/autoresearch Skill

    1★ repo

    Autonomous iterative research loop. Takes a topic, runs web searches, fetches sources, synthesizes findings, and files everything into the wiki as structured pages. Based on Karpathy's autoresearch pattern: program.md configures objectives and constraints, the loop runs until depth is reached, output goes directly into the knowledge base. Triggers on: "/digital-brain:autoresearch", "autoresearch", "research [topic]", "deep dive into [topic]", "investigate [topic]", "find everything about [topic]", "research and file", "go research", "build a wiki on".

  • Backup before troubleshooting

    rubicon/ai-skills/plugins/backup-before-troubleshooting/skills/backup-before-troubleshooting Skill

    1★ repo

    Stand up a dated, self-documenting recovery workspace BEFORE changing system, app, or configuration state, so every change is reversible and the whole effort can be forensically reconstructed afterward — including regressions caused by your own fixes. Use this whenever you are about to mutate config, application data, system files, or installed components during troubleshooting AND want to be able to both undo the changes and reconstruct what happened later. Trigger phrases: "back this up first", "before I start messing with this", "I want to be able to undo this", "set up a recovery folder", "track this troubleshooting", or when resuming an effort that already has a recovery workspace. Do NOT use for read-only diagnosis, trivially reversible edits, or code work already tracked by git.

  • Bug reproduction

    sonsriver4815/agent-skill-starter/examples/bug-reproduction Skill

    1★ repo

    Use this skill when the user asks to reproduce a bug, verify a reported failure, reduce an issue to a minimal case, or capture reliable steps before fixing.

  • Deslop

    MarcoAntolini/cursor-sync/agents/skills/code-quality/deslop Skill

    no license1★ repo

    Remove AI-generated code slop and clean up code style

    The same file is in 1 other repository

  • Bash shortening

    paulnsorensen/skillz-that-grillz/skills/bash-shortening Skill

    1★ repo

    Write, review, or refactor Bash scripts into concise, idiomatic shell code. Use this skill whenever the user is editing a `.sh`, `.bash`, or `bash`-fenced block with a Bash shebang (or no shebang in a Bash-only context), mentions "shorten this script", "make this more idiomatic", "clean up this bash", "this script is too long", "is there a shorter way to do this in bash", or asks for a code review of shell scripts. Also trigger when generating new Bash scripts from scratch — produce idiomatic patterns the first time instead of refactoring later. Covers parameter expansion, brace expansion, process substitution, arithmetic contexts, function patterns, pipelines vs temp files, heredocs, associative arrays, parallel execution, and CSV/IFS parsing — 51 techniques total. Refuses cryptic one-liners when shortening would hurt readability. Do NOT use for fish, zsh, or POSIX-only `/bin/sh` scripts where bashisms would break portability.

  • Career development

    jjfroehlich/agent-skills-for-academic-research/skills/career-development Skill

    1★ repo

    Use this skill when a scientist needs stage-specific career help with advisor or lab choice, PhD/postdoc/faculty applications, CVs, resumes, cover letters, recommendation-letter scaffolds, referee evidence packets, interviews, offers, startup negotiation, academia-to-industry transitions, job ad interpretation, networking, or a concrete career-path decision. Trigger when the input is a career artifact, opportunity, role comparison, application package, or personal career constraint. Do not trigger for manuscript, grant, figure, project-strategy, journal-selection, or lab-management tasks unless the main issue is the user's own career decision.

  • Dabing perspective

    dogxxgod/dabing-skill/dabing-perspective Skill

    1★ repo

    大冰(山东籍主持人/作家/摩旅者/直播主)的思维框架与表达方式。 基于《阳光快车道》主持生涯、10+本出版物、摩旅经历、2023-2024直播间翻红表现的系统蒸馏, 提炼5个核心心智模型、6条决策启发式、完整的中文输出适配和经典句式速查。 用途:作为思维顾问,用大冰的视角分析人生选择、情绪困境、人际关系、职业迷茫、创作表达。 当用户提到「用大冰的视角」「大冰会怎么看」「大冰模式」「冰学」时使用。 也适用于:连麦式对话、情绪疏导、人生方向梳理、反精英叙事、民谣/旅行/文艺话题。 不在用户只是普通问生活问题时触发——只在明确想要大冰式思维框架时激活。

