The catalog
610,045 rows, by stacks then stars
yashasvigirdhar/skills/competitor-backlink-audit Skill
3★ repoUse when the user wants to audit competitor backlink profiles using the free Ahrefs tool to identify link-building opportunities, or when setting up competitive SEO analysis.
KrishnaShettyDev/dosed/2cb Skill
3★ repoSimulate 2C-B (4-Bromo-2,5-dimethoxyphenethylamine) cognitive effects. Use when user wants sensual, playful, tactile AI responses - the "love psychedelic" combining MDMA-like warmth at low doses with visual psychedelia at higher doses. Erotic undertones, enhanced sensory appreciation, giggly, and mentally clear unlike other psychedelics. Activates with "take 2cb", "dose 2c-b", "/2cb", or requests for sensual/playful psychedelic AI responses.
SlideSpeak/skills/skills/slidespeak Skill
no license3★ repoGenerate, edit, and manage PowerPoint presentations via the SlideSpeak API. Use this skill when users want to create presentations from text or documents, edit existing presentations, or work with presentation templates.
The same file is in 11 other repositories
jovd83/restassured-skill Skill
3★Use when Codex needs to design, implement, run, document, or report Rest Assured API tests for REST services, contract-driven service tests, JUnit 5 automation, CI pipelines, or test-management integrations.
yokobond/scratch-skills/skills/scratch-block-dragging Skill
no license3★ repoBuilds Scratch programs by dragging and dropping blocks from the palette to the script area using Playwright mouse operations. Use this skill when you need to visually assemble Scratch code through the editor UI rather than injecting via the VM.
jmsmrgn/einstein-simplify Skill
3★Rewrites complex technical explanations, presentations, scripts, or any dense content so that a non-technical person sitting next to an expert could follow every word. Use this skill whenever the user wants to simplify a technical topic, make something ELI5, prepare an explanation for a mixed audience, strip jargon without losing accuracy, or says anything like 'explain it simply', 'make this accessible', 'dumb this down', 'non-technical version', 'teach this to a layman', or 'my audience isn't technical'. Also trigger when preparing presentations, demos, or scripts that will be delivered to audiences of mixed technical backgrounds. The Einstein frame: if you can't explain it simply, you don't understand it well enough. This skill enforces that standard.
rodrigolagodev/skill-creator Skill
3★Expert guidance for creating, structuring, and refining Agent Skills following the open standard. Use when working with skill files, authoring new skills, improving existing skills, or understanding skill architecture and best practices. Use PROACTIVELY when user mentions creating skills, structuring documentation, or building reusable agent capabilities.
mindboard/indesign-extendscript-plugins/skills/idml Skill
3★ repoUnpack and repack Adobe InDesign IDML files as editable XML, then edit the XML directly — no InDesign required. Use when the user wants to inspect, diff, or programmatically edit an .idml (stories/text, styles, colors, spreads, links) and produce a valid .idml back, or to convert between an .idml and its extracted folder.
raydeveloperF/App-Store-Connect-release-kit/skills/asc-api Skill
3★ repoSafely automate ASC through the official App Store Connect REST API from macOS using project-external local credentials, short-lived local JWT signing, and the bundled OpenAPI spec. Use when the user asks Codex to inspect, create, update, delete, or script App Store Connect resources such as apps, builds, versions, metadata, pricing, analytics reports, beta testing, certificates, identifiers, profiles, or any ASC endpoint. Also use when generating local Python automation that must never expose ASC API keys, .p8 private keys, JWTs, Authorization headers, or ~/.asc_secrets.
