The catalog
608,119 rows, by stacks then stars
AHMEDGabal1/document-craft/document-craft Skill
no license0★ repoCreate, structure, format, and review professional documents to multinational standards (ISO, ISO/IEC, IEEE, GOST, GB, APA, Chicago). Use for SOPs, specs, reports, RFPs, contracts, and policy docs in any language/RTL.
trungnghia112/dang-ky-ban-quyen-phan-mem-skill/dang-ky-ban-quyen-phan-mem Skill
0★ repoQuy trình chuẩn bị bộ hồ sơ đăng ký bản quyền phần mềm (ĐKBQ / đăng ký quyền tác giả cho chương trình máy tính) tại Cục Bản quyền tác giả Việt Nam - chụp toàn bộ giao diện (UI) + mã nguồn, che mờ (redact) thông tin nhạy cảm, gỡ hình/logo bên thứ ba, rồi lắp ráp thành bản in nộp được (.md + .docx + PDF). Dùng BẤT CỨ KHI NÀO người dùng nhắc tới - đăng ký bản quyền, ĐKBQ, bản quyền phần mềm, quyền tác giả, Cục Bản quyền, hồ sơ đăng ký tác phẩm, in giao diện và mã nguồn để nộp, chụp screenshot toàn bộ app, che mờ/ẩn dữ liệu nhạy cảm trên ảnh, gỡ logo bên thứ ba, hay tạo bản in mã nguồn đẹp. Generic cho mọi dự án phần mềm web hoặc mobile.
linxumoney/research-citation-auditor/skills/research-citation-auditor Skill
0★ repo审核论文、研究报告和专业文章中的引用真实性与支持关系,建立论断-证据账本,验证 DOI、PMID、arXiv ID、作者、标题、年份和来源类型,识别缺失引用、错误引用、二手引用和过度推断。适用于引用核验、参考文献清理、论文审稿、BibTeX 检查和“这篇文章的证据可靠吗”。
runsagents/agent-stack Skill
0★Route a production-stakes agent situation to the smallest fitting runsagents artifact or composition of artifacts.
runsagents/handoff-receipts Skill
0★Write and validate structured receipts for agent-to-agent or agent-to-human work transfers. Use when the user says "handoff" or "hand this off", when delegating work to another agent, when ending a work session with unfinished or transferable context, or when receiving work that another agent expects you to accept.
Elisedai1013/steer-agent-workflow-skill/skills/steer-agent-workflow Skill
0★ repoSteer complex Agent work before, during, and after execution using source-grounded methods from Field Guide to Fable. Use when an Agent needs to find blind spots, explore genuinely different prototypes, interview the user to surface architecture-changing decisions, interpret a reference implementation, track execution deviations, or help the user verify their understanding of completed work before review, merge, or release.
towfikul-islam/trello-skill/skills/trello Skill
0★ repoAccess the user's Trello over the raw REST API — list boards/lists/cards, read/download attachments, post comments, upload files to cards. Use when the user mentions Trello, a board/card/list, or asks to fetch/comment/upload Trello attachments.
DLYZZT/agent-token-usage-skill Skill
no license0★Reports local token usage for coding-agent sessions (Codex, Claude Code, Pi, Grok, opencode, openclaw) by running the agent-token-usage CLI against the user's on-disk session logs — no network calls, no API keys. Use whenever the user asks how many tokens they've used, wants a usage/cost breakdown, or wants to check today's/this week's/a specific session's token consumption for any of these coding agents.
