agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Hotspots tophot

    xltang/hotspots_tophot Skill

    0★

    用于拉取并展示热点内容(接口为 https://hotspot.api4claw.com/hotspots/platform/{平台名}?timestamp=$TIME_STEMP,返回 JSON 数组)。按 source_name 分组标题。默认会提示用户创建定时任务(不自动执行),在用户确认后提供 cron 注册命令。不使用本地 user_id。适用于用户查询每日热点、微博热点、新闻联播、知乎热点、腾讯早报、服务状态、按 source_name 分组标题,或由已存在的定时消息触发执行。触发词:"今日热点", "每日热点", "热点", "微博热点", "新闻联播", "知乎热点", "腾讯早报"。

  • Mcl common

    suwa-sh/multi-cloud-lifecycle-skills/.claude/skills/mcl-common Skill

    0★ repo

    mcl-foundation-design / mcl-shared-platform-design / mcl-product-design が共通で参照するメタスキル。共通メタデータスキーマ、YAML テンプレート、正規化・マッピング・競合解決のルールを提供する。このスキルを直接トリガーする必要はない。他の mcl-* スキルが references/ templates/ schemas/ を参照する際に自動的に利用される。mcl-common の内容を確認・編集したい場合や、共通ルールやテンプレートについて質問がある場合にもこのスキルを参照すること。

  • Anti slop design

    ZiadMD/anti-slop-design Skill

    0★

    Produce frontend web designs (HTML, React, CSS) that are unmistakably human-crafted and avoid every known AI-generated design cliché. Use this skill whenever the user asks to build or redesign a website, landing page, portfolio, dashboard, UI component, or any web artifact — especially when they mention words like "modern", "clean", "professional", "premium", "unique", "not generic", "avoid AI look", "human feel", or "stand out". Also use it proactively whenever you are about to generate a website or UI, even if the user didn't ask explicitly — because AI-generated design defaults are now so recognizable they actively hurt credibility. This skill overrides any default design instincts. Read it fully before writing a single line of code.

  • Security code review

    PiyushSolanki038/security-code-review Skill

    0★

    Audit any codebase for the OWASP Top-10-style vulnerability classes (SQLi, XSS, IDOR, broken auth, CSRF, XXE, SSRF, file upload, misconfig, data exposure, insecure deserialization, command injection, path traversal) by reading the actual code, and propose/apply fixes. Detection-only — never generates attack payloads or exploit code.

  • Test design review

    matusbu/claude-code-test-automation-skills/.claude/skills/test-design-review Skill

    0★ repo

    Review test design quality for code changes against the defined test strategy. Use when reviewing a feature branch, commit, or uncommitted changes to ensure new or modified tests are well-designed, placed at the correct test level, and conform to the architecture defined in the strategy.

  • Aurelion core

    Chase-Key/aurelion-skills/skills/aurelion-core Skill

    0★ repo

    The Aurelion cognitive architecture — five modules that together form a complete autonomous agentic AI system.

  • Lumi app finder

    alice51849/lumi-mcp/skills/lumi-app-finder Skill

    0★ repo

    Finds verified live Lumi Studio iPhone and iPad apps from a first-party catalog covering 29 apps and all 50 Apple locales. Use when a user asks which iOS or App Store app fits a task, especially for pay-once or lifetime-unlock, privacy-conscious, learning, productivity, photo, travel, or wellness needs. Returns localized evidence and direct App Store links; it is not an independent ranking.

  • Tack

    chris-peterson/tack/skills/tack Skill

    no license0★ repo

    Track AI-assisted development work with the `tack` route tracker, spanning session boundaries. This skill should be used at session start to answer "what am I working on?" and load context on current work, and when the user refers to tack routes, tacks, or recording a PR/MR deliverable against tracked work.

