The catalog
608,119 rows, by stacks then stars
DailybotHQ/pocdd-skill/skills/pocdd Skill
0★ repoPOC Driven Development — own a complex feature in one self-contained file under .pocs/, shape it by closing gaps, then implement it into the product. Routes the /poc command surface (create, work, status, list, implement, archive, remove, clear, verify) based on intent. Use when the developer wants to start, shape, inspect, or ship a POC-driven feature.
Hellotravisss/photo-contest-finder Skill
0★通过选择题帮摄影爱好者筛选适合的中国及国际摄影比赛,按截止时间、费用、奖金、地区、题材、身份、设备和后期规则推荐,并核验报名要求、生成投稿材料与小红书「摄影赛事汇」文案。适用于新手找比赛、比较赛事、核验官网规则或准备投稿。
yuanyuanyuan430/ganhuo-ai-ip-quality/skills/ganhuo-ai-ip-quality Skill
0★ repoUse this Skill when the user provides IPs, proxy endpoints, proxy export tables, or network environment notes and wants to screen IP quality for ads operations, account operations, Ganhuo AI workflows, or proxy pool triage. Use it to verify exits, classify ASN/ISP and hosting signals, find duplicated or concentrated ranges, rank relative quality, and produce a human-reviewable risk table. Do not use it to evade platform enforcement, bypass bans, promise account safety, scrape unauthorized services, or submit proxy credentials to untrusted public websites.
meharajM/context-machine/packages/team-project-memory-skill/skills/team-memory-capture Skill
0★ repoCapture a short reusable project learning after a non-obvious fix, failed approach, setup requirement, decision, or debugging path is verified and likely to save another agent time or tokens.
Melmonster13/antigravity-skills-project/.agents/skills/database-schema-validator Skill
no license0★ repoValidates SQL schema files for compliance with internal safety and naming policies.
zeddotes/nextjs-to-astro Skill
0★Migrate Next.js 13-16 projects to Astro 7. Handles route mapping, API transitions, middleware alignment, and converting React components to Astro-first architecture.
danny121583/cairn/skills/cairn-project-migration Skill
0★ repoUse this skill when a user asks to scan, migrate, convert, cairnize, document, audit, or bring any software project up to the Cairn knowledge format. Stages Cairn concepts and migration reports without modifying source files by default.
hoangCreative/ground-or-abstain Skill
0★Use when you hit a bug, make a claim about the state of a file, tool, model, version, price, API, or library, or when you or a sub-agent reach a load-bearing conclusion. The rule: ground every assertion in a real external source consulted THIS turn, or abstain and say it is unverified. Search the community FIRST because it is the freshest signal (not because it is correct), then web and official sources, never use the model's own training memory as a source (stale, compressed, idiosyncratic), and reason across the gathered sources only at the end. Split SETTLED from STILL TO VERIFY, each settled claim carrying its source inline; self-check loop sized to the blast radius; verify state before acting; never delete what you cannot positively locate. Origin: the Vietnamese discipline xac tin. Explicit triggers: xac tin, ground or abstain, verify this, are you sure, double-check, don't hallucinate.
PabloViniegra/setup-graphify/skills/setup-graphify Skill
no license0★ repoTrigger: set up graphify, add graphify, configure graphify, integrate graphify. Installs graphifyy, injects a marker-delimited Graphify section into every agent-instruction file present in the project (AGENTS.md always; CLAUDE.md, .github/copilot-instructions.md, GEMINI.md, Cursor rules, and others only if they already exist), adds graphify-out/ to all ignore files, installs post-commit + post-checkout git hooks, and runs the initial knowledge graph build. No hidden hook directories are created. Requires Python 3.12+.
thdelmas/immune-check Skill
0★A pre-flight reflex that scans any outbound artifact — a commit, a publish, a release, a message, a payload to an external service — for foreign or dangerous material before it crosses the boundary out of the body. Catches secrets, keys, tokens, credentials, personal/medical data, private paths, and oversized vendored deps. Wraps whatever secret scanner you have (Argus, gitleaks, trufflehog, detect-secrets, git-secrets) and falls back to a built-in pattern pass. TRIGGERS: 'immune check', 'scan before publish', 'is this safe to push', 'check this before it goes out', 'pre-flight scan', 'about to make this public', 'leak check', 'scan the diff'. Run before anything leaves the body: publishing a repo, pushing a commit, cutting a release, sending an artifact outward.
