agentsclimarketplace

The catalog

609,856 rows, by stacks then stars

  • Fable

    cookiesheep/fable-skill/skills/fable Skill

    2★ repo

    Turn a concept, domain, or idea into a memorable fable (寓言) — a concrete allegorical story (situation → characters → conflict → resolution → moral) whose moral maps faithfully back to the concept. Use when the user wants to truly understand, teach, or explain something and would benefit from a story that sticks and spreads, rather than a flat explanation. Especially good for abstract, counterintuitive, or "hard to feel" concepts. Not for exact syntax or step-by-step procedures where precision matters.

  • Task match skills

    CosmosHoshigami/task-match-skills Skill

    2★

    Intelligently analyzes user needs from natural language, extracts keywords and domain concepts, searches both locally installed and remote skills via the skills CLI (npx skills find), then presents ranked recommendations with relevance scores and install commands. Helps users discover skills they didn't know existed.

  • Ai engineer

    pablodiazjorge/prompt-forge/.github/skills/ai-engineer Skill

    2★ repo

    On-demand knowledge organization agent. Reviews ALL issues in the registry, deduplicates similar entries, recategorizes unknowns, promotes confirmed patterns (3+ occurrences) to skills or memory files, and cleans up stale single-occurrence issues. Designed to run as a subagent — invoke explicitly when the user says "organize knowledge", "clean up issues", "promote patterns", or "run ai-engineer".

  • Ai seo

    RightBlogger/bloggingskills/skills/ai-seo Skill

    2★ repo

    When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user says 'AI SEO', 'AEO', 'GEO', 'answer engine optimization', 'generative engine optimization', 'optimize for ChatGPT', 'optimize for Perplexity', 'AI Overviews', 'get cited by AI', 'AI citations', or 'optimize for Gemini'. This is about extractability and trust signals, not ranking. For on-page keyword optimization, see seo-optimize. For human-voice editing, see humanize. For SERP and competitor context, see serp-analysis.

  • Business website skill

    ChuluuMGL/business-website-skill Skill

    2★

    Build client-ready corporate, brand, B2B, service,招商,投标, and proposal-grade business websites from source materials, existing static or React/Vite/Next sites, PPT/PDF/image assets, and reference sites. Use when an agent needs to create, refactor, polish, or QA a business website prototype or launch preview with phased discovery, evidence mapping, sitemap/outline, SEO/GEO readiness, design direction options, implementation, delivery checks, and standard/premium/showcase interaction choices. Scoped to the marketing and presentation layer (corporate, brand, B2B, service, proposal, showcase, personal-brand sites); does not build transactional e-commerce (cart, checkout, payments) or application backends needing logins, CRUD, or CMS workflows.

  • Content to prompt

    TravorShelby/content-to-prompt Skill

    2★

    把参考图片、本地短视频、截图、社媒帖子、广告、封面、转写稿、Douyin/TikTok/小红书/Instagram/YouTube/电商素材等反向拆解成可复用的提示词包、分镜、视觉简报、视频特效包装、封面提示词和平台内容模板。用户要求把参考图/视频/账号/封面/广告拆成 prompt、复刻风格但保持原创、提取创意结构、生成图像/视频提示词、构建社媒内容模板时使用。

  • Ha automations

    t3chnaztea/home-assistant-skills/skills/ha-automations Skill

    2★ repo

    Use when writing, editing, debugging, or verifying Home Assistant automations with an agent: "write an automation that...", turn an English description into automation YAML, edit automations.yaml over SSH, an automation that never fires or fired once and went dead, a service call that silently did nothing, testing with automation.trigger, or reloading automations without restarting Core. Covers the write → check → reload → verify loop and the silent-failure traps (event-entity triggers, dead notify services, no-op writes). Not for the initial connection (ha-connect) or price/LLM-driven triggers (ha-external-triggers).

  • Kmd ingest

    yasik/kmd/skills/kmd-ingest Skill

    2★ repo

    The write protocol for a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern) — personal or shared. Use for EVERY write into the KB — distilling a new or scraped source, promoting a finished artifact/report/lesson into the KB, filing a durable learning, insight, or query answer, or correcting/updating an existing page, even a one-line fix. If you are about to create or edit any file inside a knowledge base (a directory with schema.md/log.md, a .kmd.json config, or a kb/ folder), use this skill first; there is no free-form edit path to the KB.