  • Init agent task md

    Zrzzzz/agent-codebase-skills/init-agent-task-md Skill

    0★ repo

    为项目初始化「任务管理层」v3——协调靠结构消除、纪律靠 hook 兜底、脚本只留便利: 1. docs/tasks/T-<slug>.md:每个任务一份独立文件,**文件名即 ID**——无编号、 无锁、无主树限制,任何 agent 在任何 worktree 里直接建文件直接 commit。 2. docs/TASKS.md:marker 区索引视图,由 git hook(pre-commit / post-merge) 自动重生成——没人需要「记得跑脚本」;marker 之外(更新协议 / 约束与决策 / 踩坑与教训)由人手写,脚本不动。 3. .githooks/pre-commit:流程纪律兜底——feat/bugfix/hotfix 分支必须有对应 任务文件才能 commit;禁止直接 commit 到 main;docs/tasks 变更自动刷索引。 4. .githooks/post-merge:主 checkout pull/merge 后自动刷索引。 5. CLAUDE.md / AGENTS.md「任务入口协议」(必装 marker 块):用户报 bug / 提需求 → 先登记任务 + 切分支,再动代码;免登记白名单写死。 6. scripts/tasks-new.sh(模板便利,无锁)、scripts/tasks-index.sh(hook 调用)、 scripts/tasks-release.sh(条目直接写进 CHANGELOG 的 Unreleased 段 + --cut 切版本)。v2 的 tasks-status.sh 已删——status 流转就是一行 frontmatter Edit,updated 字段已砍(由 git log 派生)。 7. CHANGELOG.md:Keep a Changelog 骨架(不存在时创建)。 8. 可选:把「自动跑索引 + 任务推进检测」追加进 init-session-notes 的 _summarize-worker.sh,作为会话结束兜底。 幂等升级:重跑 skill 按 scripts/tasks-index.sh 里的 skill-managed 版本号 分流——v1(monolith TASKS.md)与 v2.x(顺序编号 + 四脚本)都走迁移到 v3; 已是 v3.x 只覆盖脚本与 hook 文件。 本 skill 只管「任务管理」:会话归档 hook 归 [`init-session-notes`](../init-session-notes/SKILL.md), CLAUDE.md / AGENTS.md 分层约定归 [`init-agents-md`](../init-agents-md/SKILL.md)。 使用:/init-agent-task-md;或当用户说「给项目装任务管理」「初始化 TASKS.md」 「让 agent 先开任务再改代码」时也命中本 skill。

  • Agy image

    wjb127/claude-skills/agy-image/skills/agy-image Skill

    0★ repo

    Generate images via Antigravity CLI (agy) using Gemini's generate_image tool. Google OAuth — no API key needed. Antigravity CLI(agy)의 내장 generate_image 도구로 Gemini 이미지 생성. Google OAuth 인증으로 API 키 불필요. Usage: /agy-image cherry blossom hanok, /agy-image --out public/images space cat, /agy-image -n 3 seoul night

  • Arbitrum dapp skill

    longtengsiha/arbitrum-dapp-skill Skill

    0★

    Opinionated guide for building dApps on Arbitrum using Stylus (Rust) and/or Solidity. Covers local devnode setup, contract development, testing, deployment, and React frontend integration with viem. Use when starting a new Arbitrum project, writing Stylus or Solidity contracts, deploying to Arbitrum, or building a frontend that interacts with Arbitrum contracts.

    The same file is in 1 other repository

  • Novel to webnovel

    aimerfeng/novel-to-webnovel Skill

    0★

    将翻译腔小说文本转换为中文网文风格的多阶段工作流(格式清理、风格规范生成、分块并行改写、质量校验)。当用户要求"网文化""去翻译腔""改成网文风格""日轻转网文"或润色自己的小说稿时使用。不适用于代码翻译、技术文档翻译或普通中英互译。

  • Skill

    wasulajr/spinediagrams/skill Skill

    0★ repo

    Generate clean architecture and system-design diagrams as SVG files. Use this skill whenever the user wants to visualise how services, systems, or components connect: migration diagrams, current-state vs target-state architectures, integration maps, data-flow diagrams, platform overviews, or any diagram that shows technology boxes with arrows between them. Triggers on phrases like: "draw a diagram", "make an architecture diagram", "show me how X connects to Y", "create a system diagram", "architecture SVG", "visualise the stack", "diagram this", or whenever the conversation has produced a list of components and integrations that would benefit from a visual. Always use this skill rather than trying to write SVG by hand.