  • Serve sim skill

    malopezr7/serve-sim-skill Skill

    1★

    Controls a running iOS, iPad, or Apple Watch Simulator via the serve-sim CLI (npx serve-sim) and streams it into the host agent's preview pane. Use whenever the user wants an AI agent to view or drive an Apple Simulator — streaming to preview, taps at normalized coordinates, multi-touch gestures, hardware buttons, rotation, memory warnings, CoreAnimation debug, synthetic camera injection, or media drag-drop. Triggers include "serve-sim", "iOS simulator", "Apple simulator", "iPad simulator", "Apple Watch simulator", "stream the simulator", "show the simulator in preview", "view the simulator here", "open simulator in preview", "simulator gestures", "tap on the simulator", "rotate the simulator", "inject camera feed", or any request to drive or display an Apple Simulator visually. Do NOT use for Android emulators, building/installing an iOS app (use xcodebuild), booting a simulator from scratch (use xcrun simctl boot), in-app React Native runtime debugging (use rn-debugger), or real iOS hardware.

  • On this day reader

    ognistik/skill-on-this-day-reader/on-this-day-reader Skill

    1★ repo

    Export Day One On This Day entries from the local macOS Day One database, analyze them as a personal-history journal review, and save the result to Readwise Reader using the Readwise CLI. Use when the user asks to run, package, automate, or share a Day One On This Day to Reader workflow without relying on MCP tools.

  • Obsidian kanban skill

    HristovCodes/obsidian-kanban-skill Skill

    no license1★

    Create and edit Obsidian Kanban board markdown files correctly. Use when asked to create, modify, or work with Kanban boards, task boards, or feature planning boards in any project.

  • Prd paradigm

    hugoooo1018/pm-agent-toolkit/skills/prd-paradigm Skill

    1★ repo

    按 PRD 范式生成或审查段落/章节。用户说"写 PRD / 新建模块 PRD / 补充功能点 / 按范式生成章节 / 检查 PRD 结构"时触发。可用于模块级(整 7 章 PRD)或功能级(10 章中的模块详述章节)。

  • Neurobro catalyst watch

    axioma-ai-labs/neurobro-skills/skills/neurobro-catalyst-watch Skill

    1★ repo

    Builds event-driven trade plans through the NeuroAPI agent - maps upcoming catalysts (earnings and IPO calendars, FOMC and macro prints, token unlock schedules, airdrops, DAO governance votes, mainnet launches, listings, ETF and regulatory decisions), assesses what is priced in, and plans positioning before and after the event. Use when the user wants a catalyst calendar, asks how to position around earnings or a macro print, wants to trade a token unlock, airdrop, governance vote, or protocol upgrade, or asks what events are coming for an asset or watchlist.

  • Ruidong ui

    Rubbish0-A/raytone-ui-studio/skills/ruidong-ui Skill

    1★ repo

    Use this skill whenever building, designing, or styling any frontend UI for a Raytone (睿动) AI agent project — even if the user doesn't explicitly say "睿动风格". Apply proactively when the user mentions designing a sidebar, dashboard, settings page, chat panel, Tailwind config, or any React/frontend UI for a new Raytone agent, or says things like "睿动风格"、"睿动 UI"、"用睿动的样式"、"raytone-ui"、"SmartSolu 同款"、"智能解决方案架构师同款"、"需要和睿动其他智能体保持视觉一致"、"跟智能体广场其他 app 保持一致"、"bold-vivid 风格"、"赛博朋克风格"、"北欧简约风"、"蒸汽波风格"、or slashes /raytone-ui. Contains a curated set of styles (smartsolu-linear — the polished Notion+Linear+Raycast workbench aesthetic; bold-vivid — high-impact themed aesthetics with 4 sub-themes); the skill helps pick one when not specified and then supplies tokens, component snippets, and full example code so the agent's UI stays on brand without debating colors/fonts/components from scratch.