NoraXu-0111/resume-strategist/skills/resume-strategist Skill
0★ repoBuild, audit, and tailor a truthful, ATS-friendly, impact-oriented resume — strongest for SDE / AI-agent / LLM-platform / backend / infra / distributed-systems roles. Use when the user wants to improve a resume, turn real work into strong bullets, run an evidence-based resume audit, tailor role-specific versions, or prep interview questions from their resume.
sammdu/fetch-cache-web/fetch_cache_web Skill
0★ repoFetches web URLs and caches them locally as files with a manifest inventory, friendly names, expiry, and optional HTML-to-Markdown conversion. Use when fetching reference URLs that will be re-read across runs, caching official docs or guidance locally, checking what is already cached via the manifest, converting fetched HTML pages to Markdown, or creating or updating an agentic skill that frequently fetches upstream web content and should bundle this capability.
bman654/audio-forge/skills/audio-lens Skill
0★ repoVerify audio you (or a model) generated WITHOUT being able to hear it. Renders and inspects sound as numbers plus a screenshot-readable spectrogram PNG. Answers: is it in tune (what note / cents off)? right tempo (BPM)? clipping (distorted/too loud)? silent or empty? what is the spectral centroid (bright vs dull)? Use whenever you produce or receive a WAV — from TTS, music/SFX generation, synthesis, DSP code, or a recording — and need to CHECK it instead of trusting it blind. Trigger keywords: verify audio, check audio, is this in tune, what note, what pitch, what frequency, detect tempo / BPM, is it clipping, is it distorted, is it silent, analyze a WAV, spectrogram, waveform, RMS / loudness, audio QA. Zero-dependency Node CLI; no install.
huguryildiz/ALETHEIA/plugins/aletheia/skills/build-log Skill
0★ repoOperating discipline for rigorous, reproducible computational-science research — a portable, markdown-only Claude skill pack: 18 disciplines, a generator, and read-only auditor agents.
mvarge/agent-skills/skills/ntfy-agent-bridge Skill
0★ repoDelegate tasks to a remote autonomous agent via a private ntfy topic. Use whenever the user says "tell the agent to...", "ask my remote agent to...", "send this to <agent-name>", or when a task should be handed off to an out-of-session agent that has its own tools (email, calendar, drive, telegram, web search, persistent memory, shell). The remote agent polls the ntfy topic and replies out-of-band (Telegram, email, etc.).
hamidettefagh/agent-production-readiness Skill
0★Reviews an AI agent for production readiness across evaluation, cost, observability, guardrails, human oversight, reliability, and governance. Use when someone is preparing an agent for production or a go-live, asking whether an agent is ready to ship, reviewing an agent's design, prompt, tools, or deployment, or hardening a working prototype into a dependable system. Produces an evidence-based scorecard and a prioritized list of the gaps to close.
orchune/personal-finance/skills/personal-finance Skill
no license0★ repoRecord and query the user's personal finances in Orchune via its MCP server. Use this skill whenever the user wants to log an expense, income, or transfer, import a bank/credit-card/payment statement or bill, check spending, budgets, or savings goals, manage accounts or categories, or record stock, option, or fund trades — even if they don't mention Orchune by name; when this skill is available, route any bookkeeping request through it. Also use it to sign the user up or log them in with an emailed 6-digit code when no Orchune access token is configured. Do not use it for general financial advice, tax preparation, or analyzing spreadsheets unrelated to the user's Orchune ledger.
SilentFleetKK/zuiti-cuihun Skill
0★嘴替·催婚包——专治亲戚父母用关心和比较施压你的婚恋进度。你看别人孩子都两个了、眼光别太高、我们年纪都上来了、为你好、见一面怎么了、不图你什么就一个心事、什么时候带回来、别人都不挑你挑什么、老了没人照顾——所有过年过节饭桌上、微信群里、深夜电话里那句"你到底怎么想的",它先翻译长辈的潜台词和这段关系的真实温度,再给你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。只要用户贴出长辈催婚催恋的消息,抱怨"被催了""不知道怎么接""又提相亲""过年不敢回家""这话我该怎么回",或者说"催婚""帮我回我妈/我姨/我爸",都应主动使用本 skill。
myrrazor/agent-skills/fable-guardrails/fable-route-plan Skill
0★ repoManually assess an entire Claude Code workflow for Claude Fable 5 fallback likelihood, dependency order, context exposure, and model routing. Run from an Opus session before execution.