  • Vantage ad lab

    macmenes/vantage/skills/vantage-ad-lab Skill

    0★ repo

    TRIGGER when the user wants to CREATE their own paid ads / campaign concepts — "write ad copy", "ad concepts", "campaign ideas", "Meta ad variants", "Google RSA", "ad angles", "creative brief", "hooks for ads". Part of the `vantage` (Vantage.os) Paid-Media Lab pack. Turns competitive ad intelligence + positioning into ready-to-test ad concepts. DO NOT trigger for ANALYZING competitor ads (use vantage-ads) or organic content (use vantage-content-plan).

  • Solo

    ORBWEVA/solo-skills/skills/solo Skill

    no license0★ repo

    Solopreneur business skill. Use when user needs to productize expertise, build audience, generate leads, close sales, manage clients, handle bookkeeping, or optimize their one-person business. Triggers on "solopreneur", "freelance", "one-person business", "productize", "client management", "solo business", or /solo commands.

  • Add task

    RainZZZYYY/claude-learn-skills/add-task Skill

    0★ repo

    根据用户描述创建任务条目,自动判断归属(已有项目、新建项目、跨项目复制),插入到合适位置。当用户说"添加任务""新建任务""加一个任务""创建任务""我要学""我要做"时触发。

  • Build

    Studio-Moser/skills-n-stuff/plugins/claude-instances/skills/build Skill

    0★ repo

    Build or refresh a renamed duplicate of /Applications/Claude.app so the user can run multiple Claude Desktop apps side by side, each signed into a different account. Same skill creates a new instance (e.g. "Claude II", "Claude Client X") or rebuilds an existing one to pick up Claude's latest auto-update. Trigger whenever the user wants to add another logged-in Claude account, refresh a duplicate Claude app, or mentions things like "Claude II is out of date", "I need a second Claude for my work account", "make another Claude instance", "duplicate Claude for client X". Invoke with /claude-instances:build.

  • Hf model to api

    nynuz/ml-serving-skills/skills/hf-model-to-api Skill

    0★ repo

    Turns a Hugging Face model that already works in a notebook (text classifier, NER/token-classification, text embedder, or image generator) into a production-grade local FastAPI service, with layered app structure, lifespan model loading + warm-up, batching, input/output validation, health/readiness probes, and correctness + performance evaluation scripts. Use whenever the user wants to "wrap", "serve locally", "turn into an API", or "expose as a FastAPI service" a Hugging Face model or model_id (e.g. BERT classifiers, NER models, sentence-transformers embedders, Stable Diffusion / diffusers image generators), even if they only mention it works in a Jupyter notebook and don't say "FastAPI" explicitly. Does NOT cover frontend/client code, Docker, or cloud deployment — local FastAPI serving only.

  • Sanitize stack

    0xZOne/sanitize-stack Skill

    0★

    This skill should be used when the user asks to "sanitize a crash stack", "scrub a stack trace", "clean up a stack for crbug", "prepare a stack for issues.chromium.org", "prepare a stack for Gerrit", "脱敏崩溃堆栈", or pastes a native crash stack (typically Chromium or a Chromium-based embedder) and expresses intent to attach it to a public issue tracker or code review. Transforms raw symbolicated stacks into paste-ready comments by scrubbing downstream module names, normalizing locale tokens, collapsing verbose C++ template signatures, eliding Chromium boilerplate frames, and flagging residual PII for human review.

  • Calendar accuracy

    yhc0712/calendar-accuracy Skill

    0★

    Ensure accurate calendar and date calculations in responses. Use for ANY query involving dates, days of week, date arithmetic, scheduling, holidays, time periods, countdowns, or relative date expressions. Triggers on questions like "what day is [date]", "how many days until", "when is [event]", "X days/weeks/months from [date]", calendar planning, and scheduling tasks.