  • Qoory

    qoory-ai/qoory-skills/skills/qoory Skill

    no license2★ repo

    Crypto intelligence Skill for AI coding agents, powered by Qoory MCP and API

  • Ratemycode

    AmsonntagChow/ratemycode/plugins/ratemycode/skills/ratemycode Skill

    2★ repo

    Use this skill to rate, audit, grade, stress-test, red-team, or issue a ship/no-ship verdict on a vibe-coded, AI-built, prototype, or MVP app, repository, or live deployment. Use for Staff-level product and engineering audits; picky-user or adversarial testing; skeptical-VC reviews grounded in product evidence; release-readiness, payment-safety, security, data-integrity, and reliability checks; oral defense or one-question-at-a-time interviews about the product; prioritized fix prompts or requested fixes; and same-rubric re-reviews with score deltas. Trigger for equivalent wording such as rate my code, rate my app, would you ship this, try to break it, roast my app, 挑刺, 答辩, 能上线或能收钱吗, or VC 打分. Require an actual product artifact or concrete product evidence, including the current workspace. Do not use for isolated snippets, routine bug fixing, generic code review, generic startup advice, job-interview prep, or teaching software fundamentals unless the user is evaluating the product itself.

  • Fan poker teaching skill

    Hubujiu/fan-poker-teaching-skill Skill

    2★

    Generate fully custom HTML card worlds inside the Fan Poker Deck Web Component.

  • Accurate

    dustinkeeton/wafflestack/.claude/skills/accurate Skill

    2★ repo

    Machine-legible accuracy — write claims an agent can act on without judgment, and treat documentation as another form of code. Verifies signatures against real exports, paths against the filesystem, counts against a real enumeration, and commands against the manifest that defines them; prefers omission over invention, and never launders an unverified guess as a hedge. A wrong doc is a bug. Use when writing or updating machine-readable docs, registries, API references, or any doc whose claims an agent will act on. Invokable by users and agents.

  • Cashflow review

    bilbop1/moneyprinter-md/skills/cashflow-review Skill

    2★ repo

    Review a completed payable test using cash, delivery evidence, and bounded funnel metrics, then choose one honest stop, revise, repeat, or scale decision. Use after delivery-proof records an observed result.

  • Credit analysis router

    tywinlu1988/Credence-Global/dev/.claude/skills/credit-analysis-router Skill

    2★ repo

    Intake router for vague or compound fixed-income credit-analysis requests such as 'evaluate this company', 'check this portfolio for issues', 'what analysis should I run', 'where to start'. Use when the need is ambiguous, spans multiple roles (Credit Selector/Portfolio Manager/Advisor/Trader/Risk Officer/Individual Investor), or the user asks which analysis to run or where to start. If the user already names a concrete methodology task or engine path, use the fixed-income-credit-analysis skill instead.

  • Code review

    Alex7develop/my-agent-skills/skills/code-review Skill

    2★ repo

    Провести структурированное ревью кода по пяти осям (корректность, читаемость, безопасность, производительность, тесты) перед мержем. Используй при запросах "проверь этот код", "сделай ревью", "посмотри на PR", "готово ли это к мержу". Также применяй проактивно после того как сам написал значимый кусок кода, перед тем как показать его как финальный результат.

  • Loop engineering

    parkavenue9639/loop-engineering/skills/loop-engineering Skill

    2★ repo

    Apply loop-engineering controls to an explicitly goal-directed or skill-invoked request, classify execution risk, assign approval-preserving maker-checker roles, and turn the request into a ready-to-run Codex goal. Use when the user asks to use goal mode, create/start/shape a goal, turn a normal request into an executable loop, decide whether a task is ready for goal execution, or design a bounded delegation and independent-review policy. Do not silently start a goal for ordinary requests unless the user explicitly invokes goal mode or this skill for execution.