IcodeNet/agent-skills/skills/address-pr-feedback Skill
0★ repoOne-shot pass to address PR review comments: fetch threads, apply validated fixes, lint/test affected files, commit, push, reply, and offer to resolve. Use when the user asks to address review comments on a PR or points to a PR link/number. For continuous monitoring until merge-ready, use pr-babysitter instead.
scottconverse/visitor-audit Skill
0★Run a visitor-grade audit of a project's public-facing surfaces — verify pages, docs, READMEs, release pages, and announcements the way a first-time human visitor experiences them, not the way a developer diffs them. Reads every surface fully as rendered, follows EVERY link (counted, with per-link status), checks published checksums, and flags stale claims, jargon leaks, invisible links, mojibake, and misleading framing. Use whenever the user says "visitor audit", "audit the public surfaces", "click through everything", "is this actually done", or "/visitor-audit" — and proactively before announcing any page, doc, site, or release as done, and again after any deploy, even if the user doesn't say "audit". CI green is not a substitute for this check.
asker26/agent-skills/skills/readable-ultra Skill
0★ repoDeep readability review of a PR with finder + adversarial validator agents, based on Clean Code / The Art of Readable Code principles. Usage: /readable-ultra <PR#> [repo]
shinzoxD/knackbox/skills/coding/accessibility-review Skill
0★ repoReview UI and content for accessibility issues against WCAG-minded practices. Use whenever the user asks for an a11y review, accessibility audit, ARIA help, keyboard navigation, screen reader support, or whether a UI is accessible — even for small component snippets.
macmys/design-production-web-skill/skills/design-production-web Skill
0★ repoGuide non-designers and design-capable teams through designing, building, reviewing, and releasing distinctive production-ready websites and web applications with an evidence-producing design-engineering workflow. Use for professional or portfolio websites, product-idea and concept landing pages, company and product-spinoff sites, greenfield or existing frontend work, website audits and improvements, content sites, product UI, design systems, responsive implementation, visual direction, accessibility, browser testing, performance, SEO, security/privacy boundaries, or release evidence. Trigger when asked to create, redesign, implement, improve, critique, audit, or verify a web experience; do not use for backend-only tasks, non-web presentations or infographics, or trivial isolated style edits that do not need design judgment.
mauromedda/ccctx/skills/ccctx-review Skill
0★ repoReview ccctx changes for correctness, regressions, security, tests, documentation, and release readiness. Use when asked to review pull requests, diffs, commits, branches, or proposed changes in this repository, especially changes touching Go CLI behavior, profile storage, Claude Code credential handling, exec isolation, docs, CI, or project skills.
aiswarya797/find-your-knowns/skills/find-your-knowns Skill
0★ repoTurn hidden unknowns into actionable knowns before, during, and after implementation work. Use when the task itself is vague, under-specified, high-impact, high-risk, design-heavy, reference-based, long-running, or in an uninspected area, even if the user does not mention uncertainty. Strong implicit triggers include auth, permissions, billing, payments, migrations, schemas, data, APIs, integrations, security, deployment, performance, and UX redesign. Do not use for ordinary code review, bug review, security review, or PR defect-finding requests.
enoch3712/KERN/skills/kern Skill
0★ repoMaintain a lazy, content-addressed KERN IL mirror of a software repository and render cold semantic pages as compact images. Use when an agent must understand a large codebase with less context, refresh changed files, prepare code maps, answer questions from compressed code, or fault exact source back in before editing.
yyy805/skill-scout Skill
0★Finds, vets, installs, and immediately runs a skill from public registries when no installed skill covers the user's current task. Trigger when: (1) the user asks whether something exists for a task — "有没有 skill/插件/现成的工具能做这个"、"帮我找个 skill/工具"、 "is there a skill/tool/plugin that…"、"find me something that can…"; (2) the user requests a concrete outcome (convert, generate, integrate, automate) in a specialized domain — niche file formats (epub, subtitles), service integrations (Slack/Notion/ Stripe), framework-specific scaffolding — and no installed skill's description matches; (3) you are about to improvise a multi-step (3+) specialized workflow from scratch — check the registry first. Do NOT trigger when an installed skill already covers the task, when base tools suffice, or when the user only wants explanation rather than execution. Triggering is safe: nothing is ever installed without one explicit user confirmation.