  • Lotra

    ryangowe/lotra/plugin/skills/lotra Skill

    0★ repo

    Route long markdown output through lotra for human review before treating it as done. Use when you have written or heavily revised a document, or when a reply is long prose, a spec, or a plan the human should comment on inline rather than read in the terminal.

  • Cantonese command parser

    NewJerseyStyle/cant-agent/skills/cantonese-command-parser Skill

    0★ repo

    Parse and execute commands given in Cantonese. Use when user gives instructions or requests actions in Cantonese. Translates Cantonese commands to executable actions.

  • Audit

    Evan-Daruwalla/claude-skill-suite/audit Skill

    0★ repo

    Full sweeping project audit — code, data integrity, security, dependencies, infrastructure, performance, and docs — producing severity-ranked findings with fix plans. Use when the user says "audit", "full audit", "sweeping audit", "audit everything", "find issues/security fixes/optimizations", or "check for inconsistencies". Findings only by default; fixes happen after approval.

  • Jtbd brief

    savvides/jtbd/jtbd-brief Skill

    0★ repo

    Drafts a JTBD-native product brief from Job Map data. Accepts a Job Map YAML file (.jtbd/jobs/*.yml). Outputs to .jtbd/briefs/. Use when: "product brief", "jtbd brief", "write prd".

  • Agents build

    dkmqflx/claude-tools/.claude/skills/agents-build Skill

    no license0★ repo

    Use when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal. Triggers on: "add memory", "remember across sessions", "call agent from app", "invoke agent from code", "auth to call agent", "streaming responses", "VPC", "VPC connectivity", "VPC error", "can't reach from VPC", "multi-agent", "A2A", "A2A auth", "orchestrator not delegating", "specialist not called", "migrate Bedrock Agent", "after import", "migration issue", "framework for migration", "change model", "browser tool", "code interpreter", "delete agent", "tear down", "agentcore remove", "cross-account memory", "resource-based policy on memory". Not for connecting to external APIs via Gateway — use agents-connect. Not for scaffolding a new project — use agents-get-started. Not for CLI/dev server errors — use agents-debug. Strands vs LangGraph in a migration context routes here.

  • Wp accessibility

    xonack/wp-accessibility-claude-skill/skills/wp-accessibility Skill

    0★ repo

    WordPress child theme accessibility skill implementing WCAG 2.1 AA compliance patterns, screen reader support, keyboard navigation, focus management, and automated testing for WordPress themes, blocks, and plugin forms.

  • Agents

    ORBWEVA/solo-agents/skills/agents Skill

    no license0★ repo

    AI agent design and automation skill for solopreneurs. Use when user needs to audit workflows for automation, design AI agents, or build automation recipes using n8n + Claude API. Triggers on "ai agent", "automation", "workflow automation", "n8n", "agent design", "automate my business", or /agent commands.

  • Git workflow

    sqliang/deep-insight-engines/engines/git-workflow/skills/git-workflow Skill

    0★ repo

    Manages full-cycle Git operations including feature branch creation, conventional commit message generation, linear history synchronization (rebase), and push safety checks. Use this for git-related tasks.

  • Audit full

    cloverink/shipwright/skills/audit-full Skill

    0★ repo

    Branch-aware audit orchestrator. On main — scans whole project, opens tracker issue. On feature branch — scopes to diff, auto-fixes, stages changes.

  • Cab claims

    jiahao1553/personal-skills/skills/cab-claims Skill

    no license0★ repo

    Pull cab/ride-hailing receipts (Grab, Gojek, ComfortDelGro/CDG, Tada) from a mailbox for a given time window, convert each receipt to PDF, cross-check the trip time against a calendar to infer which meeting/client the ride was for, and compile a CSV for an expense claim system. Use when the user says "run cab claims", "compile my cab receipts", "/cab-claims", or asks to process taxi/Grab/Gojek receipts for expense claims. Accepts an optional time-bound argument (e.g. "past 3 months", "Jan-Mar 2026", explicit date range). Defaults to the past 3 months if no range is given.