zhouzilai626/clarify-idea-skill/skills/clarify-idea Skill
3★ repo将模糊想法、需求、产品请求、工具改造想法、内容计划、工作流改进,或“我不知道怎么讲清楚”的表达,整理成清晰、可执行、可验收的需求说明。 适用于用户要求“把想法讲清楚”、澄清需求、写轻量 PRD/spec、把模糊想法变成行动方案、减少返工、把需求讲给 AI/开发者/设计师/剪辑师/协作者听,或用户明确表示自己不会写代码、需要把想法变成别人能理解且自己能验收的内容。 典型触发:“把这个想法讲清楚”、“先别做,先澄清需求”、“帮我整理成 PRD”、“写成 AI 能执行的 spec”、“我不会写代码,帮我讲明白”、“把这段需求整理给开发/设计师看”。 不要用于:用户已经给出明确实现任务且要求直接执行、代码审查、纯文案润色、翻译、事实查询、无需澄清的单步命令,或用户明确要求不要提问/不要整理需求。
TheBaffledKing/jony Skill
no license3★Design-judgment skill for product interfaces. Use it whenever the user asks to design, redesign, critique, improve, polish, or ship any screen, component, page, layout, or visual change, even when they never say the word "design". Runs one of three modes: CRITIQUE judges an existing screen against sourced principles and their documented limits; LOOP generates isolated before/after moves for approval one at a time and records every rejection with its reason; GATE is a pre-ship checklist that blocks on failures. Built from Jony Ive's own words and the strongest published counterarguments to him, so every rule states where it fails. Governing rule: immersion must be earned by naturalness, not manufactured by spectacle. Reach for this skill when an interface risks being visually impressive and humanly unusable, which is now the default failure of AI-generated UI. Do NOT use it for backend, CLI, infrastructure, data pipelines, or prose editing.
fmind/agent-levers/skills/lever-init Skill
3★ repoBootstrap a repo for agent-levers. Creates .agents/levers/, wires CLAUDE.md/GEMINI.md to import AGENTS.md, writes an AGENTS.md skeleton when missing. Hands off via /lever-new.
xigua0626/darwin-skill-public Skill
3★Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".
dev2k6/ai-agent-personalities/skills/accountability-buddy Skill
3★ repoA focused partner whose entire job is to keep you on track. They ask what you committed to, check whether you did it, and hold you to your goals with firm, encouraging follow-through. Use when you struggle with procrastination, focus, or finishing what you start.
ribeirogab/specwright/plugins/sw/skills/brainstorm Skill
3★ repoYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation, concludes whether the work is a single issue or a milestone (a large delivery decomposed into issues), and writes the issue/milestone artifacts.
MarecGents/marec-agent-skills/skills/agent-orchestra Skill
3★ repo多智能体协作 SKILL —— 拥有 251 个专业 Agent(覆盖 19 个部门)的完整多 Agent 协作系统。包含总调度 Agent、专业部门 Agent 和审查 Agent。当用户需要完成复杂任务、跨领域协作、多阶段工作流,或涉及前端/后端/设计/营销/安全/金融/GIS/游戏等专业领域时,使用此 SKILL。即使是单领域但高复杂度的任务也应启用。注意:不要因为用户没有明确提到"多智能体"就不使用——任何涉及多种技能或专业知识的任务都是此 SKILL 的适用场景。
kunalsuri/ai-fication-kit/.agents/skills/add-feature Skill
3★ repoAdd a feature to this repository the safe way — spec, locate via maps, respect Stability, surgical implementation, verification, knowledge update. Use whenever the user asks to add, build, or implement functionality.
Alibaba quark transoffice qoder
alibaba-quark-scanking/alibaba-quark-transoffice-qoder Skill
3★当用户需要将图片、截图或扫描件转换为 Office 文档(Word/Excel)或 PDF 时,使用此技能。适用于包含复杂表格、合同或图文混排内容的图片或扫描件,可尽量还原原始版式并生成可编辑文档。本技能由夸克扫描王提供转换支持。即使用户未明确提到格式转换,只要用户的需求涉及将图片内容转换为可编辑文档(如 .docx、.xlsx 或 .pdf),也应触发此技能。请勿用于提取纯文本或识别文字内容、图像增强处理或从零创建文档
a28939876-max/skill-lineage Skill
3★Lineage-aware skill evaluation — before installing or recommending any third-party agent skill, trace its family tree (forks, same-name rewrites, credited derivatives), drop pure mirrors, find the family member that actually fits, and screen derivative additions for stowaway instructions. Value for the user — install the version that fits THEM (a localization, a bug-fixing fork, a port for their toolchain) instead of blindly taking the most-starred origin, and catch injected instructions before they reach the agent. Trigger when the user asks "is there a better fork of this skill", "find derivatives", "which version is best", "is this a mirror", "check lineage", "找衍生版", "有没有更好的 fork", "哪个版本最好", "查族谱", or before installing a skill found via star-sorted search. NOT for diffing your own skill's git history (use plain git diff), NOT a security scanner (pair with dedicated tools for that).