elecnix/cmux-subagent/skills/cmux-subagent Skill
0★ repoSpin off a pi subagent in a new cmux terminal surface in the current pane, then hand the task off via intercom so the subagent knows its caller and can reply when done. Use when asked to delegate work to a subagent in a separate tab.
islambenmebarekdz-collab/closed-loop-strategic-agent/ar Skill
0★ repoClosed-Loop Strategic Agent (الوكيل الاستراتيجي ذو الحلقة المغلقة) — a domain-agnostic two-phase workflow. Phase 1 challenges and clarifies the request (targeted questions, an out-of-the-box improvement proposal, then a hard gate waiting for user approval). Phase 2 executes with an internal self-verification loop (expert-reviewer persona, up to 5 correction cycles) and appends a short transparency report. Use this skill whenever the user asks for a substantial deliverable in ANY field — medicine, code, law, marketing, social-media content, academic research, business plans, cooking, or anything else — especially when the request is broad, ambiguous, or high-stakes, or when the user invokes it by name (الوكيل الاستراتيجي / الحلقة المغلقة / closed-loop). Do NOT use for trivial one-line questions or quick factual lookups.
VitorLudke/skillsync/skills/hello-world Skill
0★ repoExample skill shipped with skillsync so a fresh clone has something to sync, lint, and verify. Replace it with your own skills.
sdsrss/super-skill/codex/skills/super-skill Skill
0★ repoUse when the user wants to manage, version, audit, or roll back their Agent Skills, or to review skill candidates mined from past sessions. super-skill is a git-backed package manager for the skills in ~/.agents/skills (and ~/.claude/skills) — it seeds existing skills under version control, explains where each came from, rolls any skill back one command, checks registry integrity, and surfaces recurring task families worth turning into a skill. Triggers include "version my skills", "roll back that skill", "why do I have this skill", "check my skill registry", "what could become a skill".
bangchuiLee/llm-wiki-skill-human-first Skill
0★个人知识库构建系统(基于 Karpathy llm-wiki 方法论)。让 AI 持续构建和维护你的知识库, 支持多种素材源(网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件), 自动整理为结构化的 wiki。 触发条件:用户明确提到"知识库"、"wiki"、"llm-wiki",或要求对已初始化的知识库执行 消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发——必须是明确的 知识库相关意图。
takeshijuan/create-public-pr/skills/create-public-pr Skill
0★ repoUse when a user asks to create, open, prepare, publish, or refresh a pull request in a confirmed public repository, or explicitly asks for create-public-pr or public-safe handling; do not use for ordinary private, internal, future-public, or unverified repositories, nor for review-only, local commit-only, issue, merge, or deployment requests.
HeliCorgi/covariance-compactor/skill Skill
0★ repoRuns a pre-registered, gate-driven falsification to kill weak or over-ambitious ideas early, before real effort is committed. Use when deciding whether a big, expensive, or hard-to-reverse concept, project, or hypothesis is worth pursuing. It pre-registers falsifiable kill-metrics with null controls, runs the cheapest kill-tests on real data or sourced literature, and adversarially reviews the arithmetic and counterfactuals before issuing a keep or kill verdict. Defaults to a fast quick-kill triage; escalates to a full multi-gate campaign only for high-stakes decisions. Not for small, cheap, or reversible choices.
Business central assisted setup
bochaoli95/bc-assisted-setup-marketplace/plugins/bc-assisted-setup/skills/business-central-assisted-setup Skill
0★ repoCreate or review Microsoft Dynamics 365 Business Central Assisted Setup / Guided Experience implementations in AL. Use when Codex needs to add setup cards to the Assisted Setup page, create NavigatePage setup wizards, register setup pages with codeunit 1990 "Guided Experience", implement "Set up this app" primary setup behavior, show initial setup confirmation prompts, mark assisted setup as complete, or explain how Microsoft-style setup assistants are built in Business Central extensions.
CheshireJCat/translate-xinda-buya/translate-xinda-buya Skill
0★ repoTranslate text into a 信达不雅 style in any requested target language: preserve the source meaning and make it fluent, while actively recasting the target into rough, colloquial, vulgar, meme-like, and confrontational language even when the source is neutral or formal. Default to Chinese when the user does not specify a target language. Use when the user asks for 信达不雅, 粗口翻译, 接地气翻译, 俗一点/脏一点但准确, meme/slang/profanity translation, or a translation that must sound low-register and unpolished.
knownasnaffy/prompthound/.agents/skills/caveman Skill
no license0★ repoUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
The same file is in 1 other repository
Battlelamb/claude-code-conversation-titler/plugins/titlewise/skills/titlewise Skill
0★ repoUse when the user wants to name, title, or label the current conversation, or asks for a title suggestion. Triggers on phrases like baslik oner, konusmaya isim ver, sohbeti adlandir, bu konusmaya baslik, label this chat, name this conversation, or the command /titlewise. Analyzes the current conversation, interactively asks (via AskUserQuestion) for language (user language, EN, or CHN), length, date, and style preferences unless already given, then produces the matching title variants plus a recommended pick, a short description, and tags. Suggestion only; it proposes titles you copy and apply yourself, and never modifies the session.
lucas-carvajal/agent-skills/skills/html-theme Skill
no license0★ repoProduce standalone dark minimal HTML for the user to open in a browser — one page or a small multi-page site that links together. Use only when the user wants HTML instead of markdown (e.g. "HTML page", "standalone report", "openable page", "HTML artifact", multi-page briefing). Do not use for normal chat answers or simple markdown files.
Director level aigc short film
AGTurbo/director-level-aigc-short-film/director-level-aigc-short-film Skill
no license0★ repoUse whenever a user creates, plans, audits, or revises an original narrative multi-shot AI short film, AI movie, or cinematic sequence needing director-level psychology, relationships, shot grammar, picture-first sound, music spotting/cue sheets, visual QA, or provenance. Also use for reference-film and third-party-IP method research to redirect identifiable-expression imitation into abstract, IP-safe original-film methods. Trigger for 导演级 AIGC 短片、AI 电影、AIGC 电影、多镜头剧情、角色一致性、剧本到分镜到提示词、参考片反推、镜头/情绪/表演/剪辑/配乐/音乐时间轴. Do not use for unrelated one-off image edits, simple visual prompts, or media execution without explicit authorization.
televgtamfe-coder/audit-automation-playbook/audit-automation-playbook Skill
0★ repoCreate reusable AI audit, quality-review, compliance-review, content-moderation, customer-service QA, or order-review automation plans. Use when Codex needs to convert an existing manual review process into a rule + LLM + human-review workflow, produce cost/ROI comparisons across pure manual, domestic model, overseas model, and hybrid model options, define rollout gates, calibrate rubrics, or prepare a release-ready project playbook/document.
Lazarus893/frontend-design-flow Skill
no license0★Opinionated orchestrator for going from an idea to shipped, non-generic frontend UI. Encodes a four-stage workflow — (1) competitor motion research + clone-path decision, (2) design output & direction, (3) review + anti-AI-slop gate, (4) a stack & vocabulary reference layer that runs through all of them. It routes to specialized underlying skills by name (with install pointers) rather than bundling them. Use when the task is "design/build a website, landing page, dashboard, app prototype, React component, or UI", "make this look good / less AI-generated", "replicate a site's look or a specific effect", or "what stack / what's this effect called". Trigger words: 做原型, 做页面, 做组件, UI 设计, 高保真原型, 设计方向, 复刻网站, 提取特效, 反 slop, prototype, landing page, design direction.
Dev869/skill-orchestrator/skill-orchestrator Skill
0★ repoMeta-skill that coordinates multiple installed skills to deliver one cohesive result for multi-domain tasks. Use whenever a request spans more than one domain (e.g. "research the market, build the pricing model, and turn it into a deck"), is broad or end-to-end ("handle this start to finish", "do whatever it takes to ship this", "prepare the full launch package"), or when it's genuinely ambiguous which of several installed skills fits — even if the user never mentions skills or orchestration. Also use when a task will clearly chain outputs across skills (research feeding a document feeding a design). Do NOT use when one skill obviously and fully covers the request, or for single-domain tasks — invoke that skill directly and stay out of the way.
tylensthilaire/skill-skills-sync/skills/skills-sync Skill
no license0★ repoInstall, verify, and update the pinned skills a project lists in skills.json, and copy any conventions those skills carry into raw/ for the agent to ingest. Use this whenever skills.json is mentioned or present; whenever the user asks to install, set up, sync, verify, or update skills; whenever a freshly cloned project has a skills manifest but an empty or missing agent skills folder; whenever a skill fails to trigger because it isn't installed; and whenever a newly installed skill has a knowledge/ directory whose conventions need copying into raw/.
Stephen-creater/loop-engineering-skill/loop-engineering Skill
0★ repoEstablish commander intent before substantive human-agent collaboration, then let the agent autonomously close the execution loop. Use for implementation, modification, publishing, consequential decisions, multi-step work, or long-running tasks where purpose, observable success, boundaries, or delegated authority may be unclear. Ask one high-value clarification at a time until the intent is executable; when it is already clear, briefly restate it and proceed without waiting for confirmation.
StaryMoon/results-table-to-figure-skill/skills/results-table-to-figure Skill
0★ repoConvert CSV or simple LaTeX result tables into editable SVG/PDF and high-resolution PNG bar, line, or heatmap figures with normalized data and provenance. Use when Codex needs to turn benchmark tables, ablations, model comparisons, or experiment summaries into publication-ready plots without retyping values.
mifochen/update-stock-mcp/update-stock-mcp Skill
no license0★ repoUpdateStock MCP 服务技能 —— 通过 stdio 模式调用 UpdateStock 脚本, 提供 A 股 DuckDB 数据库管理功能:创建数据库、全量/增量更新股票数据、查询股票行情。 设计的数据库方案兼容 QuantAll(全A解析)计算引擎。 触发条件:用户提到"UpdateStock"、"创建股票数据库"、"更新股票数据"、"获取股票数据"等。
The same file is in 2 other repositories
forchain/skills/blackbox-acceptance-gate Skill
no license0★ repoGate acceptance of new or existing implementations through an approved contract, independent black-box testing, externally verifiable evidence, and a traceable verdict. Use when development and acceptance must stay isolated or when a release needs user-approved acceptance criteria.
silkyland/create-my-team Skill
0★General-purpose multi-agent teamwork: for any sizable task, probes what subagent-spawning capability the current platform actually exposes (Claude Code agents/workflows, Codex multi-agent tools, OpenCode subagents — or none, with an honest sequential fallback), designs a team topology sized to the task (scout swarm, pipeline, panel-and-judge, manager-worker), sends every member a standardized mission brief, researches BEFORE executing, presents the synthesized plan at a user gate, then spawns the execution team and cross-checks every deliverable at an integration gate before merging. Use when the user wants to spawn agents or subagents, parallelize research or work across a team, says "use a team/multi-agent" for a task, or mentions create-my-team or /create-my-team.
ecfromthedc/ec-rt-skills/checker Skill
no license0★ repoIndependent content-gate checker (the "checker" half of the maker/checker split). Takes a content artifact + a rubric path and returns PASS/FAIL with named violations. INVOKE PROACTIVELY before any content artifact ships to a client or page — captions, carousel copy, campaign budgets, creator lists, post batches. This is the enforcement layer for the verification rules that used to live as prose in CLAUDE.md; the maker never grades its own work. Trigger phrases: "check this", "grade this artifact", "run the checker", "gate-check", "rubric check", "does this pass", "verify before send", "pre-ship check".
paarangat/fabelize/skills/fabelize Skill
0★ repoHand coding work to Codex without handing over control. Use only when the user explicitly invokes `/fabelize` followed by a task and wants Fable to architect, approve, and review an isolated Codex implementation.
runsagents/voice-calibration Skill
0★Generate text in <your name>'s voice. Use when asked to "write as me", "in my voice", or when drafting anything sent or published under <your name>'s name.
jwoo0122/harness/.agents/skills/domain-modeling Skill
0★ repoBuild and sharpen a project's ubiquitous language while designing. Use when a project term is fuzzy or overloaded, or when a durable architectural decision should be recorded.
DrewGGM/project-blueprint-skill/skills/project-blueprint Skill
0★ repoActs as software architect to define a software system from scratch BEFORE writing code. Turns a raw idea into a validated, code-ready blueprint — refining the idea, writing the spec/PRD, choosing the architecture, and setting the security, quality, and testing baseline. Use when starting a new project, feature, or system, when the user says "design/plan/define/architect X", "empezar un proyecto", "definir el sistema antes de codear", or wants a PRD, architecture, or technical plan.
chang769/llm-wiki-vault-manager Skill
no license0★Manage source-backed LLM-wiki and Obsidian-style Markdown vaults as learning databases for humans and AI agents. Use when an AI coding agent such as Codex or Claude Code needs to scaffold a raw/wiki/schema knowledge database, organize provided links or files into the proper raw material directory, ingest raw sources into durable wiki notes, update the vault structure/index/log, help the user and agent learn a chosen area, answer vault questions with citations, lint indexes/backlinks/logs, automatically review, summarize, commit, and push vault enrichment changes with git, download or preserve raw material, or distill repeated source-backed workflows into reusable agent skills.
clipmasterapp/skills/skills/clipmaster-promo Skill
0★ repoProduce a vertical promo video for any business with no source footage — scan a website URL for a grounded storyboard/script via ClipMaster Promo Studio, then optionally render a talking-head AI avatar video that speaks the script. Use when the user wants a promo video, launch video, or social ad for a website/product and has no existing footage.
goonobu-dot/dev-skills-library/skills/ai-code-verification Skill
0★ repoVerification discipline for AI-generated code: close the loop with tests/build/run before declaring done, detect hallucinated APIs and dependencies (slopsquatting), spot tautological tests, avoid premature abstraction, and run an adversarial review from a fresh perspective. Use when about to report any coding task as complete, when reviewing AI-written code, when adding new dependencies, or when the user says 本当に動く?, 検証して, AIが書いたコード. Applies proactively to the agent's own output. For general review standards use code-review-standard — this skill adds the AI-specific checks on top. Hand off diagnosing the cause of a failing test or build to systematic-debugging. Not for test suite architecture (use test-suite-design).
phoben/agent-skills/.trae/rules/diagnosing-commands Skill
0★ repoUse to diagnose and fix ZCode custom slash-command (/command) configuration problems in the ZCode client. Applies when a command is missing, is overridden by a higher-precedence command of the same name, has a frontmatter parse error, is dropped for having an empty body, has an invalid name, does not substitute $ARGUMENTS/$1, uses a colon rather than a slash for nested names, has a misspelled frontmatter key, or disappears because the plugin providing it is disabled. Provides the discovery order, how to inspect commands in the client, common pitfalls, and a step-by-step localization and repair workflow.
axtontc/Multiverse-Planner Skill
0★Advanced Architectural Planner: Triggers the Multiverse Navigator pipeline to brute-force mathematically optimal architectures using parallel generation, heuristic pruning, and clustering.
MasashiFukuzawa/agent-toolbox/plugins/done/skills/done Skill
0★ repoReusable engineering skills for Claude Code and Codex
stayingapi/booking-com-skills/clawhub/booking-com-availability Skill
0★ repoCheck day-by-day Booking.com availability (the booking calendar) for a known listing over a date window. Use when a user asks whether a listing on Booking.com is open on specific dates. Powered by StayingAPI.