  • Nativephp mobile

    kuzmany/nativephp-mobile-skill/skills/nativephp-mobile Skill

    1★ repo

    This skill should be used when the user asks to "create mobile app", "nativephp", "native php", "mobile app with laravel", "ios app", "android app", "build APK", "build IPA", "sign app", "native:run", "native:install", "native:jump", "native:package", "deploy to app store", "deploy to play store", "EDGE components", "bottom nav", "top bar", "side nav", "push notifications", "firebase push", "nativephp plugin", "bridge function", "mobile deep links", "camera", "biometrics", "securestorage", "deep linking", "OnNative", "nativephp_call", "persistent runtime", "background jobs", "mobile queue", "queue worker", "laravel boost mobile", "mobile-starter", or mentions NativePHP Mobile development, Laravel mobile apps, or building iOS/Android apps with PHP. Documents NativePHP Mobile v3.0–3.1.

  • Browse orbis apis

    OrbisAPI/agent-skills/skills/browse-orbis-apis Skill

    no license1★ repo

    Search and browse 2,200+ x402-enabled APIs on the Orbis marketplace. Use when you need to find an external API or service, want to know what APIs are available, or need to discover a paid API for a specific task. Covers "find an API for...", "what APIs does Orbis have?", "search for...", "show me available services".

  • Accept five

    timeyour/agentskills-audit-collection/.claude/skills/accept-five Skill

    1★ repo

    Run five-pass acceptance testing on a website, app, repo, feature, or audit target: baseline, functional, edge/failure, visual/deployment, and retest/experience. Use when one inspection is not enough and repeated findings must become reusable experience.

  • Brandapp sdk install

    reopt-ai/reopt-skills/skills/brandapp-sdk-install Skill

    1★ repo

    Install @reopt-ai/brandapp-sdk in a consumer project. Sets up auth, OAuth client, EAV, API routes, and env config. Triggers on "brandapp-sdk install", "brandapp-sdk init", "brandapp sdk setup", "brandapp sdk bootstrap", "apply SDK", "brandapp integration".

  • Kmp expect actual

    almasumdev/awesome-kotlin-multiplatform-agent-skills/.github/skills/architecture/kmp-expect-actual Skill

    no license1★ repo

    Idiomatic use of `expect`/`actual` declarations in Kotlin Multiplatform, when to prefer interfaces + DI instead, and how to design platform abstractions that age well. Use when you need platform-specific behavior in `commonMain`.

  • Bff pattern

    almasumdev/awesome-mobile-backend-agent-skills/.github/skills/api/bff-pattern Skill

    no license1★ repo

    When and how to use a Backend-for-Frontend (BFF) for mobile -- scoping, ownership, and anti-patterns. Use when deciding whether a BFF is justified or designing one.

  • Design brief builder

    jade-666/design-brief-builder/design-brief-builder Skill

    1★ repo

    Generates structured design briefs and execution constraints for UI/UX projects. Use at the start of a design task — especially vague requests, prototype redesigns, UI audits, or brand-consistency work, or when the user attaches prototype images, Figma links, or brand documents. Trigger on phrases like "redesign this", "audit the UI", "fix the layout", or "help me brief this project".

  • Masheev ai agents

    masheev/skills/skills/masheev-ai-agents Skill

    no license1★ repo

    Use when configuring Masheev AI agents — system prompts, model selection, tool assignment, knowledge base integration, guardrails, escalation triggers, and voice agent setup with ElevenLabs. Covers the AI agent entity, how agents connect to inboxes, prompt engineering for support agents, and the relationship between AI agents (intelligence) and voice agents (TTS/STT). Use this skill when someone asks to "set up an AI agent", "configure the chatbot", "write a system prompt", "add tools to the agent", "connect knowledge base", or "set up voice AI".