  • Bifrost gateway ru

    SiteVisorCloud/bifrost-gateway-integration-skill/skills/bifrost-gateway-ru Skill

    2★ repo

    Направляет КАЖДЫЙ запрос к любой языковой модели / ИИ-провайдеру через шлюз Bifrost (https://your-gateway.example.com), чтобы все вызовы логировались и фиксировались в одном месте. Используй этот навык ВСЕГДА, когда пишешь, настраиваешь или чинишь любой код, который обращается к LLM или ИИ-провайдеру — OpenAI/GPT, Anthropic/Claude, Google Gemini, Mistral или любому другому — на ЛЮБОМ языке (Python, PHP, JavaScript/TypeScript, Go, curl) и в любом фреймворке (LangChain, LlamaIndex, Vercel AI SDK). Сюда входят новые интеграции, правка существующей настройки клиента, конфигурация base_url / api_key, вызовы chat completions, Responses API, embeddings и стриминг. Срабатывай, даже если пользователь просто говорит «вызови gpt-4o», «добавь Claude в этот скрипт», «sk-bf-...», «сгенерируй текст через нейросеть» или упоминает SDK провайдера, но не сам шлюз. НИКОГДА не обращайся к API провайдеров напрямую — весь смысл шлюза в том, чтобы ни один запрос не шёл мимо него.

  • Repository onboarding coach

    LM20230311/repo-confidence/skills/repository-onboarding-coach Skill

    2★ repo

    Analyze unfamiliar repositories and turn code evidence into durable human maintenance confidence. Use when onboarding a developer, taking over a repository, creating or refreshing a project atlas, tracing a business flow, preparing a change-impact brief, teaching someone to maintain a codebase, assessing maintenance readiness, reducing uncertainty before AI-assisted changes, or adding confidence alongside normal development without changing the existing workflow.

  • Teachme chat

    noVaSon/teachme-chat Skill

    2★

    Teach the user a topic through a genuine Socratic dialogue, then distill the shared understanding into a copyable markdown takeaway they keep — no file access needed, works in any chat surface including claude.ai. Domain-open — cooking, law, music theory, statistics, infrastructure, anything — the fit comes from intent, not subject. Use when the user wants to LEARN and RETAIN: "teach me X", "I want to understand Y and write it down", "build me a learning path for Z", "help me get up to speed on W and keep notes", or when resuming such a topic ("continue X", "pick up where we left off", by pasting a prior takeaway). Do NOT use for a one-off explanation the user just wants answered in chat ("what is X?", "explain Y quickly", "remind me how Z works") — answer those directly without this skill. The dialogue asks one question per turn and stops; each concept is captured as a visible in-chat block the moment it is understood, and consolidated into one takeaway summary at the end.

  • Amos sem workflow

    maydengximin-sketch/amos-sem-workflow-skill/skills/amos-sem-workflow Skill

    2★ repo

    AMOS 结构方程建模(SEM)一条龙工作流助手,覆盖从原始问卷数据到论文成文的完整链路:数据清洗(缺失值、异常值、反向计分、Mahalanobis 距离)→ 进入 AMOS 前的"达标预检验"(样本量与 N:p 比、正态性偏度峰度、Little's MCAR、Harman 单因子共同方法偏差、Cronbach's α、KMO 与 Bartlett、EFA、CR 组合信度、AVE 收敛效度、√AVE 与 HTMT 区分效度、VIF 多重共线性)→ AMOS 自动绘图(用 AmosGraphics Plugin 的 VB.NET 代码自动画 CFA/SEM 路径图,自动命名误差项与潜变量、自动画协方差)→ 自动分析(AmosEngine 脚本化建模与估计,免手动点击)→ 模型评估(χ²/df、CFI、TLI、IFI、RMSEA、SRMR、GFI 等拟合指标;修正指数 MI;模型比较)→ 中介与调节效应(Bootstrap 偏差校正置信区间、多群组分析、潜变量交互)→ 结果的 APA 格式文字撰写。触发词包括 AMOS、结构方程、SEM、验证性因子分析、CFA、路径分析、中介效应、调节效应、Bootstrap、拟合指标、模型修正、修正指数、MI、组合信度、AVE、区分效度、共同方法偏差、多群组、AmosEngine、Amos 插件、自动绘图、问卷数据分析。

