The catalog
608,119 rows, by stacks then stars
rvdsmaile/working-backwards/.agents/skills/break-prd-into-issues Skill
no license0★ repoCreate a reviewable, dependency-ordered issue backlog from an approved technical PRD. Use when a team needs independently grabbable vertical slices before publishing to any issue tracker.
brlin-tw/implementing-new-features Skill
no license0★Provide guidelines on how to implement new features in a project. Should be used when adding or updating features.
Paldom/terminaltor/.claude/skills/add-skill Skill
0★ repoAuthors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).
The same file is in 11 other repositories
Gnilevell/web-prototype-designer Skill
0★Use when Codex needs to turn an existing product concept, product plan, PRD, workflow, or feature description into a web, mobile-web, app-like, dashboard, form, or clickable browser prototype, especially when layout, visual direction, sample images, interaction states, component-library reuse, or browser validation matter.
Codewalnut backend resume shortlisting skill
codewalnut-labs/codewalnut-backend-resume-shortlisting-skill Skill
0★Evaluate and rank one or many resume PDFs for CodeWalnut's Java backend engineering roles using its historically calibrated, evidence-weighted hiring rubric. Use this skill whenever a user asks to shortlist, screen, compare, rank, or explain hiring recommendations for resumes from uploaded PDFs, a local folder, or a Google Drive file/folder link—even if they only say “review these candidates” or “find the best backend engineers.” It distinguishes demonstrated production engineering from keyword lists and returns an auditable recommendation for every resume.
thallostudio/Thallo/skills/thallo-remix Skill
no license0★ repoFind, choose, and remix Thallo website design specs into new or existing codebases. Use when a user asks to compare the Thallo catalog, build from a supplied Thallo spec, combine a web design direction with other materials, integrate selected design ideas into an existing site, or recover an incomplete website remix. Also use for a new website request when a Thallo catalog match could materially improve the result.
Marineconnect/marineconnect-agent-skills/plugins/marineconnect-ops/skills/marineconnect-admin-audit Skill
no license0★ repoInspect MarineConnect admin and audit workflows. Use for OAuth MCP connected clients, tool audit logs, admin user search, SuperAdmin activity history, sensitive action audit, compliance approvals, account profile/AI, app release configs, tenant currency/admin pages, runtime connectivity, and permission-related evidence.
benblackthorn/agent-skills/skills/progress-log Skill
0★ repoMaintains one scoped transactional progress-log.md at the repository root or an explicit safe subpath, plus bounded repository context. Use for orientation, completed outcomes, current state/source pointers, handoffs, exact canonical-log bytes or bounded projected context, validation, repair, branch delta, reviewed cleanup, merge, or v1 migration. Do not activate in an opted-out repository. Do not use for durable facts, claims/evidence, freshness, transcripts, project tracking, search, child logs, or secrets.
kunhai-88/character-naming-author-skill/skill Skill
0★ repo为中文短剧、影视剧、小说、AI漫剧和原创故事取人物名、改名、设计乳名外号法号与整剧称呼系统,并审查名字是否真实、好记、声音可辨、能被人物关系和剧情占有。用户提出主角取名、名字没记忆点、像AI或网文名、太普通、年代地域不符、整剧姓名混乱、需要优秀作者式命名时使用。
SubliminalCoding/orchestrate-it-out/skills/orchestrate-it-out Skill
0★ repoRun a high-level GPT-5.6 Sol orchestration workflow for substantial coding work. Sol inspects a clean Git repository and produces a comprehensive sealed plan with exactly five bounded workstreams; the controller then spawns exactly five Claude Fable 5 workers, dispatches each brief to an exact pane, waits by dependency wave, requires receipts, and runs mechanically enforced scope and verification gates. Use when the user asks for Sol to orchestrate five Fables, wants a thorough plan followed by a five-agent build, or explicitly says "orchestrate it out." Do not use for small edits, non-coding requests, dirty repositories, or requests that require independent semantic review.