  • Openspecpm

    aks-builds/openspecpm Skill

    1★

    Spec-driven, BDD-shaped project management for AI agents. Converts natural language proposals into BDD feature files and tracked work items in GitHub Issues, Azure DevOps, Jira, Linear, or GitLab. Use when writing specs, defining acceptance criteria, creating user stories from requirements, or managing a product backlog from natural-language descriptions.

  • Agent browser

    justincordova/agents/skills/agent-browser Skill

    1★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

    The same file is in 21 other repositories

  • Cometchat astro patterns

    cometchat/cometchat-replit-template/.agents/skills/cometchat-astro-patterns Skill

    no license1★ repo

    Framework-specific patterns for integrating CometChat React UI Kit v6 into Astro projects using React islands. Covers client:only rendering, island communication, CSS handling, and common pitfalls.

    The same file is in 1 other repository

  • Sigmalifting cli

    sigmalifting/skills/sigmalifting-cli Skill

    1★ repo

    Use when the user wants to create, translate, import, validate, inspect, or update powerlifting training programs or workout logs for SigmaLifting using sigmalifting-cli, especially from spreadsheets, manuals, public programs, app exports, program-import bundles, or process-import bundles.

  • Agentic workflow guard auditor

    guorunjie/agentic-workflow-guard/skills/agentic-workflow-guard-auditor Skill

    1★ repo

    Use before granting AI automation write access, reviewing agentic GitHub Actions, Bitbucket Pipelines, GitLab CI, Travis CI, Drone CI, TeamCity, Harness CI/CD, Tekton Pipelines, Argo Workflows, AWS CodeBuild, Google Cloud Build, CircleCI, Azure Pipelines, Jenkins, Buildkite, auditing n8n, Dify, Flowise, Langflow, Node-RED, Make, Pipedream, Airflow, browser automation, or checking MCP tool configs for prompt-injection and side-effect risks.

  • Vibe prompt

    TurnkeyIsaiah/vibe-prompt Skill

    1★

    Generate an optimized Claude Code kickoff package (spec + initial build prompt + feature-by-feature prompt sequence + workflow checklist) for building an app. Use when the user invokes /vibe-prompt or asks to "vibe code", "build an app", "help me prompt", describes an "app idea", or asks for a "coding prompt", "prompt to build", or "kickoff prompt". Turns a vague app idea into well-structured prompts grounded in Anthropic's official Claude prompting best practices, and teaches the correct build process (always starting in plan mode).

  • Agent context files

    DeanThompson/agent-skills/skills/agent-context-files Skill

    1★ repo

    Create, review, and optimize persistent agent context files such as AGENTS.md, CLAUDE.md, .cursorrules, GEMINI.md, or repository-specific AI assistant instructions. Use when the user asks to create or improve agent instructions, project memory, coding-agent onboarding docs, or context files that should be loaded across sessions.

  • Bug fix tdd

    geigermatic/claude-craft/skills/bug-fix-tdd Skill

    1★ repo

    Fix a bug test-first. Reproduce as a failing test before writing the fix. Use when the user reports a bug or asks you to fix a defect.

  • Soul loader

    imphillip/agentbox/skills/soul-loader Skill

    1★ repo

    Install the soul-loading capability into your runtime, so your human can hand you SillyTavern V2 character cards in chat and you'll import them as SOUL.md.

  • Learn video

    9Tech-Solutions/learn-video Skill

    1★

    Extract reusable knowledge from a YouTube/TikTok/Vimeo URL via a 6-stage audio+visual fused timeline (ingest → transcribe → probe → target/summary → vision → classify → fuse). Hands off to /learn-eval so the output lands in the right bin (skill, rule, tip, note, discard). Use this when the user shares a video URL and wants extracted notes, not when they want the video downloaded or clipped.

  • Background work optimization

    almasumdev/awesome-mobile-performance-agent-skills/.github/skills/battery/background-work-optimization Skill

    no license1★ repo

    Schedule, batch, and constrain background work with WorkManager, BGTaskScheduler, and push-over-poll patterns to minimize battery and data cost.