  • Research rigor

    bsq415/research-rigor-skill/skills/research-rigor Skill

    2★ repo

    Run, recover, audit, or assist a human-led research lifecycle with evidence-gated workflows for question selection, literature and novelty analysis, claim design, theory, experiment design and execution, implementation, reproducibility, result checking, failure repair or scientific redesign, statistics, paper writing and audit, visualization, reviewer response, release, and postmortem. Use when a researcher asks Codex, Claude Code, or another Agent Skills-compatible assistant to autonomously advance authorized work across multiple stages or support one specific stage. Keep the researcher in control of material scientific decisions, interpretation, authorship, ethics, privacy, and conclusions; distinguish engineering readiness from scientific validity and stop at unsupported or human-only decisions.

  • Delphi method

    maydengximin-sketch/delphi-method-skill/skills/delphi-method Skill

    2★ repo

    德尔菲法(Delphi Method / 专家咨询法)全流程方法学助手,聚焦"用多轮匿名专家咨询构建并筛选指标体系"的完整链路。当用户要做德尔菲专家检验的任何环节时使用:判断该不该用德尔菲(vs 层次分析法/问卷调查/焦点小组)、指标初选与初始指标体系搭建、专家遴选(人数、资质、代表性)、咨询问卷设计(Likert 计分、开放意见栏)、轮次设计(几轮、什么时候停)、四大核心统计量计算与解读——专家积极系数(回收率)、专家权威系数 Cr(判断依据 Ca + 熟悉程度 Cs)、专家协调程度(肯德尔和谐系数 Kendall's W + 卡方检验、变异系数 CV)、专家意见集中程度(算术平均值、满分频率);两套指标筛选标准(界值法 / 变异系数-均值法)的公式、判定规则与选择依据;指标增删改的决策与专家反馈;权重确定;德尔菲过程文档与论文方法章写作;审稿与答辩高频质疑应对。触发词包括"德尔菲""德尔菲法""Delphi""专家咨询""专家检验""专家打分""指标体系构建""指标筛选""肯德尔和谐系数""Kendall W""协调系数""变异系数""满分频率""专家权威系数""专家积极系数""界值法""两轮咨询""指标剔除""专家意见集中度"等。工具中立(SPSS/Excel/R/DView 皆可),覆盖从"要不要用德尔菲"到"最终指标体系成文"的全过程。

  • Reviewing reports with five lenses

    jasperkong1996xx/decision-gauntlet/skills/reviewing-reports-with-five-lenses Skill

    2★ repo

    Use when a report, proposal, business case, project update, presentation, or executive decision needs adversarial review, assumption testing, opportunity discovery, outsider clarity checks, or concrete next actions before approval, presentation, go/no-go, or stakeholder review. Also use for 汇报、方案、PPT、商业案例和决策材料评审.

  • Adjust inventory

    skuio/sku-skills/dist/claude/inventory/adjust-inventory Skill

    2★ repo

    Adjust the on-hand quantity of a product at a warehouse in SKU.io — an increase, a decrease, or a set-to-value. Use this for stock takes, corrections, damage/shrinkage write-offs, or found stock. Resolve the product with find-product first so the adjustment targets the right product and warehouse.

  • Broken resource skill

    AmsonntagChow/ratemyskill/evals/fixtures/broken-resource-skill Skill

    2★ repo

    Use this skill for invoices, finance, writing, business questions, and checking documents.

  • Perplexity

    Elnora-AI/elnora-websearch-tools/skills/perplexity Skill

    2★ repo

    Web-grounded Q&A with citations via Perplexity's Sonar API. Use when the user says "ask perplexity", "get an AI answer with citations", "web-grounded answer", "answer with sources", "reason about" / "compare" / "evaluate tradeoffs" over live web data, or "deep research" / "literature review" / "comprehensive investigation". The Sonar models search, synthesize, and cite in a single call — reach for this over raw result lists when you want a written answer backed by sources. Bundled curl-based skill (Perplexity ships no official CLI or Agent Skills).

  • Agent motivation

    erdemuk/agent-motivation Skill

    2★

    Persistence mode for unfamiliar, underspecified, failure-prone, or loop-prone tasks. Use when work may not match common examples, attempts keep failing, requirements are sparse, the path is novel, or the agent may drift toward a familiar adjacent task instead of the user's actual outcome. Trigger especially before saying "this seems unsupported", "let me try a simpler approach", "I'll use the older API instead", or "this may be impossible". Also use when writing prompts or skills that need internal drive without repeated user encouragement. Do not use for quick single-answer questions with no multi-step work.

  • Assumption mapping

    risadams/ink-and-agency/skills/business-product/assumption-mapping Skill

    no license2★ repo

    Use when the user needs to identify and prioritize risky assumptions in a product idea, feature, or strategy. Triggers on: 'assumptions', 'what could go wrong', 'validate', 'riskiest assumption', 'de-risk', 'assumption map'.

  • Fal lora inference

    shahshrey/fal-portrait-lora-skills/skills/fal-lora-inference Skill

    2★ repo

    Generates and evaluates images from a trained portrait LoRA using fal-ai/flux-lora, including LoRA scale sweeps, local image downloads, and review contact sheets. Use when the user asks to run inference, generate, render, sample, or test images from a LoRA; to check likeness or whether a LoRA is overtrained; or mentions flux-lora, lora_scale, safetensors weights, a trigger phrase in a prompt, guidance scale, image_size, or seeds.

  • Zuiti jiafang

    SilentFleetKK/zuiti-jiafang Skill

    2★

    嘴替·甲方包——专治甲方/客户用话术压价、加需求、拖款、无限改稿。把甲方那句噎人的话丢进来,它先翻译潜台词(他到底想让你免费垫什么),标误读风险,再给三档可以直接发出去的回复(体面版 / 绵里藏针版 / 掀桌版),最后给长期策略和发送建议。命中场景:小改动很简单、顺便加一下、别人家更便宜、款在走流程、改回第一版、上线时间不变、都合作这么久了、先做起来、这个不难吧、你效率高、走个内部价、下次一定、量大从优、朋友价、试试水、看看效果再说。只要用户贴出甲方/客户发来的消息,抱怨"这需求怎么回""被压价了""又要改""款还没到怎么办""不知道怎么拒绝甲方",都应主动使用本 skill。

  • Knowledge capture

    kricha/knowledge-capture/skills/knowledge-capture Skill

    2★ repo

    Use after coding, debugging, investigations, architecture discussions, code reviews, handoffs, /capture requests, or context compaction to save one local raw Markdown capture with decisions, evidence, changes, and next steps.

  • Memory

    linellazatin/openclaude-memory/skills/memory Skill

    2★ repo

    Read and write global persistent memory across opencode sessions

  • Cheat engine cli

    chengyixu/cheat-engine-cli-skill/skills/cheat-engine-cli Skill

    2★ repo

    This skill should be used when the user asks to use Cheat Engine CLI or cecli, automate Cheat Engine from a terminal, scan or read process memory, connect to ceserver, inspect a local macOS or Windows process, preview an authorized memory write, or says “命令行扫描内存”, “读取进程数值”, “修改单机游戏数值”, or “连接 ceserver”. It guides safe target selection, JSON-first inspection, exact scans, typed reads, and confirmation-gated writes for authorized processes.

  • Skill doctor

    KyTiXo/skill-doctor Skill

    2★

    Audit a skill against Pocock's write-a-skill spec and return a prioritized, diagnose-only fix report.

  • Linggan talking cards

    yihui-dev/linggan-talking-cards/skills/linggan-talking-cards Skill

    2★ repo

    将中文或英文口播文案与可选截图拆成 3–10 张 PPT 式演示卡片,输出文字准确的 PNG 卡片、结构化 manifest 和带逐卡口播台词的响应式 HTML 预览页。支持 3:4、16:9、9:16、4:3 四种比例,以及苹果白色毛玻璃、糖果、Obsidian、新丑风等 10 种视觉系统;适用于“口播文案拆解PPT生多图”“把逐字稿做成卡片”“给口播配 slides”“截图放进讲解卡片”“生成多图和预览页”“换一种 PPT 风格”以及修改指定卡片的请求。

  • Momo tools

    jordannn02/momo-tools/plugin/skills/momo-tools Skill

    2★ repo

    Route an AI agent task through a local capability index, risk gates, action gates, and verification levels before choosing tools. Use when the user asks which tool/skill/plugin/connector/script to use, wants a capability dashboard, or needs a safe workflow for work that could touch files, private data, credentials, external services, browser state, automation, or persistence.

  • Idea spark agentic

    yysxjz/idea-spark-agentic Skill

    no license2★

    Agentic variant of idea-spark. Generates ONE reviewer-defensible, implementable research idea from a stated direction. Phase 0 and Phase 3.1 retrieval use Claude Code native WebSearch/WebFetch sub-agents instead of API connectors - no .env file or API keys required. Reuses the same 5-phase pipeline and ideation-pattern vocabulary as idea-spark.

  • Annotate screenshots

    madeyexz/annotate-screenshots/skills/annotate-screenshots Skill

    2★ repo

    Capture or transform screenshots into honest, deterministic annotated images using matched raw PNGs plus Sharp-composited SVG labels, outlines, arrows, and callouts. Use for PR before/after comparisons, product-change evidence, UI walkthroughs, bug reports, or requests to highlight differences in screenshots without generative image editing.

  • Building mental maps

    varadfromeast/Vskills/building-mental-maps Skill

    2★ repo

    Build and maintain a living Obsidian codebase atlas. Use for whole-system orientation, planned mapping from issues, PRDs, or ADRs, or synchronization from PRs, commits, diffs, or working-tree changes.

  • Actually legible

    Chillsbro/actually-legible Skill

    2★

    Architectural taste for TypeScript and React coding agents. Minimize conceptual surface area, preserve clear dependency direction, and produce code humans can navigate, review, and evolve. Use when implementing, refactoring, reviewing, scaffolding, or organizing TypeScript and React code, including modules, imports, exports, folders, files, functions, components, hooks, naming, and comments.

  • Addictive writing

    MarcoWorms/addictive-writing Skill

    2★

    Drafts, rewrites, and reviews prose and scripts for earned attention using clear stakes, question-driven momentum, causal progression, expectation-and-reveal, re-hooks, rhythm, conversational tone, distinctive story lenses, purposeful endings, and medium-appropriate hooks. Use when the user asks to make writing more compelling, gripping, page-turning, bingeable, high-retention, suspenseful, or engaging; diagnose hooks, pacing, narrative tension, story structure, transitions, or reader drop-off; or improve fiction, nonfiction, articles, essays, newsletters, speeches, presentations, sales narratives, video scripts, podcasts, and social content without sacrificing truthfulness or the author's voice.

  • Coding style

    26zl/universal-agent-skills/skills/coding-style Skill

    2★ repo

    Keep code comments and docstrings concise, neutral, human-authored in tone, and written in English unless another language is required. Use when writing, refactoring, or reviewing code where comments, identifiers, or docstrings may be added or changed; do not use to shorten required public API documentation, safety notes, or legal notices.

  • Issue flow

    asanabrial/issue-flow Skill

    2★

    Trigger: issue-flow analyst [conditions], issue-flow dev, analyst, developer, claim issue, move task states. Analysts file at most one evidenced issue; without conditions, audit the repository critically.

  • Portable skill

    daijx66-crypto/skillwitness/examples/portable-skill Skill

    2★ repo

    Validate a synthetic Agent Skill when testing SkillWitness locally or in CI.

  • Bluebook review

    yonathanarbel/legal-ai-skills/bluebook-review Skill

    2★ repo

    Review and correct legal citations in Microsoft Word DOCX manuscripts using the current Bluebook Style — Epps Version guide and CSL implementation from danepps/bluebook. Use for law-review footnotes, citation audits, first and short forms, Id. and supra usage, pincites, source-type formatting, signals, parentheticals, typography, Zotero citation fields, and delivery of a reviewed or redlined Word document. This skill applies the Epps materials, not the proprietary official Bluebook, and must not invent missing citation metadata.

  • Readme

    thuanvd378/write-me-a-readme/plugins/write-a-readme/skills/readme Skill

    2★ repo

    Create, redesign, audit, or update a repository README.md by inspecting the actual project; write accurate setup and usage guidance with a selectable brand voice, polished information architecture, evidence-based badges and claims, discoverability suggestions, and an optional editable SVG/PNG banner. Use when the user asks for a README, README refresh or audit, repository landing page, GitHub presentation or SEO improvement, tone/style rewrite, social preview, or README banner. Do not use for unrelated documentation or generic marketing copy.

  • Architecture for comprehension

    batteryshark/skill-tap/skills/development/architecture-for-comprehension Skill

    2★ repo

    Evaluate and map a repository's architecture for coherence, discoverability, predictable execution paths, local reasoning, onboarding friction, accidental complexity, and cognitive load. Use for system-level architecture reviews, newcomer usability probes, repository legibility scorecards, or requests to make a codebase easier to understand as a whole.

  • Kaspi skill

    sw1pp3r/kaspi-skill Skill

    2★

    Live Kaspi product search, seller-level delivery verification, decision-ready comparison, and official app QR codes for Claude Code and Codex. Use when the user invokes /kaspi or $kaspi; says "найди на Каспи", "подбери на Kaspi", or "сравни товары"; asks what can arrive today, tomorrow, by express, or by a date; or wants a current price, availability check, shortlist, or best-value choice on Kaspi in Kazakhstan.

  • Pw playwright fieldkit

    jpbaking/playwright-fieldkit/skills/shared/pw-playwright-fieldkit Skill

    2★ repo

    Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, and test live sites via deterministic scripts; portable Agent Skill for Codex, Claude Code, Antigravity, and Cline

  • Extract youtube creator transcripts

    yanyi8171/extract-youtube-creator-transcripts/skills/extract-youtube-creator-transcripts Skill

    2★ repo

    一键导出指定 YouTube 博主或频道当前公开的长视频、Shorts 和直播回放字幕,保存为带时间轴的 SRT 与清洗后的 Markdown,并支持断点续跑和增量补齐。用户提到“导出博主全部字幕”“YouTube 逐字稿”“批量转 MD”“补齐频道字幕”“更新博主字幕库”“下载 Shorts 字幕”时都应使用本 Skill;不要用于只处理单个本地字幕文件、下载视频画面或绕过会员与地区权限。Export all currently public transcripts from a YouTube creator or channel, including videos, Shorts, and stream replays. Use for bulk transcript export, SRT and Markdown generation, incremental updates, or creator transcript archives.

  • Shell

    posidoni/shell-skill/skills/shell Skill

    2★ repo

    Load before running or writing ANY shell — including throwaway one-liners you intend to run yourself, not just scripts you save. Trigger on the act, not the request: you are about to type awk, sed, cut, or a second pipe; you are parsing du/ps/ls/find output; a command needs a loop, a conditional, or arithmetic; you are writing $(...) inside another $(...); you need a file list, sizes, or process info; you are choosing a shebang or an interpreter; a command exceeds one line or will outlive this session; output must be machine-read, or must separate data from diagnostics; you are editing a Makefile recipe, Dockerfile RUN, CI run: block, cron entry, or .env; or you are reviewing or debugging shell someone else wrote. Answers "should this be shell at all?" first — usually jq, yq, sd, nu, Python or bun — then applies the Bash/Zsh/POSIX/Nushell safety rules to whatever survives that question.

  • Newshub skill

    RobinZorro86/newshub-skill Skill

    2★

    Fetch, rank, and summarize current AI, tech, world, business, and ecommerce news from curated or custom RSS/OPML sources. Use for news briefings, AI updates, eBay/Etsy/Shopify seller updates, ecommerce scans, or source monitoring. Do not use for historical questions, single-page summaries, authenticated social scraping, publishing, or investment advice.

  • Diagnose use case

    rajshah4/ai-framing-skills/diagnose-use-case Skill

    2★ repo

    Use when the user has an AI system that is already running (production, pilot, or serious testing) and wants to know why it underperforms, whether it's actually working, or whether to keep going, change course, or kill it. Triggers include "why isn't this working", "metrics are flat", "users aren't adopting it", "should we keep investing in this", or any post-launch review. For projects not yet built, use frame-use-case instead.

  • Autonovel consistency pass

    DukeTwoCan/autonovel-agent-skills/skills/creative/autonovel-consistency-pass Skill

    2★ repo

    Autonovel Phase 3b.1 — cross-chapter consistency review focused on character voice, plot, world rules, and repeated phrasing. Builds a rolling chapter summary then windows over the manuscript in 4-chapter groups, emitting per-window critique and merging into critique/consistency.md. Hands targeted fixes back to autonovel-revision. Max 2 cycles. Designed for the 27B/65k local-model envelope — never loads the full manuscript at once.

  • Expert mode

    TanKucukhas/expert-mode-skill/skills/expert-mode Skill

    2★ repo

    Turns vague "act as an expert" requests into fully-specified expert engagements. Builds a precise expert persona — specific role and seniority, industry and domain context, named methodologies, real operating constraints, and a required output format — then executes the task in that mode, or produces a reusable expert prompt the user can run anywhere. Use whenever the user wants expert-level output, asks you to "act as", "think like", or "answer as" a professional, wants a consultant-grade deliverable (audit, strategy, review, analysis, plan), complains that answers feel generic, or says "/expert-mode". Works in Claude Code, Claude Desktop, Claude Web, and any agent that supports the Agent Skills format.

  • Branded pptx

    dzivkovi/agent-skills-on-databricks/skills/branded-pptx Skill

    2★ repo

    Turn a markdown document into a branded PowerPoint (.pptx) deck: a title slide from the H1, one content slide per H2, bullets from list items, with a light brand skin (accent colour + footer). Pure-Python (python-pptx), runs on Databricks Free Edition serverless - no Node, no LibreOffice. Use when you need a real .pptx from markdown without a design toolchain. Triggers: 'make a deck', 'markdown to powerpoint', 'branded pptx', 'slides from this doc', 'pptx from markdown'.

  • Branch done

    dkmqflx/git-workflow-plugin/plugins/git-workflow/skills/branch-done Skill

    2★ repo

    Delete the current feature branch and switch back to the base branch after opening a PR. Use when the user has just opened a PR and wants to clean up — phrases like "PR 올렸으니 정리해줘", "브랜치 정리해줘", "정리하고 돌아가줘", "clean up this branch", "delete feature branch", "/branch-done". Do NOT use inside a git worktree — that is the worktree-done skill.

    The same file is in 1 other repository

  • Skills by JusDots Devs

    shubh72010/skills-by-JusDots-Devs Skill

    2★

    Forces exploration from multiple independent thinking directions before producing conclusions. Uses a five-phase workflow (primary exploration, independent domain exploration, cross-pollination, challenge, synthesis) to avoid tunnel vision, anchoring bias, and superficial ideation. Triggers on "brainstorm", "explore this topic", "think about", "discuss from multiple angles", or when the user explicitly requests divergent thinking.

  • Develop academic paper

    ylzjpky/vibe-academic-writing/plugins/vibe-academic-writing/skills/develop-academic-paper Skill

    2★ repo

    Plan, research, draft, cite, review, synchronize course materials, and export source-grounded academic assignments. Use for pasted or uploaded briefs; one-off tasks; long-term course workspaces; public, institutional-library, or authorized LMS research; course-material sync/resync; APA, Chicago, MLA, Harvard, or custom citations; Word/PDF delivery; and evidence or citation audits.

  • Ai feature go no go

    Abhillashjadhav/PM-agent-OS/.claude/skills/ai-feature-go-no-go Skill

    no license2★ repo

    Strategy-stage skill: turns an AI-feature idea plus context into a build/kill decision that names the single criterion it turns on. Use when the user asks for a go/no-go, build-or-kill, or ship-worthiness call on an AI or LLM-powered feature — 'should we build AI auto-replies', 'build or kill: LLM search', 'make the call on this AI feature' — or when /pm routes such a request here. Do NOT use for non-AI feature prioritization, for mapping assumptions without deciding (assumption-mapper), for model/vendor selection, or for launch-timing decisions.