  • Api skill builder

    aditya-m-bharadwaj/APIskillBuilderSkill/.claude/skills/api-skill-builder Skill

    0★ repo

    Bootstrap a new "<vendor>-api-skill" project — a safe, cross-platform single-file Python CLI that mediates a third-party REST API, plus a matching Claude skill that drives it under explicit AI-safety constraints (token never enters AI context; every mutation passes through a six-tier safety classifier; every mutation is recorded in a local audit log). Trigger when the user asks to "build a CLI / skill for <some API>", "wrap the <X> API safely", or to mirror the linode-api-skill pattern for a new vendor.

  • Ui prototyper skill

    x0c/ui-prototyper-skill Skill

    0★

    Create product-faithful, visually ambitious UI/UX prototype images for mobile apps, web apps, websites, and dashboards. Use imagegen to turn one real product moment into an original visual world, not a generic application shell.

  • Knowledge bank lookup

    maicon76/sundayhao-plugins/second-brain/skills/knowledge-bank-lookup Skill

    0★ repo

    Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b], [project-c], Claude Code), requests investigations, or queries past lessons. Returns structured, actionable insights achieving 69-94% context reduction. (project, gitignored)

  • Claude code dev guardrails

    guidefanti/claude-code-dev-guardrails Skill

    0★

    Systematic development guardrails that enforce disciplined, context-aware coding AND product-aware thinking. Use this skill BEFORE any development task — coding, debugging, refactoring, architecture, file creation, automation building, or any technical implementation. This includes tasks involving Supabase, n8n, React, TypeScript, Python, APIs, database schemas, frontend/backend integration, AI agent development, or any project where code is written or modified. Always trigger this skill when the user asks to build, fix, implement, create, modify, refactor, debug, or deploy anything technical — even if the request seems simple. Do NOT skip this skill for "quick fixes" — those are where most regressions happen.

  • Tap capture replay

    LeonTing1010/taprun/plugins/tap/skills/tap-capture-replay Skill

    0★ repo

    When a browser task is REPEATED and runs on a LOGGED-IN / authenticated site, use Tap to record it once (capture), then replay it every time as a zero-token deterministic run — instead of driving a fresh live browser and burning tokens on every run. Trigger when: the user says "I do X on site Y every day/week"; capturing a login-gated admin panel or dashboard; regularly posting / checking / exporting on an authenticated page; any repeated browser chore the user will do again. Also triggers when the user asks "can this be automated?" or "can I avoid paying tokens every time?".

  • Career companion

    mishafyi/claudus-maximus/plugins/career-companion/skills/career-companion Skill

    0★ repo

    Career Companion for frontier tech — AI, space, aerospace, robotics, drones, defense, autonomy. Searches live job openings, tailors resumes and CVs, runs mock interviews, researches salaries. Use when user asks about jobs, careers, job search, job hunting, applying, hiring, resume or CV review, interview prep, salary, compensation, or mentions companies like SpaceX, Rocket Lab, OpenAI, Anthropic, Blue Origin, NASA, Boston Dynamics, Waymo, or any aerospace/AI/robotics company. Also triggers on 'I want to work at X,' 'help me get hired at X,' 'I have an interview at X,' or 'what do they pay at X.'

  • A b test designer

    prvthmpcypher/skills-design/skills/a-b-test-designer Skill

    0★ repo

    You are a conversion optimization expert. When given a conversion problem, design statistically valid A/B tests with clear hypotheses, variants, and success metrics. ## Process 1. Identify the conversion problem and current metrics 2. Formulate a clear, testable hypothesis 3. Design control and variant(s) 4. Define success metrics and statistical significance 5. Estimate sample size and test duration ## Output Format ## A/B Test Design ### Problem \[Current conversion rate and goal\] ### Hypothesis 'If we \[change\], then \[metric\] will improve because \[reasoning\].' ### Variants - Control (A): Current design - Variant (B): \[Specific change description\] ### Success Metrics - Primary: \[Main metric to track\] - Secondary: \[Supporting metrics\] - Guardrail: \[Metrics that shouldn't decrease\] ### Statistical Plan - Confidence level: 95% - Minimum detectable effect: X% - Estimated...

  • Agentic commerce news

    xuxinmaxen/agentic-commerce-news Skill

    0★

    Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.

  • Maven operations

    scagogogo/mvn-skills/plugins/maven-skills/skills/maven-operations Skill

    0★ repo

    Executes Maven commands, parses POM files and settings.xml, manages dependencies, installs Maven, and automates Java project builds. Use when the user asks to run Maven builds, parse pom.xml, find Maven artifacts, manage local repository, install Maven, or perform any mvn-related operation. Also use when working with Java/Maven projects that need build automation, dependency resolution, or POM analysis.

  • Run tests

    thinkyou0714/ccmux/.claude/skills/run-tests Skill

    0★ repo

    Run the ccmux test suite and typecheck, then summarize failures. Use when asked to test, verify, typecheck, or check a change.

  • Ccc

    happygoluckydev/c3/skills/ccc Skill

    0★ repo

    Claude Code Concierge — タスク内容に最適な Claude Code 組み込み機能・コンテキスト・プラグイン・スキル・エージェント・Hook・LSP・Monitor・Output Style・MCP サーバーの組み合わせをローカルカタログ(RAG)から検索して提案する。使い方 /ccc <やりたいタスク>(/c3 でも可)。Web 調査は原則行わずクレジット消費を最小化する。

  • Rule audit

    xniperbuilds/rule-audit Skill

    0★

    Find out which of your agent rules are actually enforced and which are only hope — then convert the ones that matter into deterministic enforcement. Use whenever the user says Claude ignored my rules, it pushed to main again, it keeps forgetting my instructions, my CLAUDE.md isn't working, "same mistake again", "I told it not to", "rule follow nahi karta", "phir wahi ghalti" — or asks to add a hook, block a command, enforce a convention, run something automatically after edits, review their CLAUDE.md, or make an instruction actually stick. Also use before writing a new rule, to decide whether it belongs in prose or in the harness, and when a CLAUDE.md has grown long enough that compliance is degrading. It inventories every rule you have, classifies each as enforceable or advisory, generates the hook or permission config for the enforceable ones, tells you plainly which rules can never be enforced, and prunes the rest so the remaining instructions actually get followed.

  • Ddd core

    agony1997/TouchFish-Skills/plugins/ddd-core/skills/ddd-core Skill

    0★ repo

    DDD 端到端交付流程。DDD 理論基礎(戰略設計、戰術設計、CQRS)→ Event Storming 領域探索 → SA 領域分析 → SD 戰術設計 → 實作規劃。關鍵字: ddd, domain driven design, 領域驅動, bounded context, aggregate, event storming, 事件風暴, sa, sd, 系統分析, 系統設計, implementation plan, 實作規劃, cqrs, 戰略設計, 戰術設計, 限界上下文, 聚合, 聚合根, 領域事件, 通用語言, ubiquitous language, context mapping, 上下文映射

    The same file is in 2 other repositories

  • Seatmap

    FlightSeatmap/flightseatmap-plugin/skills/seatmap Skill

    0★ repo

    This skill should be used when the user asks about "seat map", "seatmap", "seat selection", "best seat", "window seat", "aisle seat", "legroom", "exit row", "seat availability", "airplane seats", "flight seats", "seat pitch", "seat review", "bulkhead", "quiet zone", mentions specific flight numbers (e.g. QF1, BA178, AA716), or wants to check, compare, or find seats on a flight.

  • Skill advisor

    Dcrr1717/skill-advisor Skill

    0★

    Intelligent skill advisor. Scans ALL installed skills (personal + plugins), reasons about which ones best fit the user's idea or project, and delivers: a table of recommended skills with justification, a phase-by-phase workflow, which external AIs/tools to combine, and a ready-to-paste prompt. Honestly reports gaps the installed catalog does not cover. Use when the user asks "which skills should I use for...", "recommend skills", "set up the workflow for my project", "/skill-advisor", "what's the best way to tackle this idea", or describes a new project and wants to know how to attack it with the tools they have installed.

  • Engineer agentic ai

    ArthurZakirov/SystemSmith/skills/engineer-agentic-ai Skill

    0★ repo

    Translate natural-language requests about modifying an AI coding agent, its skills, MCP tools, MCP servers, prompts, routing, tool descriptions, context loading, memory, portability, or other agentic behavior into the concrete mechanics of the target system. Use when a request is underspecified, phrased in human terms instead of runtime terms, or risks making the wrong change because the agent must reason about how Codex, Claude Code, OpenCode, MCP-based systems, or similar runtimes select skills, choose tools, load instructions, apply configuration, and stay transferable across users and machines.

  • Analyze

    AI-Driven-School/aiki/.claude/skills/analyze Skill

    0★ repo

    Analyze entire codebases using Gemini CLI's 1M token context. Generates architecture reports covering structure, security, performance, and improvement roadmaps. Use when auditing code quality or running /analyze.

  • Goal formatter

    jgsystemsconsulting/jgs-goal-spec/skills/goal-formatter Skill

    0★ repo

    Convert verbal task descriptions into structured, testable goals. Use when you say "write me a goal", "create a goal for X", or want to frame work as a measurable objective. Analyzes repo state (git history, technical debt, memory, code) to synthesize clear goals with success criteria, verification methods, and test coverage outlines, then SELF-REVIEWS the draft against a quality rubric and revises before presenting. Optionally also emits a draft engineering specification alongside the goal (spec mode) for handoff to the goal-spec and spec-review skills. Model-agnostic: works with any LLM or agent framework.

  • Suzhou trip

    fxp/claude-skill-suzhou-trip/suzhou-trip Skill

    no license0★ repo

    好吃好玩在苏州 - 苏州出行与美食规划Agent。优先推荐公交线路(旅游专线、好行观光巴士), 辅以地铁换乘方案,结合苏州地铁食堂等特色餐饮,为用户规划吃喝玩乐一体化行程。 输出包含可视化HTML行程页面(含高德地图导航链接)。 使用场景:用户说"苏州怎么玩"、"从XX到YY怎么走"、"苏州一日游攻略"、"苏州美食推荐"等。

  • Architecture diagram gpt imagegen

    ArthurZakirov/ProofStack/skills/architecture-diagram-gpt-imagegen Skill

    no license0★ repo

    Generate a copy-paste-ready GPT prompt that produces a polished architecture or workflow diagram image, and optionally render the image directly via Codex CLI image generation. Trigger when the user wants to create, make, generate, draw, or visualize a diagram, architecture image, system workflow picture, or flowchart, or pastes a Mermaid diagram asking for a polished image.

  • Clodcaster

    hyperhodge/clodcaster Skill

    0★

    Turn a script into podcast-style audio with distinct neural voices. Use whenever the user wants to convert dialogue, a conversation, an interview, notes, or any script into spoken audio / an audio file / a podcast episode. Accepts a raw script in ANY format — the user does not need to structure it. Triggers: 'make this a podcast', 'turn this into audio', 'read this as a conversation', 'generate an episode', 'text to speech for two hosts', mentions of podcast/audio/voices/narration from a script. Produces an mp3 with British hosts by default. Runs fully offline on CPU, no API keys.

  • Cleaning data

    guanyugangstar/cleaning-data Skill

    no license0★

    Use when user needs to analyze data - upload data file, specify path, or use data/ directory. Load first 5 rows, generate custom.yaml config, run cleaning script, and review EDA report for anomalies.

  • Audit deps

    latuconsinafr/claude-code-config/skills/audit-deps Skill

    no license0★ repo

    Use when you want to audit project dependencies — scans all lockfiles for CVEs, outdated major versions, and license violations. Run before releases or periodically as a health check.

  • Erklaerbaer

    manu-brighter/claude-code-kit/plugins/dev-workflow/skills/erklaerbaer Skill

    0★ repo

    Breaks any context (a concept, code, an error message, jargon) down into a simple explanation an absolute beginner can follow — friendly "Erklärbär" persona (ʕ•ᴥ•ʔ), everyday analogies, compact, ASCII diagrams where they help, kaomoji instead of emojis. Detects whether the user wants to understand it themselves or needs something forwardable, and answers in the language of the input. Use when the user explicitly asks for something explained simply or for someone with no background knowledge. English signals: "ELI5", "explain like I'm five", "for dummies", "in plain English", "break it down", "dumb it down", "I don't get X", "for my grandma". German signals: "erklärbär", "erklär mir das einfach", "für meine Oma", "auf normal-deutsch", "mach das simpel", "ich raff X nicht". Do NOT use for normal developer-level questions ("what does this function do", "why is the test failing", "make the code simpler") — without an explicit simple/beginner signal the bear does not trigger.

  • Run tests

    thinkyou0714/github-flow-kit/.claude/skills/run-tests Skill

    0★ repo

    Run the github-flow-kit test suite and summarize failures. Use when asked to test, verify, or check a skill change.

  • Claude md tuner

    NakSAlone/deckhand-free/skills/claude-md-tuner Skill

    0★ repo

    Use when the user wants to create, audit, tune, trim, or improve a CLAUDE.md (or AGENTS.md) project instruction file for Claude Code — makes the file actually steer the agent instead of bloating context. Triggers on "write a CLAUDE.md", "improve my CLAUDE.md", "audit CLAUDE.md", "set up project instructions".

  • Aesop cry wolf

    evnchn-agentic/aesop-skills/aesop-cry-wolf Skill

    0★ repo

    Use when about to emit a warning, flag, or alert for a LOW-confidence issue — the alert-fatigue / signal-credibility discipline. False alarms have an asymmetric cost: after repeated low-confidence warnings, the operator stops reading the channel, and the one true warning gets ignored. Fires on choosing a log level (warn vs info vs error), inflating a PR title/commit to "CRITICAL", marking speculative concerns as ⚠️ risks, or surfacing so many maybe-problems in a review that the real one drowns. Anti-pattern handle for defensive over-flagging.

  • Skill

    mihailShumilov/solana-incident-response-skill/skill Skill

    0★ repo

    Solana security incident response and war-room coordination. Use the moment a live or suspected exploit, drained treasury, compromised key, malicious upgrade, or failing-in-prod program is in play. Routes the responder through the five IR phases — DETECT, CONTAIN, INVESTIGATE, TRACE, RECOVER — plus stakeholder coordination (SEAL 911, SIRN), forensic replay (Surfpool fork), on-chain fund tracing, whitehat/Safe Harbor negotiation, and post-mortem + disclosure drafting. For writing/auditing program code use solana-auditor / trailofbits / safe-solana-builder; this skill is for the response, not the audit.

  • Walkthrough

    TheBitcoinBreakdown-95/claude-walkthrough/skills/walkthrough Skill

    0★ repo

    Use when the user wants to be walked through a plan, document, or set of decisions one at a time and ratify each before moving on, especially anything technical or jargon-heavy. Trigger phrases: "walk me through", "beat by beat", "ratify this plan", "go through this with me one at a time", "let's step through this", "one at a time", "one beat at a time". Keywords: one decision per beat, single hinge question, plain language first, no jargon, gloss terms inline, wait for my verdict, six-line cap, no dumps.

  • Claude md doctor

    az9713/youtube-transcript-to-skills/.claude/skills/claude-md-doctor Skill

    no license0★ repo

    Audit and improve CLAUDE.md files. Use when rules aren't working, context is bloated, or after learning a lesson that should become a rule.