  • Boundary definition

    zoidbergclawd/coherence/skills/boundary-definition Skill

    1★ repo

    Use when starting a feature, refactor, integration, API change, or state-machine change, before writing code, to force explicit interfaces, inputs, outputs, contracts, invariants, ownership, non-goals, and failure modes.

  • Application lifecycle trace

    ChristopherAlphonse/calphonse-skills/application-lifecycle-trace Skill

    1★ repo

    Show case application lifecycle

  • Architecture diagram

    taleshagn-horushub/thoth/skills/architecture-diagram Skill

    1★ repo

    Gera diagramas de arquitetura de sistemas em formato Mermaid. Use para: criar representações visuais de arquiteturas de software, fluxos de dados, infraestrutura em nuvem e topologias de rede usando a sintaxe Mermaid.

  • Super automation

    arpitexplores/super-automation Skill

    1★

    Workflow and app automations across SaaS tools, APIs, and integrations.

    The same file is in 1 other repository

  • Setup

    philpalmieri/engineering-manager-skills/setup Skill

    1★ repo

    Interactive setup wizard for Engineering Manager Skills. Walks the user through creating their team.json configuration file with team roster, org settings, vault path, and project tracking config. Run this first after installing the skills. Use when asked to 'set up', 'configure', or 'initialize' the manager skills.

  • Babysit pr

    endalk200/skills/skills/babysit-pr Skill

    no license1★ repo

    Validate and triage pull-request review findings before addressing selected items.

    The same file is in 2 other repositories

  • Question upgrade

    alavten/question-upgrade Skill

    no license1★

    Upgrades vague user questions into expert-level, system-level, high-density questions using Munger-style multidisciplinary latticework, first principles, inversion, and incentive/second-order framing—without answering them. Use when the user asks to reframe, upgrade, sharpen, or improve a question; mentions question upgrade, expert-level questioning, Munger, latticework, 芒格, 思维格栅, 逆向思考, 跨学科, or 问题重构 / 升级问题 / 专家级提问; or needs a question strong enough to elicit world-class answers. When the upgraded question is solution-ready, prompts the user to opt in before answering from the final upgraded question (开始给方案 / Start with the plan).

  • Gallery

    All-The-Vibes/ATV-PaperBoard/adapters/claude-code/_dist/skills/gallery Skill

    1★ repo

    Regenerate the Paperboard Gallery — a local HTML index of all rendered artifact triples. Invokes `paperboard gallery` via the atv-paperboard CLI.

  • Skill fidelity bench

    c0ffee-milk/skill-fidelity-bench Skill

    1★

    Benchmark whether a modified or poisoned skill still preserves the clean skill's capabilities, reasoning, boundaries, and distinctiveness. Use this whenever the user wants a clean-vs-poisoned skill benchmark, a capability-fidelity audit, a taskset + rubric workflow, or a reproducible comparison report.

  • Agentizer zh

    ispacekid/agentizer-zh Skill

    1★

    让任何文本或对话更像 AI —— 不是去 AI 味,而是把 AI 味拉满。一个反讽性质的 逆向去痕工具,注入最浓的 AI 八股文(否定排比、三段式、科技隐喻、抽象哲学、 开放结尾)用于搞笑和批判。支持 /agentizer-on、/agentizer-off 持续对话模式, 以及 /agentizer [文本] 单次改写。

  • Migrate to pnpm 11

    llbbl/pnpm-upgrade-skills/claude/migrate-to-pnpm-11 Skill

    1★ repo

    Migrate a JavaScript/TypeScript project from npm, yarn, or older pnpm (≤10) to pnpm 11, adopting its supply-chain-hardened defaults (minimumReleaseAge, allowBuilds, blockExoticSubdeps, strictDepBuilds, verifyDepsBeforeRun). Use when the user says "migrate to pnpm 11", "upgrade pnpm", "switch to pnpm", or wants to harden a project against npm supply-chain attacks.

  • Prettify pdf

    sethupavan12/prettify-pdf Skill

    1★

    Redesign or QA PDFs for clarity while preserving IDs, dates, amounts, barcodes, QR codes, seals, signatures, labels, and meaning. Use for receipts, invoices, forms, tickets, resumes, reports.