maxgfr/secretgate/skills/secretgate Skill
3★ repoUse when the user wants to protect secrets/credentials from being sent to an LLM by a coding agent, install or manage a local secrets firewall, or scan text/files/repos for leaked credentials. secretgate detects secrets (221 gitleaks-derived rules + entropy + Luhn, zero-dependency engine, `node scripts/secretgate.mjs`) in prompts, file reads and tool output BEFORE they reach the LLM API, redacts them to stable placeholders (SECRETGATE_xxx) and restores the real values locally when the agent writes them back to files. Ships installers for Claude Code (hooks), OpenAI Codex CLI (hooks) and OpenCode (plugin). Triggers: 'protect my secrets', 'secrets firewall', 'stop sending credentials to the LLM', 'install secretgate', 'scan for secrets', 'redact secrets before sending', 'block credentials in prompts'.
gomzkov/scout Skill
3★Reveal consequential blind spots after answering. Use proactively for exploration, research, product thinking, architecture, planning, creative work, and decisions, or when the user asks what they missed, what to ask next, or to challenge an idea. Skip routine execution unless a hidden issue could materially change the outcome.
TopEase-AI/topease-customs-mcp-skill/plugins/topease-customs-mcp/skills/topease-customs-mcp Skill
no license3★ repo通过 TOPEASE/Tradee Customs MCP 查询和分析全球海关贸易记录。用于用户要求查询进出口海关数据、买家或供应商出货记录、产品关键词贸易数据、HS 编码贸易数据、国家或市场进出口记录、进口商/出口商线索,或要求配置、接入、排查 TOPEASE 海关数据 MCP 服务时。
volkthienpreecha/modesofthinking/plugins/modesofthinking/skills/modes-of-thinking Skill
3★ repoUse for difficult decisions or when the user invokes think, deepthink, council, sweep, reframe, decide, forecast, redteam, experiment, or debrief. Routes problems through fitting lenses, evidence hygiene, experiments, and bounded independent-agent councils.
pingidentity/agent-plugins/plugins/ping-identity/skills/ping-app-integration Skill
3★ repoUse when writing code or wiring an SDK to integrate Ping Identity into a web, mobile, or backend app — Android/iOS/JavaScript SDK installation, OIDC authorization code + PKCE flows, token management, ForgeRock-to-Ping SDK migration, and app-side troubleshooting (redirect_uri_mismatch, CORS, token refresh failures).
hnikoloski/imlazy Skill
3★Use when you want tier-aware agent routing — detects task complexity, routes to Quick/Standard/Heavy/Vault workflows, and auto-dispatches the right agent. Trigger with /imlazy or "i am lazy" prefix.
Chariton-kyp/Memgentic/memgentic Skill
3★ repoUniversal AI memory — recall past decisions, learnings, and context from all your AI conversations (Claude Code, Gemini CLI, ChatGPT, Aider, etc.)
d-init-d/aleph-skill Skill
no license3★Evidence-grounded causal timeline simulation for AI CLI and IDE hosts that support Agent Skills or an Aleph adapter contract. Use for counterfactual history, prospective interventions, hybrid past-to-future projections, butterfly effects, calibrated scenario analysis, domain-pack modeling, evidence-based or assumption-only actor decisions, and auditable uncertainty.
Edison-777-crypto/sports-prediction/plugins/sports-prediction-codex-plugin/skills/sports-prediction Skill
3★ repoStructured sports match prediction workflow emphasizing transparency, uncertainty, data freshness, and educational analysis. Not betting or financial advice.
cku3987/codex-local-cleanup-skill/codex-local-cleanup Skill
3★ repoClean local Codex Desktop metadata under $CODEX_HOME or ~/.codex by safely identifying mobile-visible stale projects, non-active project threads outside saved project roots, archived threads, deleted workspace cwd entries, session JSONL files, thread indexes, global state, config trust entries, and SQLite rows; always back up first, keep saved projects/projectless chats/current thread unless explicitly requested, and verify with read-only checks before reporting.
h5i-dev/h5i-ctx2img/skills/ctx2img Skill
3★ repoCut context tokens by rendering it as images. `ctx2img paint <path|->` turns any text-shaped input (a repo, a directory, a file, markdown, stdin) into dense images that carry the full text at 60-75% fewer tokens, with stable handles and a verbatim factsheet; `ctx2img read` recovers guaranteed-exact text. Use before ingesting any large text or at the START of any task in an unfamiliar or large repo.
skoppisetty/paxel-skill Skill
no license3★Score your own Claude Code and Codex CLI sessions on YC Paxel's exact 5-axis rubric, locally, with Claude as the scorer (no upload, no backend). Use when the user wants to see how Paxel would evaluate their work, run a self-assessment on Execution Leverage / Steering / Engineering Quality / Product Thinking / Planning, or check their builder score without sending sessions to YC.
feilipu/8085-skills/.grok/skills/extended-usage Skill
3★ repoUsage hints and coding preferences for Intel 8085 extended (undocumented) instructions, using Zilog mnemonics. Strong rule: stack-only locals and intermediates; static/BSS only for state that must survive across function calls — never for intermediate storage. Prefer when choosing idioms for stack frames, reentrancy, 16/32-bit shifts, K-flag loops, sub hl,bc compares, or optimizing 8085 assembly beyond the bare opcode map. Complements /opcode-reference. Use when the user runs /extended-usage or asks how to use 8085 extended ops effectively.
chrisgeenyc/price-on-the-proof Skill
no license3★Set a defensible price for a consulting engagement, advisory retainer, coaching package, workshop, training, or cohort course by triangulating three anchors — the value created (an ROI estimate), the market band (real comparables), and a cost floor — then tune it over time with a quarterly close-rate diagnostic. Built for solopreneurs, independent consultants, coaches, agencies, and course creators who sell expertise, not software. Use when the user asks "what should I charge," "how do I price this," "am I underpriced," "should I raise my rates," "price this engagement/proposal," "value-based pricing for a service," "productize my pricing," "how much for a workshop/course/retainer," or wants to justify a fee to a client. NOT for self-serve SaaS subscription tiers (that's a packaging problem, not an offer-pricing one).
afloy011-spec/lora-dataset-prep Skill
3★Use when preparing image datasets for LoRA training in Ostris AI Toolkit / Z-Image Turbo. Covers character LoRA image selection (15-30 imgs, shot variety, 1024px), captioning rules (natural language, media type, trigger token), folder structure, .txt sidecars, validation, VLM auto-captioning, and resize. Use when the user wants to organize raw photos, write captions, choose a trigger word, or validate a character dataset before training.
coroboros/agent-skills/skills/agent-creator Skill
3★ repoCreate, configure, and orchestrate Claude Code subagents — specialized Claude instances with focused roles and limited tool access. Covers YAML frontmatter (name, description, tools, model, permissions, hooks, MCP servers), system prompt design, tool restriction patterns, background execution, and multi-agent orchestration. Use whenever the user mentions subagents, delegation, specialists, agent configs, `.claude/agents/`, the `/agents` command, or wants to parallelize work — even when they just say "background agent" or "delegate this".
densmirnov/hidden-achievements-skill Skill
3★Build, operate, or review a hidden daily achievements system for team agents. Use when Codex needs to add hidden achievements, gamify team work, generate a sealed daily achievement deck after a daily brief or scheduled workday snapshot, evaluate chat/task/project-board/knowledge-base events, prevent retroactive awards, enforce anti-spam and prompt-injection safety, manage private/public ledgers, or summarize opened achievements in team operations.
sanwu-maizi/CERES Skill
3★Review untrusted coursework and project showcase submissions against supplied instructions, templates, rubrics, tests, and report requirements. Use for isolated, evidence-based assessment of source code, experiment results, reports, demonstrations, and AI or agent implementations involving tools, memory, ReAct, RAG, planning, or multi-agent workflows; for controlled reproduction under execution limits; or for producing consistent individual and batch review reports.
TueJon/webmcpify/skills/webmcpify Skill
3★ repoMake a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".
redamancy231-create/claude-skills/kill-test-first Skill
3★ repo[决策:预注册] Pre-registration audit for new research directions, quant strategies, or thesis topics: falsifiable hypothesis, prior-art check, strongest counter-argument, death criteria before results, cheapest falsification with strong baseline, three-state verdict (GO/STOP/REDESIGN). Use before committing resources to a new direction. Not for bug fixes, experiment reproduction, or routine controlled experiments.
netcopilot-labs/promptize/skills/promptize Skill
3★ repoTurn a rough ask into a structured prompt that the user reviews before execution. When the user invokes "/promptize <rough-ask>", Claude parses the ask, clarifies until ≥95% confidence, assembles the prompt using a 9-field canonical structure (Goal, Context, Inputs, Expected output, Scope, Constraints, Success criteria, Open assumptions, Examples), shows it for approval, then executes (in-session by default; optionally in an isolated subagent to avoid context contamination). Approved prompts auto-save to ~/.claude/prompts/ as a versioned history. User-initiated only — never convert a normal request into promptize mode proactively.
lythos-labs/lythoskill/packages/lythoskill-arena/skill Skill
3★ repoTest play for skills and deck configurations. DEFAULT: agent reads config, spawns parallel subagents via native Agent tool, judges outputs. Single-deck test AND multi-deck A/B comparison both run agent-orchestrated (no CLI). Cross-player comparison (kimi vs codex) is the ONLY case that needs the CLI runner. Always restores parent deck. No install, no working-set pollution, no deck overwrite. Subagent-friendly: resumes interrupted runs from saved state. CRITICAL: experiments run in `/tmp`, never in committed directories. Subagent inherits parent CWD — prompt must explicitly set workDir.
sinberCS/grill-with-docs-qa-filter/skill Skill
3★ repoSupplemental decision-filtering policy for grill-with-docs. Use together with the primary skill when a user wants fewer, higher-value questions: automatically resolve routine decisions with the recommended default, reserve 5%-20% of decision points for major or genuinely controversial questions, and ask exactly one question at a time. This skill is not standalone and must not replace the primary skill's exploration, terminology, documentation, ADR, or decision-recording workflow.
TheColliery/CoalLedger/plugin/skills/doc-consistency Skill
3★ repoDocs-health contradiction scan — docs that disagree with EACH OTHER: the same fact stated two ways in two places, terminology drift (one thing under several names, or one name for several things), copy-paste blocks that were updated in one home and not the other, and cross-LANGUAGE drift (a doc and its counterpart in another language no longer say the same thing). Catches CONTRADICTORY doc sets. Triggers on: "/doc-consistency", "doc-consistency", "docs contradict", "terminology drift", "are the translations in sync". Semantic (paid, consent-gated — comparing meaning across files is judgment, not pattern-matching). Severity judged by context, never mechanical; CONFIRMED contradictions and SUSPECTED tensions reported separately.
Flowerf19/agents-skills/architecture-docs Skill
3★ repoCreate and maintain concise project architecture and agent guidance docs and root README files based on real repository evidence.
drakulavich/iago/iago Skill
3★ repoAppend a Mermaid diagram (sequence, flow, class, or entity-relation) to a GitHub PR's existing /review comment. Like Iago the parrot from Aladdin, this skill loudly squawks a visual summary on top of an existing review. Also triggered by /squawk. Use after the /review skill finishes, or when the user asks to add/append a diagram to a pull request review, or says "squawk". Auto-detects the most useful diagram type from the diff; accepts an explicit override.
Lucas-Fong/html-report-stable-base Skill
3★Use when supplied content or an existing HTML report needs a stable editable browser shell in either long-screen single-page mode or 16:9 PPT mode, including global and per-element styling, ECharts canvas support, standalone HTML delivery, or optional PPTX export in PPT mode.
thelarryrutledge/counterpoint Skill
3★Run a substantive idea, draft, design, architecture, strategy, or decision through a modular Council → Chair → Executor → Reviewer workflow. Use when the user asks to council, develop, pressure-test, stress-test, poke holes in, strengthen, review, synthesize, create an implementation plan, or turn a complex set of perspectives into controlled convergence and actionable artifacts. Do not use for simple factual lookup, pure creation with no review need, trivial yes/no choices, or low-stakes decisions with no meaningful tradeoff.
joshsmithxrm/ppds-skills/.claude/skills/release Skill
3★ repoCut a PPDS Skills package release — get the recapture, decide the version bump, clean up prose, update CHANGELOG, tag + GitHub Release. Use when PPDS ships a new stable CLI/MCP that the skills package must track, or to publish any skills-package version bump.
Martin-Hausleitner/martins-awesome-skills/skills/analysis/tool-comparison-heatmap Skill
3★ repoCreate interactive feature-comparison heatmaps that score, rank, and crown winners across multiple tools, repos, or products. Use this skill whenever the user asks to compare tools, software, GitHub repos, frameworks, extensions, or any set of alternatives across multiple features or criteria — especially when they want a visual matrix, heatmap, scorecard, ranking, or 'who wins' analysis. Also trigger when the user says things like 'compare features', 'which is the best', 'feature matrix', 'score them 1-100', 'rank these tools', 'Vergleich', 'Heatmap', 'wer gewinnt', or 'Gewinner küren'. The output is always an interactive React (.jsx) artifact with clickable GitHub/repo links, last-update dates, color-coded scores, sorting, and an automatic winner badge.
aayushiagratha/job-search-score Skill
3★Search LinkedIn Jobs without logging in, verify every listing's real company identity and agency status (never trust the card text), check visa sponsorship against the official UK register, rank by fit x sponsorship x competition, and — only after you confirm — build tailored application documents in your own CV format. Triggers include "job search", "find me jobs", "score this role", "ATS analysis for X".
zxhydfzr/website-seo-audit Skill
3★Crawl any website and produce a graded SEO diagnosis — on-page (title, meta, headings, canonical, mobile viewport, image alt, thin content), technical (HTTPS, robots.txt, sitemap.xml, broken internal links, duplicate titles/meta, near-orphan pages), and structured data (JSON-LD / Schema.org validity and required fields). Zero config, no API keys, pure Python standard library. Use when the user wants to audit, diagnose, check, or review a website's SEO, find SEO problems, or asks "how is my site's SEO / 帮我诊断这个网站的SEO".
nelsonwerd/ideate-skill/ideate Skill
3★ repoTake a fuzzy idea (or an existing thing you want to improve) through a disciplined funnel — explore → pressure-test → converge — and produce one living CONCEPT_BRIEF.md: a locked concept + phased roadmap. Acts as a blunt, honest co-founder (permission to overrule you), forces a success metric and a kill criterion before any roadmap, and hands off cleanly to the prompt-pack skill for building. ALWAYS invoke when the user says any of "help me figure out what to build", "I have an idea for…", "is this idea any good", "pressure-test this idea", "should I build / should I rebuild X", "evaluate whether my app/idea is worth building", "where are we really at", "is this idea or app worth pursuing", "iron out / scope / spec this concept", or "turn my idea into a plan/roadmap". Also invoke proactively when someone is reasoning about WHAT to build or WHETHER an idea is worth it — before any code or prompt pack exists.
The same file is in 1 other repository
thienhoc/dwi-by-thienhoc/modules/dwi-all-in-one Skill
3★ repoApply the relevant Dwi lenses together when several observed workflow problems co-occur. Select only the lenses the task needs, preserve a silent fast path for clear reversible work, and keep authority and evidence explicit. Prefer a focused module when one issue dominates.
AndreRatzenberger/dojo/example/taste-extractor/v0.1/candidate/taste-extractor Skill
3★ repoExtracts portable taste from any accessible medium into an evidence-traced profile and downstream production brief. Use when the user asks to extract, distill, reverse-engineer, or capture the style, taste, feel, visual language, voice, or character of an interface, image, text, video, music, object, brand, or experience so another agent can create new work with the same character without copying source content. Also use for cross-medium style translation. Refuse to fabricate a profile when the source cannot be inspected. Not for directly generating the final artifact unless the user asks for both extraction and creation.
petehottelet/spreadsheet-auditor Skill
3★Audit an existing spreadsheet or financial model for correctness defects: live formula errors, broken or deleted references, hardcoded values inside formulas, off-by-one and inconsistent aggregate ranges, totals that do not reconcile or cross-foot, circular references, hidden rows/columns/sheets affecting outputs, and data-hygiene risks like numbers stored as text. Use when the user asks to review, check, validate, audit, debug, or find errors in an .xlsx, .xlsm, or .csv they already have. Produces a severity-ranked findings report and optional annotated copy. Do not use when the user wants to create, build, format, or rewrite a spreadsheet.
catharinepalatial88/bazi-skill Skill
3★四柱八字命理分析。通过交互式步骤收集出生信息(姓名、曾用名、阳历/农历生日、时辰、性别、出生地), 排出四柱八字,参照经典命理典籍(穷通宝典、三命通会、滴天髓、渊海子平、子平真诠等)进行专业分析。 Use this skill whenever the user asks for 八字、四柱、命理、算命、Bazi、fortune telling、 birth chart analysis, or wants to know about their 八字命盘、运势、大运、流年. Triggers: "算八字", "看八字", "批八字", "排八字", "四柱", "命盘", "算命", "帮我看看八字", "我想算八字", "分析八字", "排盘", "bazi", "bazi analysis", "fortune telling", "birth chart", "算一卦", "看运势", "命运分析". 即使只是提到"算命"、"八字"而没有明确说要用skill,也应该使用此skill。
The same file is in 1 other repository
Synchromy/synchromy-skills/skills/council Skill
3★ repoConvene a multi-model adversarial council to resolve a contentious decision. Spins up N fresh-context members across model families (Anthropic + OpenAI/Codex + Moonshot by default; Z.ai and xAI in gauntlet tier when provisioned) playing structured roles (Skeptic, Builder, Strategist, Operator), runs them through Position -> Cross-rebuttal -> Chair-synthesis, and emits a markdown decision packet with TL;DR, recommendation, named dissents, open questions, and transcript appendix.
patonkikh/APES/docs Skill
3★ repoAI Product Engineering Skills Platform (APES) is an open library of Engineering Playbooks for AI agents. Each Skill is a single skill.md file that defines the methodology for completing one specific engineering task.
doublesq97-ui/know-me/skill Skill
3★ repoCollaboration-profile interview that creates or refreshes a reusable AI Collaboration Manual. Use when the user invokes Know Me ($know-me or /know-me), chooses first use, quick start, or deep calibration, asks for an AI collaboration manual, provides an existing manual to update, wants stable long-term collaboration preferences, or reports repeated AI misunderstanding. Do not trigger on bare "开始", "初次使用", or "如何开始" without Know Me or collaboration-profile context.
s-a-s-k-i-a/design-md-skill Skill
no license3★Generate or update a DESIGN.md for the current project following the google-labs-code/design.md specification. Inventories existing design inputs (theme.json, Tailwind config, CSS custom properties, DTCG tokens, brand assets), maps them to typed tokens (colors, typography, rounded, spacing, components), writes the spec-conformant prose, and validates the result with the official `@google/design.md` CLI. Use when the user asks to "create a DESIGN.md", "document the design system", "extract design tokens to DESIGN.md", "generate design.md", or "sync the visual identity into a machine-readable format".