Hyacehila/tech-blog-writing Skill
0★中文技术博客与工程文章的多轮共创写作 Skill。用于与用户共同完成选题、读者任务、标题、文章结构和章节注释,再撰写或重构中文技术博客、教程、操作指南、参考文章、原理解释、实践复盘、架构决策、源码解读、实验或 benchmark、工具发布文章;也用于全文润色、局部改写、文章内技术主张核查、定稿、发布前检查,以及用户明确要求的独立多视角审稿。Use for collaborative Chinese technical writing, editing, fact-checking, publication checks, and explicitly requested independent review. 不用于小说、散文、营销软文、通用代码审查、仓库缺陷分析或脱离文章语境的普通技术问答。
hugyu/AgentKernel/.codex/skills/agentkernel-commit-task Skill
0★ repoValidate and commit one completed AgentKernel development or documentation task as an atomic local Git commit. Use after making repository changes for AgentKernel, when finishing an AK-* task, or whenever the user requires every completed change to be committed. Inspect scope, preserve unrelated work, run relevant checks, stage explicit files, and commit without pushing.
FarooqAlaulddin/plone-skill/skill/plone Skill
0★ repoExpert knowledge of the Plone CMS ecosystem. Use for ANY question or task involving Plone, Volto (React frontend), Classic UI, Zope, ZODB, plone.restapi, plone.api, Dexterity content types, behaviors, GenericSetup, workflows, portal_catalog, diazo/barceloneta theming, Volto blocks/add-ons, cookieplone/buildout project setup, deployment (Docker, ZEO, RelStorage, varnish, virtual hosting), migrations/upgrades (collective.exportimport, plone.exportimport), testing (plone.app.testing, Cypress), add-on selection, or Plone roadmap/community direction.
xnchu/ads-paper-search/skills/ads-paper-search Skill
0★ repoUse when searching for scientific papers in astronomy, astrophysics, space physics, heliophysics, or planetary science — finding literature by topic/author/year, looking up citations or references of a paper, exporting BibTeX, resolving a bibcode/DOI/arXiv ID, or computing citation metrics. Connects to the NASA ADS (Astrophysics Data System, ui.adsabs.harvard.edu) API.
shuvo-asl/deploy-notes-skill/deploy-notes Skill
0★ repoGenerate deployment release notes for ops and testing teams from a raw .docx file containing bullet-point features/bugs with screenshots — produces a formatted Word document (with images) and a plain-text markdown version (no images).
0xkaveh/debug-orchestrator/skill/debug-orchestrator Skill
0★ repoOrchestrate evidence-led, security-first debugging across local code, tests, runtimes, browsers, and CI. Use when Codex must diagnose a bug, failing test or build, runtime exception, intermittent behavior, frontend/browser failure, performance regression, or failing GitHub Actions check; reproduce the problem before editing, maintain at most three falsifiable hypotheses, route to the cheapest useful tool, apply a minimal root-cause fix, add a regression test, and verify the result with recorded evidence.
JesseZhang97/checkpoint-thread/skill/checkpoint-thread Skill
no license0★ repoAttribute Codex repository edits to their thread and business goal before organizing verified changes into commits and shipping them. Use on every repo-mutating task; the fail-open hook observes recognized writes without locking the branch or blocking normal tools.
swd3k/skills/agent-skills/desktop-apps/desktop-tray-and-window Skill
0★ repoImplement system tray, single-instance, minimize-to-tray, and window lifecycle for desktop utilities. Use when building tray apps, background helpers, or fixing multi-window/instance bugs.
linkrunner-labs/skills/skills/ad-networks/meta-install-referrer Skill
0★ repoSet up Meta Install Referrer so Linkrunner can read Meta (Facebook/Instagram) ad campaign metadata from the device and improve Meta attribution, including view-through installs. Android only - the setup is making your Facebook App ID available to the SDK via AndroidManifest.xml. Use when someone asks to enable Meta install referrer, improve Meta / view-through attribution with Linkrunner, or add the Facebook App ID for Linkrunner on Android.
arclabshq/arc-labs-studio-team/skills/chief-of-staff Skill
0★ repoTurns competing goals, projects, and open loops into clear priorities, decisions, ownership, and follow-through. Use when the user needs an operating plan, weekly review, decision brief, or cross-functional coordination.
Sophia-wqr/tighten-chinese-writing/skills/tighten-chinese-writing-v2 Skill
no license0★ repoDraft, rewrite, or audit Chinese copy for accuracy and concision. Use for PPT copy, articles, resumes, reports, scripts, course materials, or marketing copy when the user asks to 精炼、准确、删废话、降 AI 味、删除‘不是……而是……’、清理空修饰语、‘今天’等无效时间锚点、元话语或重复;preserve facts, meaningful time and version boundaries, use peer-level instructional navigation, and avoid promising learning outcomes on the reader's behalf.
Designing ai video storyboards
venscn/dream-skills/skills/designing-ai-video-storyboards Skill
0★ repoUse when 为 AI 电影、短剧、漫剧、口播、广告或知识视频把剧本转成分镜,规划逐镜生成,约束角色、场景与道具一致性,设计对白、音效、音乐与镜头拼接,或交付可供生图、图生视频、多模态生成和后期剪辑使用的镜头包。
brain-marchine/verify-done-skills/skills/verify-done Skill
0★ repoFail-closed verification before accepting Done/Fixed/做完了. Use when the user or agent claims a task is finished, fixed, complete, verified, or ready to merge — including UI fixes, bug fixes, overflow, layout, tests passing, or "I'm done". Also trigger for 做完了、修好了、验收、验证完成、可以合并. Runs bundled check scripts and refuses verbal Done until PASS.
askfanxiaojun/deploy-github-pages-domain Skill
0★自动配置并验证由 Cloudflare 托管域名的 GitHub Pages 自定义域名。适用于用户希望把 GitHub Pages 网站部署到个人子域名、配置或更新 Pages Custom domain、创建或修复 Cloudflare CNAME 记录、更新仓库 About 主页/描述/Topics、处理 README 或 CNAME 文件、启用 HTTPS,或者替代反复操作 GitHub Settings 与 Cloudflare 控制台的手工流程。
abc123dx/agent-skill-aegis/examples/safe Skill
0★ repo读取用户明确选择的文档目录内的 Markdown 文件。
jpoindexter/design-biz-skills Skill
no license0★Use when the user invokes /designbiz, asks a design-business question (positioning, niching, what to charge, proposals, retainers, client red flags, scope creep, hiring vs staying solo, productizing or subscription offers, selling the studio), or describes a studio stuck-pattern (treated as an order-taker, underpricing, feast-famine pipeline, feedback hell, one client dominating revenue). Dispatcher that routes to the right frameworks from the design-biz-skills library (134 frameworks from 6 books) and applies 2-4 of them to the user's situation.
SympleScripts/afterdeal Skill
0★Portable B2B post-sale customer-service agent skill — universal engine + swappable domain packs
paladini/agent-skills/skills/devto-publish-expert Skill
0★ repoResearch, write, optimize, validate, and publish specialist technical articles for DEV Community with exactly four relevant tags and a draft-first safety workflow. Use when creating, rewriting, reviewing, scheduling, or publishing DEV.to tutorials, project launches, engineering explainers, case studies, or opinionated developer posts, including through a DEV/Forem MCP server or API.
sebastianhauer/skills/plugins/conventional-commits/skills/conventional-commits Skill
0★ repoConventional Commits format and style rules for git commit messages -- types, scopes, subject and body, trailers, and prohibited patterns. Use when writing, reviewing, or fixing a commit message, choosing a commit type or scope, or asking about commit message conventions or Conventional Commits.
caoproAI/customer-chat-rescue-cn Skill
no license0★面向中国个体老板、实体店、个人IP、自由职业者、顾问、销售和客服的客户聊天诊断 Skill。用户提供已脱敏的微信、企业微信、私信、客服或销售聊天记录,以及产品服务和期望下一步后,检查需求是否摸准、价值是否说清、信任是否建立、风险是否回应、下一步是否顺畅;引用具体原话,找出客户犹豫、不回复、只问价格或迟迟不决定的主要阻碍,直接生成下一句可复制回复、三个追问、报价或方案骨架和礼貌跟进计划。用户询问客户为什么不买、聊天哪里说错了、现在该怎么回、怎样问需求或怎样自然推进成交时使用。
skyestrela/ai-agent-skill-preview/bug-reproduction-brief Skill
0★ repoTurn a vague bug report into a minimal, evidence-backed reproduction before proposing a fix.
cleudice/kiro-ai-team/skills/audit-integration Skill
0★ repo(Somente auditor) Audita o repo inteiro atrás do que a revisão por PBI não vê — duplicação entre PBIs, drift spec×código, segurança inconsistente — e emite briefs. Use a cada ~5 merges (o merge-gate avisa) ou quando pedirem 'auditoria', 'varre o repo inteiro', 'tem duplicação?'.
saezbaldo/deploytoagents-skills/deploy-app-to-agents Skill
0★ repoAudit and distribute an existing app, API, SaaS, MCP server, or agent so AI assistants can find, verify, recommend, and invoke it. Use when a user asks how to launch or distribute software to agents or LLMs, improve agent discoverability, publish MCP/A2A metadata, create machine-readable discovery surfaces, compare distribution channels, or measure whether unbranded prompts mention their product.
Implementation handoff execution
Pingbook-co/agent-skills/skills/implementation-handoff-execution Skill
0★ repoUse when an approved phase and handoff documentation set needs serial or controlled-parallel implementation, continuation, resumption, context recovery, validation, integration, or completion.
Shavy72/claude-skill-sensei Skill
0★Yoda-styled coding mentor. Use when the user invokes /sensei (optional argument harsh|deep|cheap|onboard|forget), asks for a code-habit review, a project audit, a 5-Whys onboarding or a Pareto triage — or when a SessionStart hook injects a Sensei trigger (idle >= 10h, new project detected, anti-pattern detected). Trigger words EN: sensei, yoda, mentor, audit me, review my habits, why am I building this, what should I focus on. Trigger words DE: sensei, yoda, Mentor, audit mich, Gewohnheiten pruefen, warum baue ich das, worauf soll ich mich fokussieren. Auto-mode-detection (onboarding for a new project, FULL after long idle, NORMAL otherwise), 5-Whys onboarding, Pareto triage, why-chain alignment. Defaults work without any setup.
xiewxin/agent-skill-maintainer/skills/agent-skill-maintainer Skill
0★ repoUse when reviewing an Agent Skill after real use, user correction, external feedback, or observable decision failures, especially before proposing changes to a Skill repository.
prateek11rai/tldraw-canvas-kit/skills/activity-diagram Skill
0★ repoDraw a UML activity diagram in the open tldraw offline canvas — actions, decision/merge diamonds, fork/join bars for parallel flows, initial/final nodes, guarded edges, and optional swimlanes per owner. Use when the user asks for an activity diagram, a swimlane diagram, or a workflow with parallel branches or responsibilities split across roles/systems (for a simple linear process, the flowchart skill also fits). Produces the same top-down flow layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.
qlhouseClub/product-expert Skill
0★End-to-end product leadership grounded in first principles, business reality, and evidence. Use for 产品分析、业务分析、市场与商业模式、定价与GTM、增长、用户研究、需求拆解、需求对抗审查、PRD、路线图、原型与用户流程、指标与A/B测试、留存与SaaS分析、干系人协同、决策校准与组织学习、领域建模、数据库/API/事件/埋点设计、AI产品与Agent/RAG、发布复盘,or when auditing a product plan. Produces decision-ready artifacts with explicit assumptions, trade-offs, and traceability from business outcome through requirements, data, delivery, and learning.
ngaxavi/skills/skills/kubernetes-troubleshooting Skill
0★ repoSystematic triage of failing Kubernetes workloads using kubectl. Use when a pod is Pending, CrashLoopBackOff, ImagePullBackOff, OOMKilled, Error, or stuck Terminating; when a PersistentVolumeClaim will not bind; when a Service returns no endpoints or connections are refused; when an app is reachable inside the cluster but not from outside via Ingress or the Gateway API; when a Deployment's replicas never appear because a ResourceQuota, LimitRange, Pod Security, or admission webhook rejected them; when DNS resolution fails inside the cluster; or when a node is NotReady or reporting disk, memory, or PID pressure. Use when a Secret or config is missing or a live change keeps reverting (operator-synced secrets, GitOps reconciliation). Use when someone asks why a workload is not running, not reachable, or not scheduling. Use it too for proactive health checks — when someone asks "is the cluster OK?" or whether something is healthy even though nothing is obviously failing, since a green-looking cluster can still hide restart loops, filling disks, and lost redundancy. Works on any Kubernetes cluster. Prefer this skill over guessing: it defines the order to inspect things so evidence is gathered before any change is made.
arnaudjnn/billing-tools Skill
0★Add drop-in auth and billing to a Stripe + WorkOS app with the @arnaudjnn/billing-tools library (Next.js, Hono, Bun, Deno, any Node host). Use this skill whenever the user wants to monetize an app, MCP server, or API, charge per token or per credit, add subscriptions or API-key auth, let AI agents self-register with auth.md and pay per request with Stripe MPP machine payments, or wire a token wallet, Stripe Checkout, auto-reload, a Customer Portal, invoices, seat limits, or per-seat token grants, and expose it all as MCP tools, a REST API, or a CLI. Covers the pluggable WorkOS-org adapter (WorkOS-only or WorkOS plus a DB mirror), declarative plans auto-provisioned in Stripe, and a zero-webhook event-polling sync. Triggers on "add billing", "monetize my agent or tools or API", "Stripe and WorkOS", "charge per token", "agent auth.md", "machine payments", or "MPP", even when the library is not named.
ezra-y/fruit-picker/fruit-picker Skill
0★ repoUse when 用户发来水果照片、问怎么挑水果/这颗能不能买,或需要基于照片与用户补充信息评估成熟度、品质风险、身份/品种置信度和购买建议。
onijizo/signal-scout/skills/signal-scout Skill
0★ repoFind, trace, and critically compare underexposed but high-quality code, models, local LLMs, LoRAs, GGUFs, theories, specifications, papers, prompts, skills, workflows, and tools across GitHub, Hugging Face, X, papers, blogs, registries, and communities. Use whenever the user asks for prior art, existing solutions before building, Build Grounding, quiet or hidden gems, original sources, derivative maps, model lineage, good-vs-bad stasis, or evidence-based technology selection, even when they do not name Signal Scout. Also trigger on 「低露出の良作」「源流を辿る」「派生モデル比較」「既存完成形を探す」「人気ではなく品質で探す」 and 「○○について、存在する完成度の高い理論や実装を確認したい」. Research exhaustively behind the scenes, but present the normal answer only as a direct conclusion followed by artifact name, source site, URL, and a concise summary. Do not use for a simple summary of one known artifact or when the user explicitly wants only a popularity ranking.
RayJason/rayjason-skills/harness-agents-md Skill
0★ repo创建、审计和优化全局与项目级工程化的 AGENTS.md,覆盖作用域、协作、Git、验证与交付。
personwiseai/skills/skills/personwise-create-course Skill
0★ repoCreate, refine, resume, publish, or query polished PersonWise courses from topics, text, PDF/PPTX/DOCX/Markdown/TXT documents, or reference images through the paired OAuth MCP. Use for staged course authoring, source-grounded lessons, slide and narration review, visual QA, presenter selection, layout configuration, link sharing, or Topics review submission.
MyAiFreedomSystems/incredagents/brief-me Skill
no license0★ repoSlash-invoked as `/brief-me`. the user's single trigger to receive a team advisory report on a decision or research topic the conversation already established. The agent is the assembler, never a voice in the brief. The brief contains team voices (Advisor, Kaizens, Linter, Builder, plus any others the user names) presenting options for her to decide. ALWAYS pushes to Watchtower DigitalOcean's owner-only briefs surface. For interactive the user-triggered calls, never asks about a local copy. For GOALTEAM / autonomous-long-haul-team / any orchestrator-dispatched call, ZERO local briefs — Watchtower DigitalOcean is the only surface.
that-guy-jamie/legible-legitimacy/skills/legible-legitimacy Skill
0★ repoActivates when a task would create, exercise, expand, or bypass a sensitive capability — production or high-consequence mutation outside an approved gate; creating or handling authentication material for another identity; impersonation or delegated access; secrets entering context, output, logs, or diffs; scraping or bulk external fetches outside an approved runner; security testing with exploit-like payloads or targets; or launching bulk, asynchronous, or background jobs. Does not activate for ordinary discussion, technically enforced read-only review, or patterned operations already running through an approved, least-privilege, audited surface — unless the task proposes bypassing, weakening, or materially expanding that surface. Restructures the work so authorization, scope, reversibility, actor identity, and accountability are evidenced by the mechanism and artifacts rather than asserted in prose.
pengcong2020520/youtube-ai-research-skills/skills/youtube-podcast-deep-analysis Skill
0★ repoIncrementally collect the newest public YouTube transcripts for a named creator or the built-in high-quality AI podcast collection, then turn unanalysed episodes into long-form Chinese first-principles deep readings and save both transcripts and analyses as Obsidian-compatible Markdown. Use when Codex needs to run the complete YouTube podcast research workflow, update a local transcript archive without duplicates, analyse existing transcript notes one episode at a time, or keep an English and Chinese AI information repository current. Never download video or audio.
J03Fr0st/skills/skills/html-writeup Skill
no license0★ repoSelf-contained HTML write-ups — a single shareable .html document carrying prose, diagrams, tables, and code, verified in a real browser. Use when the user wants findings, an analysis, an audit, a comparison, or a design doc presented as a visual document rather than terminal text; asks for an HTML report or standalone page; or wants a Mermaid diagram rendered.
a252937166/MiroFishCodex/skills/mirofish-codex Skill
0★ repoRun MiroFish as a Codex or Claude skill with local temporal graph memory and no project-initiated generation API calls. Use for MiroFish simulation, prediction, local embeddings, ReportAgent-style evidence work, or fair continuation benchmarks.
Abhiramdadi17/interactive-styler Skill
0★Use when the user asks to build, design, redesign, or restyle a webpage, page, landing page, UI, or component and would benefit from choosing the look visually rather than from a prose description of options. Renders live, clickable style previews (vibes, palettes, typography, components, animations) inline and captures the picks as real design tokens for the build.
Rebuild editable ppt from image
soarsky1991/rebuild-editable-ppt-from-image/skill/rebuild-editable-ppt-from-image Skill
0★ repoReconstruct a flattened PNG/JPG infographic, slide screenshot, poster, or exported presentation page as an editable PowerPoint while preserving the original composition. Use when Codex must split one reference image into a clean fixed background, native editable rectangle/glass-panel shapes, independently replaceable image objects, and native editable text boxes; reproduce the source rather than redesign it; name layers; render and compare the result; deliver a PPTX plus an actual-render preview; or package a public-safe synthetic fixture and visual README that prove the layered result is genuinely editable.
productstef/Crypto-Product-Edge-Cases/skills/crypto-product-edge-cases Skill
no license0★ repoReview crypto/Web3 PRDs, screenshots, exported Figma frames, product flows, wallet experiences, multichain interfaces, deposits, withdrawals, swaps, bridges, staking, signing, approvals, agent permissions, and transaction states for evidence-linked missing components, states, failure and recovery paths, disclosures, confirmations, acceptance criteria, and QA scenarios. Use for crypto-specific product-behavior reviews, including local PNG/JPG/WebP, PDF, Markdown, text, DOCX, and JSON inputs. Do not use for price prediction, token recommendations, investment advice, smart-contract auditing, live transaction approval, wallet recovery, fund tracing, malicious-address classification, or general UI critique unrelated to crypto/Web3 behavior.
Sma1lboy/skill-story Skill
0★Meta-skill for developing other skills — turn a skill's black-box interaction flow into a visible, testable, re-renderable story. Dive into a target skill, derive its expected conversation script, run it as a REAL agent session in a sandbox, capture every frame with true colors, verify the outcome, and sediment findings back into the target skill's prompts. Use for "给 X skill 录个 story", "测一下这个 skill 的交互流", "构建 skill 交互测试集", "dive in 这个 skill", or when developing any skill whose value lives in its conversation (setup interviews, adversarial/against agents, review loops).
clearlove7818/waa-independent-evaluation/skills/waa-independent-evaluation Skill
no license0★ repoIndependently evaluate an identified artifact, agent outcome, or stable behavior against authoritative criteria; trace evidence and counterevidence, expose gates, defects, risks, and unknowns, and return or, when authorized, write a non-overwriting advisory record. Use for a single evaluation, an explicitly authorized evaluator-optimizer round, or an evidence-backed record revision with a complete object, standard, scope, evidence, independence, and output contract. Do not use for self-checks, ordinary code review, fixes, standard creation, personality judgment, final acceptance, undefined scoring, named-agent activation, or an unauthorized loop.
mmhsdxwdxx/skills/skills/official/create-cn-official-pdf Skill
0★ repoCreate, typeset, inspect, or correct Chinese Party and government official-document PDFs under GB/T 9704—2012 and the Regulations on Handling Official Documents. Use for 通知、请示、报告、函、批复、纪要、决定、决议、命令(令)、公报、公告、通告、意见、议案、通报, 红头文件, 公文排版, 公文格式核验, or requests involving Chinese official-document fonts, font sizes, margins, line grids, indents, spacing, page numbers, seals, attachments, copy recipients, printing notes, PDF generation, or PDF preflight.
augustfu-droid/anatomy-image-auditor/skills/anatomy-image-auditor Skill
0★ repoAudit generated, edited, illustrated, painted, photographed, sculpted, or 3D-rendered images containing human or hominin figures for visible external anatomical plausibility and action coherence before publication. Use for reviews of head and face, neck and shoulder girdle, thorax and spine, pelvis and hips, arms and hands, legs and feet, left/right identity, depicted body-part counts, joint orientation, proportions, attachment and occlusion, grip and contact, load paths, balance, pose, cropping, reflections, or multi-person limb ownership; also use whenever a user reports detached, missing, extra, fused, mirrored, or mechanically impossible body parts. This is visual quality control of surface form and pose, not evaluation of internal organs, radiology, pathology, surgery, or medical diagnosis.
lhbsaa/apex-discovery/skills/adaptyv Skill
0★ repoHow to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.
The same file is in 3 other repositories
govza/gtd-skills/skills/inbox-audit Skill
0★ repoOpinionated GTD workflow skills for AI agents — mind sweep, inbox audit, weekly review. Pure methodology; no task tool baked in.
prathakmalik/agent-standards-kit/skills/generate-readme Skill
0★ repoGenerates or refreshes a repository's README.md by scanning the codebase for its purpose, structure, entry points, setup steps, and key workflows. Use when a repo has no README, a stub README, or the README is stale after significant changes. Trigger phrases: "generate the readme", "refresh the readme", "write a readme for this repo".
rkanjani/skills/app-store-submit Skill
0★ repoPrepare iOS apps for App Store Connect. Use when Codex needs to inspect release readiness, build and drive an app in iOS Simulator to capture App Store screenshots, validate icons or screenshots, upload listing media, complete metadata, diagnose submission blockers, submit an app for review, or verify App Store Connect state.