    The same file is in 2 other repositories

  • Careful coding

    tuoitho/careful-coding-skill/skills/careful-coding Skill

    1★ repo

    Use when handling software engineering tasks such as coding, debugging, refactoring, architecture, testing, documentation, code review, or technical decision-making.

  • Openclaw doc2md

    benmillerat/openclaw-doc2md Skill

    no license1★

    Convert Telegram document attachments to clean Markdown using markitdown, defaulting to LLM-enhanced conversion, then reply with a .md file and a short, clean preview. Use when a user sends a supported document or media attachment and wants it converted to markdown.

  • Legacy support adjudication

    pratyush1712/legacy-support-adjudication-skill/skills/legacy-support-adjudication Skill

    1★ repo

    Use during code review when a change touches backward-compatibility logic, migration shims, deprecated API/version bridges, old schema or payload handling, feature-flag fallbacks, transitional formats, old client support, historical data readers, or retired runtime/build support. Trigger even when the reviewer doesn't name 'compatibility' or 'deprecation' directly — questions like 'can we delete this yet?', 'is this still needed?', 'old clients?', 'migration complete?', or 'probably dead code' on a diff qualify, as do PRs that delete or simplify code paths named legacy/compat/fallback/shim/v1/deprecated. Produces an evidence-based verdict: retain, instrument, deprecate, quarantine, or remove.

  • Book call

    DualNova/agent-skills/spec/examples/book-call Skill

    1★ repo

    Book a free 30-minute discovery call with the team to discuss a project.

  • Qa vibe test specialist

    moonki080/qa-vibe-test-specialist Skill

    1★

    Standards-aligned software testing support for vibe-coded code, prototypes, PRs, implementation diffs, and intermediate results. Use when Codex needs to assess, design, generate, run, or review tests using CSTS-aligned Korean software testing practice, ISTQB-style test techniques, ISO/IEC/IEEE 29119-informed test process and documentation, ISO/IEC 25010 quality attributes, OWASP WSTG security checks, risk-based testing, exploratory testing, defect reports, QA signoff, direct repository test execution, remediation planning, or iterative test-fix-retest improvement loops until a defined quality goal is reached for AI-generated or fast-iterated software work.

  • Apply agent evolution

    fmind/agent-evolutions/skills/apply-agent-evolution Skill

    1★ repo

    Apply phase of an agent evolution — diff the winner workspace against the live repo, get explicit user confirmation, copy files in, optionally re-run gates against the live tree. Writes `applied`. Requires `winner` set by `/run-agent-evolution`.

  • Agent bus

    MustaphaSteph/agent-bus-plugins/claude-code/plugins/agent-bus/skills/agent-bus Skill

    1★ repo

    Coordinate work across Claude/Codex/Cursor sessions on the same machine via a local message bus. Use to delegate to helpers, get a second opinion, ask specialists by capability, or track shared tasks.

  • Neo design skill

    ImNeo-hub/neo-design-skill Skill

    no license1★

    Neo的个人视觉设计系统(品牌DNA:暖黄·朱红·湖蓝复古插画风 + 宋体标题)。把内容做成**视觉成品**:小红书 3:4 图文卡片(1080×1440、多图可导出 PNG)、HTML 页面 / landing page、海报、封面等。从模板改、不从零写,输出风格统一、不像 AI。 触发:用户要「做图文/做卡片/小红书图文/把文章转成卡片/做个页面/做 landing/做海报/做封面」等需要**出图或出页面**的视觉任务。说「做图/图文/卡片/小红书/生成 html」含糊时默认走 3:4 卡片,不默认做长滚动网页;明确说「网页/landing/官网」才做网页。 现状:**目前只有小红书 3:4 卡片是成熟稳定输出**(公众号封面等在建)。要强制锁定 3:4 卡片、绝不退回网页,用命令 /nds-xhs。 不适用:纯文字文案(用 neo-write-skill);视频(用 neo-video-skill)。

  • Skill creator

    krkn-s/ai-workspace/.pi/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories