agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Agrivalue iq operator

    cdm227/AgriValue-Tracker/.agents/skills/agrivalue-iq-operator Skill

    0★ repo

    Operates AgriValue Tracker as an interactive AI agent workflow. Use when testing the challenge demo, running value-chain optimization, asking the AI Harvest Advisor, generating Fair-Trade contracts, preparing Copilot MCP prompts, or validating Fabric IQ, Foundry IQ, and Work IQ flows.

  • Yang weibo book notes

    tianyayu6/yang-weibo-book-notes Skill

    0★

    为“阅读思考写作-每日不坠”账号创作、改写和润色中文微博与读书笔记,保留其从事实出发、分析机制与利益约束、承认不确定性、克制落下个人判断的表达方式。用户提到写微博、微博评论、转发语、热点观点、读书笔记、书评、阅读感想、把素材写成文章、模仿其既有账号风格或要求“按我的风格写”时使用。

  • Ithildin agent

    Madwr1d/ithildin-agent Skill

    no license0★

    Use to drive Ithildin (a Swiss operations portal) from the terminal — manage sales leads, run a cold-call queue and log outcomes, fill a task planner, and read finance summaries. Use whenever the user wants an agent to operate their Ithildin workspace (add leads, work the dialer, schedule tasks, check net worth) instead of clicking the web UI.

  • Sheepdog audit

    filipores/sheepdog/skills/sheepdog-audit Skill

    0★ repo

    Whole-repo audit for architecture boundary drift: god orchestrators, layer violations, misplaced side effects, persistence leaks, pattern fragmentation, and dependency-direction problems. One-shot report; no edits.

  • Session to skill

    Eldorado-ling/session-to-skill Skill

    no license0★

    从 OpenCode 会话分享链接中提取可复用模式,自动生成符合 SkillHub TRACE 评测体系和安全三线审核标准的可发布 Skill,并打包为 ZIP。用户在完成项目后新开会话,粘贴 share URL 即可触发。

  • Loam initializing vault

    scchearn/loam/skills/loam-ground/loam-initializing-vault Skill

    0★ repo

    Scaffold a new Obsidian vault with pre-configured settings, keymaps, and core plugins. Use when the user wants to "set up a new Obsidian vault", "create an Obsidian vault", or "replicate my Obsidian setup".

  • Extract health data

    OpenBioHack/openbiohack/skills/extract-health-data Skill

    0★ repo

    Turns raw health materials (PDFs, scanned documents, images, spreadsheets, exported files) into two layers: first a faithful, fully traceable extraction of each source; then a set of cross-source compiled views (timeline, lab-trends, and others) built once for pattern-spotting without re-burning tokens. Every item traces back to a verbatim source quote. Reorganises data; never interprets, concludes, or flags. Use when handed raw health materials that need to become structured, traceable, pattern-ready data before any analysis. Called by /investigate-health Step 1, or directly when extraction is the whole task. Triggers: "extract this data", "process these records", "pull the values out of these PDFs", "/extract-health-data".

  • Safe multi session deploy

    Madwr1d/safe-multi-session-deploy Skill

    0★

    Use BEFORE committing or deploying any repo that multiple Claude/agent sessions may share (Vercel/Railway/Node web apps). Prevents the three failure modes of concurrent sessions on one working tree — clobbering another session's unsaved work, deploying to the WRONG linked project, and not knowing which session's build is actually live. Stamps a session-tagged build provenance marker and verifies it post-deploy.

  • Flowthis

    Mario-Vishal/flowthis-visual-skill/skills/flowthis Skill

    0★ repo

    Turn conversations, documents, PDFs, research papers, repositories, architecture notes, product ideas, ads, user stories, debug timelines, PR summaries, or other context into polished FlowThis-owned self-contained HTML visuals. Use when the user says things like "visualize this", "make a FlowThis visual", "save this as a visual", "turn this document into a visual", "diagram this repo", "create a research paper visual", or runs /flowthis. Provides visual briefs, source-type routing, component recipes, evidence rails, no-JS interaction patterns, quality gates, and diagram guardrails when the user does not specify a layout.

  • Hermes skill web3marketing

    web3blind/hermes-skill-web3marketing Skill

    no license0★

    Use when the user invokes /web3m or asks to build, audit, diagnose, position, launch, or grow a Web3, Web2.5, crypto-adjacent, DeFi, NFT, DAO, infrastructure, devtool, or AI-for-crypto project using Web3 GTM, funnel, community, positioning, channel, landing-page, or retention strategy.

  • Skill

    alexbanda08/solana-auditor-skill/skill Skill

    0★ repo

    Solana/Anchor program security audit workflow - scope the attack surface, run static analysis (cargo-audit/clippy/deny/geiger), manual vuln review (signer/owner/PDA-bump/PDA-sharing/CPI/overflow/type-confusion/close-revival), dynamic analysis (litesvm PoC, fuzzing), and severity-graded reporting; use when asked to audit, security-review, find vulnerabilities in, or write a findings report for a Solana program.

  • Rabbit hole

    dd3ok/rabbit-hole Skill

    0★

    Use for unfamiliar code, new APIs, papers, prototypes, vague features, or root-cause debugging. Create a small verified artifact before full implementation.

  • Skills

    genie360s/grant-application-skills/skills Skill

    0★ repo

    Expert support for writing, strengthening, and reviewing any funding or opportunity application — grants, fellowships, scholarships, prizes, awards, accelerators, residencies, RFPs, calls for proposals, concept notes, cover letters, budgets, and pitch decks. Use this whenever the user says anything like "I'm applying for a grant / fellowship / funding / opportunity", "help me write my proposal", "review my application", "draft a concept note", "build my budget", "answer this funder question", or shares a call/RFP/eligibility text and wants help responding to it — even if they don't say the word "grant". It blends proven fundraising, storytelling, and persuasion frameworks with a disciplined fit-and-criteria check so the application is tailored to the specific funder, answers the actual questions, stays within the rules, and keeps the applicant's authentic voice and honest claims.

  • Site visibility report

    timofeiryko/site-visibility-report Skill

    0★

    Generate a polished, client-ready SEO / GEO / AEO website "visibility" report (standalone HTML + PDF) for any URL. Runs live measurement scripts, an AI-visibility benchmark across AI engines (ChatGPT/Perplexity/Gemini/Google AI Overviews), and automatic competitor analysis, then assembles a 12-section flagship HTML report and a 9-section PDF. Use whenever the user wants to audit a site's search + AI visibility, build a "витрина" / showcase report for a prospect, analyze how well a site is found by Google and cited by AI engines, benchmark a site vs competitors on SEO/GEO/AEO, or asks "почему сайт не находят", "проверь SEO/GEO", "сделай отчёт по сайту".

  • Ultraindex

    maxgfr/ultraindex/skills/ultraindex Skill

    0★ repo

    Use when an AI agent must UNDERSTAND a big repo, not merely search it — and its claims must be provable. ultraindex is the verified knowledge layer over codeindex, the deterministic zero-dep engine it vendors: codeindex tells you WHERE things are, ultraindex tells you what they MEAN and proves it. It builds an encyclopedia (a small always-loadable INDEX.md plus per-module entries): generated regions rebuild every time, human regions hold YOUR cited analysis, preserved across rebuilds and renames. dossier/ask hand you real source to write from; check REJECTS any [file:line] citation that does not resolve; verify proves each cited excerpt supports its claim. status is the enrichment work-queue, orchestrate fans it out to subagents. Triggers: index/map/document/analyze this codebase, where is X handled, how does Z work in this repo, which files do I change for Z, review this branch/PR, this repo is too big for context. Want plain code search, no model in the loop? Use codeindex directly.

  • Launchclip

    rogerchappel/launchclip Skill

    0★

    Create reviewable launch videos and OSS promotion packets from repositories, products, briefs, and media.

  • Hermes skill risk radar

    web3blind/hermes-skill-risk-radar Skill

    no license0★

    Узкий X/Twitter risk radar по выбранным DeFi-проектам. Use when нужно вручную или по cron проверить новые risk-упоминания по Hyperliquid и xStocks и прислать только короткие сигналы.

  • Baseline ui

    kindaidai/agent-skills/skills/baseline-ui Skill

    no license0★ repo

    Enforces an opinionated UI baseline to prevent AI-generated interface slop.

    The same file is in 30 other repositories

  • Linkedin posting skill

    Imasaikiran/linkedin-posting-skill Skill

    0★

    The complete operating system for posting on LinkedIn. Use this skill for anything about LinkedIn posts, profiles, or growth: what to post, when to post, how often, writing the post, hooks, carousels, content calendars, building a personal brand, growing a following, getting more reach or comments, or studying what top creators do. Covers global and India audiences. Triggers include "LinkedIn post", "post on LinkedIn", "LinkedIn strategy", "grow on LinkedIn", "best time to post", "LinkedIn content", "LinkedIn hook", "personal brand on LinkedIn", "go viral on LinkedIn", "LinkedIn carousel", "thought leadership".

  • Kometa config core

    nichtlegacy/kometa-skill/skills/kometa-config-core Skill

    0★ repo

    Use whenever the user needs `config.yml` created, repaired, or explained, including connectors, library mappings, file blocks, root settings, file schedules, library schedules, overlay scheduling, operations, and root playlist wiring. Use this skill aggressively for any Kometa request that mentions `config.yml` or top-level service setup.

  • Xxtrade agent

    Madwr1d/xxtrade-agent Skill

    no license0★

    Use to read xXTrade (Hyperliquid perps) market and account data from the terminal — top markets by open interest, a coin's mark price, and the open positions / account value for a wallet address. READ-ONLY (no trading). Use when an agent needs live perp prices, funding, OI, or to check a wallet's positions on xXTrade.

  • Agentic quality gates

    g-shevchenko/agentic-quality-skills/skills/agentic-quality-gates Skill

    0★ repo

    Use before non-trivial agentic, coding, workflow, tool, automation, release, or public-surface work, and when the user says quality gate, acceptance gate, red flags, risk gate, architecture gate, decision handoff, side-effecting workflow, contracts first prompts last, prompt-only fix, human gate, or release gate. Classifies risk, defines deterministic acceptance gates, catches red flags, and decides whether to proceed autonomously or ask a human.

  • Fusion

    Neznakometz/StackForge/analytics/skills/fusion Skill

    0★ repo

    Multi-model generation — run a task through several models (Claude + Codex/ChatGPT + Gemini) and synthesize the best answer. Apply to complex non-technical/research tasks where different points of view are valuable.

  • Open source octopus investigation

    thdelmas/open-source-octopus-investigation Skill

    0★

    Discover relevant open-source projects and contributors by crawling GitHub social graphs (stars, follows, contributions) from an origin, organizing findings into thematic 'tentacles', logging every profile/repo to a dedup tracker, and optionally filing issues. TRIGGERS: 'open source octopus investigation', 'octopus investigation', 'octopus search', 'octopus this', 'crawl the social graph', 'map the open-source landscape from <user>', 'who's connected to <github-user>', 'find projects like <repo> via stars/follows', 'technology scouting for <domain>'. Use when the user wants graph-based discovery (following human curation) rather than keyword search.

  • Hermes skill web3 risk check

    web3blind/hermes-skill-web3-risk-check Skill

    no license0★

    Web3-specific risk screening for dApp domains, protocol pages, token contracts/mints, and project legitimacy. Use when the user asks whether a crypto/Web3 project, dApp URL, token, contract, or protocol looks risky, scammy, unaudited, illiquid, honeypot-like, or worth adding to a portfolio risk workflow.

  • Weblica

    feast107/Weblica/skills/weblica Skill

    0★ repo

    基于 CloakBrowser 与 Agent-in-the-Loop 的智能 Web 应用克隆复现工具,支持人机协作登录、深度优先遍历与本地离线 replay。

  • Context synthesis

    QiRebecca/Agentdemo/skills/context_synthesis Skill

    0★ repo

    From-scratch agent runtime with task graphs, multi-index RAG, memory, typed tools, reusable skills, handoffs, traces, and smoke tests.

  • Create pipeline

    glassflow/agent-skills/skills/create-pipeline Skill

    0★ repo

    Use when the user asks to create a GlassFlow ETL pipeline. Walks through source configuration (Kafka or OTLP), optional dedup/filter/transform stages, and ClickHouse sink mapping, then submits the v3 config to the GlassFlow API. Triggers on phrases like "create a pipeline", "set up a Kafka to ClickHouse pipeline", "ingest logs from OTLP into ClickHouse".

  • Cursor seo router

    khymerao/cursor-seo/skills/cursor-seo-router Skill

    0★ repo

    Entry point for all SEO work in Cursor. Replaces upstream claude-seo /seo slash commands. Use when the user asks for an SEO audit, page analysis, technical SEO, E-E-A-T content review, schema markup, GEO/AI-search optimization, sitemaps, image SEO, local SEO, maps intelligence, keyword clustering, SXO, drift monitoring, e-commerce SEO, hreflang, Google API data (GSC, PageSpeed, CrUX, GA4), backlinks, or live DataForSEO data.

  • Auto skill installer

    harrylabsj/auto-skill-installer Skill

    no license0★

    Understand a user or agent capability need, discover relevant Codex/agent skills, choose the best candidate, install it, and verify the installation. Use when a user asks what skill to install, asks to automatically find/install skills, describes a task that may require a missing specialized skill, or when an agent notices it lacks a reusable capability during a task.

  • Linktwerk

    Vitrehac/linktwerk Skill

    0★

    Transforms boring sentences into cringe-maximalist LinkedIn thought leadership posts. Use when the user says linktwerk, linktwerk it, wants a LinkedIn post from a plain message, or asks for cringe inspirational thought leadership.

  • Seamkeeper

    knowledgeco/seamkeeper Skill

    0★

    Maintain continuity of design intent across coding sessions and across different AI models or thinking budgets, so a codebase reads as one authored work — "Software Program V1.45" — rather than a stitched-together anthology of fragments by different hands. While authoring, it prevents new "seams"; while auditing, it honestly patches existing ones. Use this whenever writing, editing, refactoring, or auditing code that will be touched across more than one session — ESPECIALLY when the model, thinking budget, or author may change between sessions (a reset, a model swap, a budget-limited run, a "free model today" detour). Seams include: idiom drift, defensive scar tissue at boundaries, the same problem solved two ways, and — most dangerously — latent fault-lines where an implicit contract (e.g. "this input is already validated") died with the reasoning that produced it, compiles fine, passes the happy path, and breaks on the edge nobody had budget to consider. Trigger this when picking up code from a previous session or another model, when auditing or refactoring an unfamiliar codebase, or any time you want the repository itself to carry the "why" so future readers (human or AI) can recover intent instead of guessing — even if the user never says the words "continuity," "seams," or "ledger."

  • Bank proposal generator

    himanisharrma/finverge-sales-skills/plugins/finverge-sales-skills/skills/bank-proposal-generator Skill

    0★ repo

    Generate tailored bank proposals for FinVerge products (NACH, PG, Collect Stack, Collections, SoftPOS, Orchestrate, Connected Banking, BBPS COU, PA-P). Use whenever the user mentions creating, drafting, preparing, or generating any kind of proposal, pitch, deck, or presentation for any bank — HDFC, ICICI, SBI, Axis, Kotak, Yes, IndusInd, Canara, PNB, BoB, Federal, IDBI, RBL, HDFC, any co-operative bank, any RRB — even when the user doesn't explicitly say "proposal". Triggers on phrases like "make a proposal for HDFC", "bank pitch", "bank deck", "draft something for Axis", "we need to pitch ICICI", "presentation for SBI on Collections", "prepare for the Kotak meeting", and similar. Handles product selection from the shared Product KB, compliance language (RBI/NPCI/PCI-DSS), stakeholder-specific framing (CIO, CTO, COO, CRO, Head of Digital, Head of Transaction Banking), bank logo retrieval (local-first, internet fallback with caching), FinVerge branding, and output in DOCX, PPTX, or Canva format.

  • Expression spark

    zxc779177631-ui/expression-spark Skill

    no license0★

    从零激发并积累用户自己的表达语料:通过低压力、一次一问的访谈,把最近经历、外部输入、业务判断、感悟和不同意见沉淀为经用户确认的原话、轻量选题卡与证据化个人画像,并在证据充足后生成本人 Persona Skill。用户说“不知道拍什么”“脑子一片空白”“想聊聊最近发生的事”“帮我收集个人语料”“建立我的表达风格”“蒸馏我自己”“看看还有什么没拍”或要求导出 Expression Spark 试用成果与反馈时应主动使用。用户已有明确主题且只要求直接写完整脚本时不要使用。

  • Logo as code skill

    ChanMeng666/logo-as-code-skill Skill

    0★

    Use when turning a hand-drawn, sketched, or scanned logo into clean reproducible code — fitting smooth cubic Bézier curves to the real outline to produce an editable SVG, color/layout variants, an interactive side-by-side/difference review gallery, PNG/ICO/favicon exports, and optional AI showcase renders. For brand logos, monkey/mascot marks, wordmarks, avatars, or any artwork that should become a parametric, infinitely scalable, version-controlled asset instead of a flat image. This reconstructs an existing drawing; it does not generate brand-new logo designs from scratch.

  • Swap

    Phytonking/swap/skills/swap Skill

    0★ repo

    Delegate mechanical sub-tasks to cheap local/cloud models to save on frontier token cost. Use whenever you need to (1) summarize tool output, logs, file dumps, or grep/search results longer than ~500 tokens, (2) extract structured data (errors, fields, entities) from text, (3) classify text into categories or make a yes/no triage call, or (4) draft mechanical code/diffs — INSTEAD of reading the raw content into your own context. Routes to the user's local Ollama (or a configured cloud model). Self-installs on first use.

  • Skill vetting reporter

    jovd83/skill-vetting-reporter Skill

    0★

    Security & trust vetting for an AgentSkill (folder, SKILL.md, zip, or single script) before it is installed or approved. Runs a mandatory open-source scanner gate (Cisco skill-scanner, NVIDIA SkillSpector, Snyk Agent Scan, sentry/skill-scanner), then static heuristics, and produces a draft review report — file inventory, executable surface, findings by severity, an OWASP Agentic Skills Top 10 (AST01-AST10) coverage map, a red-flag checklist, a suggested review tier (0-3), and reviewer sign-off blocks. Use this whenever someone asks "is this skill safe", "vet/review/scan this skill or SKILL.md or script", "run the vetting on skill X", "should I install this skill", or when a skill must pass the AgentSkills review flow. Also use it to re-vet an updated skill and diff the reports. It assists review and never approves anything on its own.

  • Pubifact

    domuk-k/pubifact/skills/pubifact Skill

    0★ repo

    Publish a standalone HTML or Markdown file to a shareable public URL instead of telling the user to open it locally. Use when an agent has produced or is pointed at a .html or .md artifact — a prototype, slide deck, report, dashboard, research note, or interactive explainer — and the user wants a link to share. Triggers on "publish this", "share this page", "give me a URL for this", "deploy this html", "host this file". Can also set up the user's own free permanent hosting account and take published pages back down.

  • Claude code agent sdk

    ucsandman/claude-code-capability-primer/skills/claude-code-agent-sdk Skill

    0★ repo

    Use when building custom AI agents headlessly, embedding Claude Code tools in an app, or running scripted/cron agents—need SDK package names, setup, core API entry points, supported languages, and relation to Claude Code CLI and Messages...

  • Lens studio assets and fbx

    zajalist/zajal-skills/skills/lens-studio-assets-and-fbx Skill

    0★ repo

    Use when importing or wiring assets in Lens Studio via MCP — textures (PNG), 3D models (FBX/GLB), materials and their texture slots, PBR base/normal slots, duplicating/moving assets, and pulling private files off Google Drive into the project.

    The same file is in 1 other repository

  • Guitar setup

    duckysmacky/guitar-setup-skill/skills/guitar-setup Skill

    no license0★ repo

    Guitar and amplifier setup assistant. Activate this skill when the user asks how to set up their guitar or amp to play a specific song or wants to dial in a tone for a particular artist, song, or genre. Triggers on phrases like "how do I set up for [song]", "what are the settings for [artist]", "dial in [song] tone", "I want to play [song] on guitar", "set up my amp for [song]", "guitar settings for [artist/song]", or any request to configure guitar/amp equipment to match a specific sound. Also triggers when the user says the tone "doesn't sound right" or "doesn't sound like the original" and wants help tuning their settings. Always use this skill when a song, artist, or tone target is mentioned alongside guitar or amp setup - even if the phrasing is casual.

  • Virtuous laziness

    OMouta/virtuous-laziness Skill

    0★

    A compact agent skill for making smaller, cleaner, more maintainable changes by avoiding unnecessary code, abstractions, dependencies, and output.

  • Create

    Skillroy-AI/skillroy/.claude/skills/create Skill

    0★ repo

    Author a new skillroy-compliant Agent Skill — in an existing collection or in a brand-new one — or bring an existing skill toward compliance. Scaffolds the collection shell when needed (README metadata block, skills home, gitignore, .agents symlink) and the skill folder with a conventions-correct SKILL.md (tier-aware name, what+when description, the metadata.skillroy block), plus references/, scripts/, and evals/, applying the phase-appropriate quality bar. Use when creating, scaffolding, or authoring a new skill or skill collection/repo; starting a skill from a research seed document; or making an existing skill skillroy-compliant. Pairs with `research` (turns sources into the seed doc this consumes) and `review` (lints the result).

  • Dope skill

    soil-dev/dope-skill Skill

    0★

    Read a person's style as one of four bird profiles (Peacock, Dove, Eagle, Owl) and adapt how you communicate, sell, or relate to them so it lands the way that person actually receives things. Use this whenever the user wants to figure out how to approach, persuade, write to, sell to, or get along with a specific person — drafting or rewriting an email/Slack/proposal for a named recipient, prepping a negotiation or hard conversation, shaping a sales pitch or renewal to a customer, working out what a colleague/client/boss/partner/family member cares about or what motivates them, defusing recurring friction with someone, or explicitly asking for someone's 'bird', 'type', DISC style, or communication style. Also use when the user pastes someone's writing and asks how to pitch, reply, sell, or get through to them, even if they never say the word 'profile'. Covers work messaging, selling, and personal/family relationships from one shared model.

  • Popperian reasoning

    calebikhuohon/popperian-reasoning/skills/popperian-reasoning Skill

    0★ repo

    Use Popperian critical rationalism to improve reasoning by falsification, risky tests, competing conjectures, and error elimination. Invoke implicitly in any agent harness when a task involves uncertainty, hypotheses, tradeoffs, claims, explanations, debugging, diagnosis, research evaluation, plan review, design choice, or improving an LLM answer by asking what would break it before asking what supports it. The user does not need to name this skill if the harness supports contextual skill selection.

  • Agent handoff kit

    claudette-agent/agent-handoff-kit Skill

    no license0★

    Lightweight handoff workflow for AI coding/research agents. Captures objective, state, constraints, next action, verification, and risks.

  • Revenue leak auditor

    IgorGanapolsky/revenue-leak-auditor-skill/revenue-leak-auditor Skill

    no license0★ repo

    Audit Stripe Checkout, payment links, attribution, abandoned-checkout recovery, and analytics instrumentation in agent-built funnels. Use when asked to find why visitors are not paying, whether checkout links are confusing, whether observability is exact enough, or whether a funnel is ready for paid traffic.

  • Ai hotdog

    huzoukai/ai-hotdog Skill

    no license0★

    Configurable hot-topic and content-idea radar for AI-HOTDog. Use when Codex needs to initialize a user-selected topic radar, bind or rebind logged-in platform access through Chrome, scan public and social/media sources for trending topics, generate a cited Top 10 hotspot report with Top 5 content ideas, or create a Codex automation that runs the configured radar on a schedule.

  • Oh my gh writing

    PINKIIILQWQ/oh-my-gh-writing Skill

    0★

    Draft and revise GitHub-facing writing artifacts: issues, PR descriptions, maintainer comments/replies, code reviews, commit messages, README/CONTRIBUTING/CHANGELOG docs, release notes, migration guides, RFCs, issue/discussion forms, PR templates, and local multi-file release/launch/contribution workflow packs. Use only for GitHub repository artifacts; do not use for generic prose, UI copy, marketing, or code implementation.

  • Skill

    jamieafk/fable-check/skill Skill

    0★ repo

    Run an extensive code review or get advisory input from Claude Fable 5 (Anthropic's most capable model). Use when the user asks for a code review, a fable check, a second opinion on changes, a pre-ship review, an adversarial/deep review of the working tree or a branch — or wants Fable's advice on an architecture choice, design tradeoff, plan, or technical decision about the codebase. Read-only — it never modifies code.

  • AnimatePresence

    goharabbas321/zeoel/skills/AnimatePresence Skill

    no license0★ repo

    Zeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.

  • Lins living loop

    LinLin00000000/lins-living-loop Skill

    0★

    Use this skill whenever the user asks for Lin's Living Loop, LLL, living loop, DOP, Deep Orchestration Protocol, 深度编排协议, 深度调研, 深入研究, 重型任务, 长时任务, 可恢复执行, 并行 agent, background agent, durable work, or complex multi-step work likely to cause context explosion, API timeouts, upstream instability, long-running execution, workspace reuse, or nontrivial validation. This skill turns chat into a lightweight supervisor, keeps the filesystem as the durable source of truth, chooses the simplest reliable carrier, puts human deliverables at the workdir root beside mission.md, keeps process/audit state under internal/, enforces that human-facing deliverable prose follows the user's requested/current interaction language instead of silently falling back to English templates, and treats skills/workflows as living procedural memory that can repair itself without becoming ceremonial.

  • Readme standard

    sametbrr/readme-standard Skill

    0★

    Enforces a consistent README.md + README.tr.md structure across projects. Use when: - "readme oluştur" / "create readme" / "yeni readme" → Create mode: generates both README.md and README.tr.md from scratch - "readme kontrol et" / "audit readme" / "readme'yi incele" → Audit mode: prints a checklist report, writes no files - "readme düzelt" / "fix readme" / "readme standardize et" / "readme'yi güncelle" → Fix mode: rewrites existing README(s) to match the standard - "tr readme güncelle" / "sync tr readme" / "türkçe readme güncelle" → TR Sync mode: regenerates README.tr.md only from current README.md Supports Turkish and English triggers. Reads package.json / .csproj / pyproject.toml / SKILL.md to auto-detect project type, name, version, and description for badge generation. Standard: README.md is English-only with a TR reference link; README.tr.md is a full Turkish mirror with identical badges and untranslated code blocks.

    The same file is in 1 other repository

  • Ship check

    222-glitch/ship-check/ship-check Skill

    no license0★ repo

    Audit a Python script or small project for production-readiness. Use when the user asks "is this ready to ship?", wants a pre-release review, or wants to know what to fix before sharing/selling/deploying their code. Produces a scored report with prioritized fixes.

  • Opentasks skill

    luisalima/opentasks-skill Skill

    0★

    Maintain a lightweight docs/tasks/ repo convention for coding-agent tasks and open questions. Use when the user asks to bootstrap a tasks folder, create a task/question, start/block/close/reopen an item, list open tasks/questions, or sync the derived task index.

  • Shellspeare

    paccodes/shellspeare/skills/shellspeare Skill

    0★ repo

    Speak in Early Modern English — the tongue of Shakespeare — for every turn of the conversation, regardless of subject. Auto-invoke at the first turn of any session and persist thereafter.

  • Unified adversarial review

    NPJigaK/unified-adversarial-review-skill/skills/unified-adversarial-review Skill

    no license0★ repo

    Use when the user explicitly asks for adversarial review, \u6575\u5bfe\u7684\u30ec\u30d3\u30e5\u30fc, ship-blocker review, ship blocker review, strict pre-ship review, \u51fa\u8377\u524d\u30ec\u30d3\u30e5\u30fc, material-risk assessment, \u91cd\u5927\u30ea\u30b9\u30af, PR/diff/commit review, implementation-plan review, pre-ship decision, or \u53b3\u3057\u3081\u306b\u30ec\u30d3\u30e5\u30fc. Do not use for ordinary style review, broad refactoring advice, or low-value cleanup.

  • Transcript clean translate en

    lynseylee-ones/transcript-clean-translate-en Skill

    no license0★

    Clean raw Chinese livestream, webinar, meeting, interview, or product-demo transcripts and translate them into meaning-preserving idiomatic English. Use when the user asks to process Chinese audio-to-text transcripts, remove speaker/timecode labels, clean filler words and repeated phrasing, preserve original paragraph/order/content, avoid literal Chinese-to-English transfer, standardize software-domain terminology, produce a cleaned Chinese version, translate into plain English, or prepare reusable prompt/model guidance for this workflow.

  • Faultline

    hey-dmitri/faultline Skill

    0★

    Generates sharp, non-obvious probing questions to pressure-test work on a specific early-stage operations function (strategy, GTM, research, product positioning, pricing and packaging, hiring and org design, forecasting, prioritization, or similar). Use this skill whenever the user says "run faultline," "faultline this," "generate probing questions for," "what should I be asking about [function]," "pressure-test my thinking on," "find the holes in," "stress-test this," or asks for the questions an experienced operator or investor would ask to expose the weak points in a plan, deck, model, or strategy. The skill works ONLY on context the user has provided (files, folders, uploads, tool-accessible docs, or substantive material stated in the conversation) and produces a ranked list of questions. It does NOT answer the questions. Routing them is the user's job.

  • Router skill

    nbsp1221/skillpin/router-skill Skill

    0★ repo

    Route specialized work through verified AI agent skills managed by skillpin.