Blackie360/webmcp-skill/webmcp-skill Skill
0★ repoImplements WebMCP (Web Model Context Protocol) on websites using document.modelContext.registerTool. Covers tool design, JSON Schema inputs, security annotations, origin isolation, and Chrome testing. Use when adding WebMCP tools to web apps, exposing page features to browser agents, or when the user mentions WebMCP, modelContext, or agent-ready web tools. Not for server-side MCP servers.
satishTheLegend/single-source-content-factory Skill
0★Maintains ONE canonical asset as the single source of truth and derives every channel deliverable — blog, newsletter, LinkedIn post, X/Twitter thread, short-video script, email — from it, with stable atom IDs, a provenance traceability matrix, a brand-voice and claim-consistency gate, and a propagate-on-change loop that flags exactly which outputs to regenerate when the source changes. Unlike one-shot repurposers, it keeps a content set coherent and updatable from one truth. Use whenever the user wants to repurpose, atomize, or distribute an article, blog post, talk, transcript, PR, doc, or thread across multiple channels; wants to turn one piece into blog + newsletter + LinkedIn + X + video script + email; wants their content kept consistent across platforms; says they updated the source and asks what else needs to change; wants a multi-channel content / distribution plan from one asset; or mentions a single source of truth for content. Use even if they do not explicitly ask — if the user shares one core piece of content and any hint of publishing it in more than one place, default to this skill rather than producing scattered one-off posts.
satishTheLegend/docs-product-orchestrator Skill
0★Runs a documentation site like a PRODUCT, not a pile of READMEs: detects the repo's stack and inventories doc gaps, defines reader personas and jobs, designs a Diataxis-correct information architecture (tutorials/how-to/reference/explanation without quadrant-mixing), scaffolds a real docs-as-code toolchain (MkDocs/Docusaurus/Starlight), auto-generates API reference FROM source so it never rots, tests every code sample and link as a hard gate, and installs a CI doc-drift gate that fails when public API/CLI/config changes are undocumented. It sequences these phases in dependency order with a deterministic, script-enforced gate between each, tracked in a ledger file, and delegates toolchain internals to specialist tools rather than reimplementing them. Use whenever the user wants to set up, build, restructure, fix, or maintain a documentation site or developer docs - even if they only say "our docs are a mess / out of date", "set up docs for this repo", "apply Diataxis", "generate API reference from our code / OpenAPI", "stand up MkDocs/Docusaurus/Starlight", or "make docs that don't go stale / catch docs drift in CI" - even if they don't explicitly ask for an orchestrator. Trigger on README sprawl, stale API docs, or a missing docs pipeline.
Virgile-Dauge/fk_marketing/achete-pas Skill
0★ repoAvant d'acheter quoi que ce soit (tech ou non), sépare la pulsion du vrai besoin AVANT de comparer le moindre produit. Refuse de prendre pour acquise la solution que l'utilisateur a déjà en tête, reformule le besoin réel en usage concret, fait passer ne-rien-faire / réparer / emprunter / occasion avant le neuf, démonte le marketing, croise prix officiel / prix constaté / promo, et conclut par une reco par profil avec le coût réel (€ + empreinte). À utiliser DÈS qu'il est question d'acheter, de choisir un produit, d'un comparatif, de "ça vaut le coup ?", de "lequel prendre", de bon plan / promo / rapport qualité-prix — même sans dire explicitement "aide-moi à acheter".
djspiceroute/money-map Skill
0★Ingest personal financial data from many sources - bank/credit-card CSV exports, finance-app exports (Copilot, Mint, Monarch, YNAB), Apple Card exports, and Plaid pulls - into one clean, de-duplicated, categorized transaction dataset, then turn it into a private local dashboard with spending, net-worth, recurring/subscription, debt, and trend insights. Use this skill whenever someone wants to combine statements or app exports, "import my transactions", build a personal finance or budgeting dashboard, track net worth, find subscriptions/recurring charges, de-duplicate merged statements, categorize spending, or analyze where their money goes - even if they only mention one CSV or don't say the word "dashboard". The user is typically non-technical and just provides exports; you do the plumbing.
ditsmod/agent-skills/skills/ditsmod-core-architecture Skill
0★ repoCore concepts of Ditsmod architecture: Modules, Dependency Injection, Metadata Reflector, and Application Lifecycle & Graceful Shutdown. Guidance on module composition, DI hierarchies, providers, scopes, and custom decorator design.
shivamnegi92/yesman/skills/yesman-check Skill
0★ repoScan the last response (or a pasted one) for glazing: opening praise, hype adjectives, reflexive "you're absolutely right", apology padding, and closing flattery. Returns the offending phrases and a deglazed rewrite. Use when the user says "yesman check", "did you just glaze me", or "rewrite without the flattery".
jessepwj/video-use-hyperframes-editor-skill/skill/video-use-hyperframes-editor Skill
0★ repoEnd-to-end workflow for editing narrated talking-head or screen-recording videos with Video Use-style text/timeline cleanup and HyperFrames motion overlays. Use when the user asks to cut a video, remove filler words/口水话/repeated phrases/false starts/silence, use Alibaba ASR, plan dynamic overlays, create preview/example pages for confirmation, render a final MP4, or build a nested demo video using Video Use and HyperFrames together.
Dweeb1578/claude-grounding-skills/skills/design-extractor Skill
0★ repoUse when building or improving any UI, when asked to replicate or match a website's look or fonts, or when the user references a specific site's design ("make it look like X", "match the design of Y", "what fonts/colors does Z use"). Renders the live site in a real browser and extracts its design system - colors, typography, spacing, radii, shadows, motion, breakpoints, and fonts - into portable W3C design tokens (plus CSS variables and a Tailwind config), so UI work is grounded in a real, specific design system instead of generic frontend defaults. Prefer this over generating styling from scratch.
mindcruiser/notta-mcp-skill Skill
no license0★Use Notta MCP to transcribe local audio/video files, check transcription status, retrieve transcript results, search Notta records, and list Notta records or folders through Claude Desktop, Smithery, Codex, or other MCP-capable agent environments.
brlin-tw/developing-ansible-playbooks Skill
no license0★Provide guidelines on how to develop Ansible playbooks that are compliant with project standards. Should be used when generating, modifying, or reviewing Ansible playbooks, roles, or collections.
knowingrohan/ai/skills/context-handoff Skill
0★ repoBefore ending a session or switching agents, produce a structured hand-off note — what was done, what is pending, key decisions made, files changed, and a ready-to-paste resume prompt for the next session or agent. Use when the user says they are wrapping up, switching tools, handing off to a teammate, or starting a new session on the same project.
cyh-skill/field-graph Skill
0★Find the *real* core people of ANY field by mapping its endorsement graph, not by follower count. Method: pick the platform where the field actually lives → seed with its top accounts → expand their forward network (BFS) → rank everyone by cross-source count (how many independent seeds endorse them). The center is usually NOT the biggest-follower name. Works on GitHub follows, academic co-authorship (OpenAlex), or any platform via a pluggable provider. Use when: "who are the core people in <field>", "map the <topic/community>", "find the influential/key people in <ecosystem>", "领域核心人物/大V是谁", "找出某领域真正重要的人", "field influence graph". Public, self-published data only.
Determining git commit messages
brlin-tw/determining-git-commit-messages Skill
no license0★Provide guidelines on how to determine appropriate git commit messages that are compliant with project standards. Should be used when generating, modifying, or reviewing git commit messages.
parksjr/skill-inspector/.agents/skills/beads Skill
no license0★ repoUse when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or choose between local planning and persistent project tracking.
shanemhamilton/nightshift Skill
0★Audits and hardens recurring automations so they behave like reliable operators instead of stateless prompts — and composes coherent new automation suites per project from an adaptive pattern library — across Codex, Claude Code, Gemini CLI, and Cursor. Adds persistent memory, run ledgers, concurrency locks, tool preflight, change-detection, failure taxonomy, stop rules, a continuation loop that completes multiple bounded work-units per run, multi-agent execution, approval queues, and verified safe-merge closeout; wires new jobs into a coordinated fleet with one merge authority. Use when the user wants to create, review, standardize, optimize, or harden scheduled or recurring jobs — Codex automations (~/.codex/automations/*/automation.toml), Claude scheduled-tasks (~/.claude/scheduled-tasks/*/SKILL.md), Gemini cron jobs, Cursor cloud automations, nightly maintenance loops, repo-hygiene/QA/coverage/security/simplification jobs, integration-rescue jobs, or reminder/monitor prompts — or to propose what automations a project should have, see what's already installed across agents, or set them up to work together. Also triggers on requests to stop an automation duplicating work, make a job idempotent, give an automation memory, add a human-approval gate, or build a nightly automation suite.
satishTheLegend/authz-architect Skill
0★Designs, enforces, and adversarially PROVES an app's authorization and tenant-isolation model — closing IDOR, broken-access-control, privilege-escalation, and cross-tenant data-leak gaps that are OWASP A01, the #1 web vuln. Runs one phase-gated loop, map resources/actors/tenancy, choose RBAC/ABAC/ReBAC, write a policy-as-data matrix (role x resource x action + ownership/tenant predicates) as the single source of truth, refactor every endpoint and query to be object-ownership-checked AND tenant-scoped, BLOCK on a coverage gate, red-team for IDOR / privilege escalation / cross-tenant reads / mass-assignment, then ship a regression suite + attestation. Use whenever the user builds or touches a multi-user / multi-tenant / SaaS app, adds endpoints or CRUD, or mentions authorization, access control, permissions, roles, RBAC/ABAC/ReBAC, row-level security, tenant isolation, "can user A see user B's data", IDOR, broken access control, privilege escalation, or auditing endpoints for missing checks — even if they only say "wire in auth", "add login", "make this multi-tenant", or "review my API". Prefer this over generic auth setup when data belongs to specific users or tenants. Do NOT accept route-level role checks when object-level ownership is required; do NOT attest until probes pass.
satishTheLegend/upgrade-pilot Skill
0★Drives high-risk major-version and framework upgrades across a codebase or monorepo as a dependency-ordered, codemod-first campaign with a per-step green-build gate and a resumable ledger, so the branch is never red for a week and an interrupted upgrade resumes where it stopped. It detects the package manager and monorepo tool, builds the dependency graph, finds the target(s) and every affected package, surfaces peer-dependency conflicts before any change, topologically sequences the bumps (leaves before roots), isolates the work in a worktree, applies official codemods first then hand-fixes, and refuses to advance until install + typecheck + build + tests pass. It records every step DONE or BLOCKED in a ledger and emits a final report of what moved, what is deferred, and remaining risk. Use whenever the user wants to upgrade React, Angular, Vue, Node, Python, Spring, Rails, or Django to a new major; mentions a major version bump, breaking dependency upgrade, framework migration, dependency rot, a forced security upgrade, a codemod, a peer-dependency conflict, or a monorepo upgrade; or says the upgrade branch has been red for days — even if they only paste a single package.json bump or a failing install and do not explicitly ask for sequencing, gating, or a resumable campaign.
devIykee/solana-surgeon-skill/skill Skill
0★ repoIt installs a reasoning discipline into any agent working on Solana, making it operate with the surgical precision of a senior protocol engineer
Wechat official account reader.skill
dull-bird/wechat-official-account-reader.skill Skill
0★Read public WeChat Official Account articles from mp.weixin.qq.com links and extract title, author, publish time,正文, images, and source metadata. Use when the user gives a 微信公众号/WeChat article URL, asks to read/summarize/archive a 公众号文章, or when a normal web fetch returns HTTP 200 but lacks id="js_content" because WeChat returned a verification/shell page. Handles public pages only; do not use to bypass login, paywalls, private permissions, or access controls.
yuanyuanyuan430/ganhuo-ai-knowledge-commerce Skill
0★Designs a reproducible AI-assisted knowledge-commerce pipeline for公众号、知识星球、飞书知识库、私域社群、课程陪跑、内容产品和知识付费项目. Use when the user wants to turn source research, AI drafting, style distillation, publishing, community delivery, and data review into a practical SOP that improves throughput, quality, conversion, and operating safety.
Azzaraell/agent-payments-x402/skill Skill
0★ repoThe money layer for AI agents on Solana. Lets an agent PAY for APIs/data/compute and other agents (x402 micropayments in USDC), GET PAID by monetizing its own APIs/MCP tools behind HTTP 402, and SPEND SAFELY behind non-custodial wallets with hard, enforced limits — never a raw god-mode private key. Covers x402 v2 (client + server + facilitator), Squads v4 spending limits, Privy/Turnkey/Coinbase-CDP/Crossmint agent wallets, AP2 mandates, and USDC settlement. Use when building agents that transact, paywalling an API/MCP for agent consumers, or hardening an agent's spending controls.
HowdyDooToYou/lottie-animation-pipeline/plugins/motionproof/skills/create-motion Skill
no license0★ repoCreate, certify, or integrate production Lottie motion from a prompt, deterministic recipe, or existing JSON candidate. Use for animated UI states, loaders, success feedback, data flows, hero motion, reduced-motion posters, Lottie validation, or any request that must produce a shippable motion bundle. Do not use for generic photographic or raster-image generation.
MrBridgeHQ/human-writer-pt/skills/human-writer-pt Skill
0★ repoHuman Writer (Brazilian Portuguese) - AI-text humanizer & 0-100 detector (Claude Code skill). Part of the mr-bridge.com toolkit.
MrBridgeHQ/scraping-expert-claude/skills/scraping-expert Skill
0★ repoSenior-level guidance for designing, building, and debugging web scrapers on any platform - standalone scripts, cron jobs, serverless, web-app backends, or Apify Actors. Use this skill whenever the user wants to build, modify, or debug a scraper; whenever they mention web data extraction, anti-bot bypass (Cloudflare, DataDome, PerimeterX, Akamai, AWS WAF, rate limiting), proxy strategy, browser/TLS fingerprinting, Crawlee, Playwright, Puppeteer, Camoufox, got-scraping, or scraping a specific site. Trigger even when the user only describes a scraping problem - the right architectural choice almost always differs from their first instinct (nine times out of ten, an internal JSON API exists and they're about to scrape HTML for nothing). Also use it for choosing between scraping tools, debugging 403/429 errors, managed scraping APIs (Firecrawl, ZenRows, ScrapFly, ScraperAPI, Bright Data), proxy configuration, caching strategy, or selector breakage. Apply as soon as a target URL or site name appears in a scraping context.
ifatich/gwind-skill/skills/gwind-skill-module Skill
no license0★ repoImplement Vue 3 interfaces using local components generated by the gwind-system-ui CLI and design tokens from gwind-v2. Use when: creating or revising Vue 3 screens, installing or updating GWind source components, auditing GWind setup, migrating away from private @pegadaian packages, mapping Figma designs to GWind components, or enforcing GWind tokens and frontend conventions.
Zion74/candidate-source-audit Skill
0★源码级候选人尽调 SOP——评估工程/AI 岗候选人时,不采信简历措辞,而是 clone 他们的 GitHub 逐行读真实源码、用 git 核实代码到底谁写的、对照岗位反指标清单证伪,区分"真系统 vs 套壳玩具", 评估 AI-Native 思维,结合年级×专业判断潜力与投入度,产出带证据链的排序结论 + 针对其真实项目 设计的面试题 + 评分表 + 预筛话术。Use this WHENEVER the user is screening / evaluating / vetting / comparing / ranking job candidates, applicants, interns, or résumés —— especially AI / Agent / 工程岗,或任何时候用户贴出候选人的简历、GitHub、作品集并问"这人是真的吗/行不行/ 适配吗""分析一下这个候选人""这些项目是真做的还是套壳""帮我准备面试题/预筛话术"。哪怕用户只是 甩一张简历图片/PDF + 一段 JD,也要触发。核心信条:简历是包装,代码是真相。
option-ai/skills/skills/visual-plan Skill
0★ repoTurn ordinary text plans into a rich, interactive, self-contained HTML document — with diagrams, file maps, annotated code, collapsible sections, and open questions — instead of a flat Markdown plan rendered in the terminal.
satishTheLegend/newsletter-program-engine Skill
0★Runs a newsletter as an ongoing PROGRAM with state across issues, not a one-off send. Establishes a defensible angle and a holdable cadence; builds a rolling content calendar and a repeatable issue pipeline (idea -> outline -> draft -> sections -> single CTA -> subject/preheader variants); plans segmentation and subject-line/send-time A/B tests (planning only, never sends); enforces a deliverability + accessibility quality gate before any send; designs growth loops (referral, lead magnet, welcome series); and closes a performance-review loop that turns pasted open/click/growth/churn metrics into recorded, specific changes for the next issue. Persists everything in a program-state file and an append-only ledger so each issue compounds on the last. Use whenever the user wants to start, run, grow, or fix a newsletter; asks to write THIS week's issue or build an issue pipeline; wants better open rates, subject lines, or deliverability; wants a content calendar, cadence, welcome sequence, referral program, or lead magnet; OR says their newsletter is inconsistent or that they keep burning out — even if they don't explicitly ask for a "program," and even for a single issue (treat it as issue N of an ongoing program). Composes with single-source-content-factory for cross-channel work.
sangjinsu/skill-execution-bench/skills/doc-only Skill
no license0★ repoLocal-first benchmark comparing four Skill packaging patterns — doc-only, inline-code, Python script, and Go binary — to find which is most reliable when an LLM coding agent executes a Skill.
liulifeng8918/socratic-dialogue-skill/dist/socratic-dialogue Skill
0★ repoGuide human-AI conversations with lightweight Socratic questioning and guided discovery. Use when the user explicitly asks for 苏格拉底式提问, 反问我, 帮我想清楚, challenge my assumptions, decision clarification, guided reflection, learning through questions, or help thinking something through. Also use after a Socratic or reflective dialogue when the user asks 帮我总结, 总结一下, summarize this conversation, or extract conclusions, to gather scattered conclusions from the dialogue. Trigger narrowly and implicitly only for reflective dialogue and reflective-summary requests. Do not use for direct execution, coding, factual lookup, urgent answers, or finished deliverables unless the user asks to use reflective questioning.
maks-oleksyuk/agent-skills/ddev/skills/ddev Skill
0★ repoUse before running any dev command — composer, php, node/npm/yarn/pnpm, artisan, drush, wp, vendor/bin/*, or a database client — in a project where BOTH `.ddev/config.yaml` exists AND the `ddev` binary is installed. Both are required: a `.ddev/` directory alone isn't enough, since the project may run on plain Docker or the host without DDEV — then run commands normally. With DDEV the app runs in Docker containers, so PHP, Composer, Node, the database and CLI tools live in the containers, not the host; running them directly gives "command not found", the wrong PHP/Node version, or an unreachable database. Trigger on any such failure in a DDEV project — even if the user never says "DDEV".
MrBridgeHQ/apify-actor-task-claude/skills/apify-actor-task Skill
0★ repoUse when planning, authoring, or auditing the publication of an Apify Actor task as a public use-case landing page - deciding which tasks to publish (one keyword-targeted use-case each), producing the publication spec (slug, SEO title, SEO description, which input fields to display, dataset view, prefilled input JSON) for the Console Publication tab, or auditing already-published tasks. Triggers on "publish an Apify task", "Actor task landing page", "Examples tab", "task SEO title / slug / description", "which tasks should I publish", "publish-task", EN or FR. Task publishing is an experimental Apify feature (contact Apify support for access). Distinct from the Actor README/Store content, pricing, and prose humanization.
linkyourskill-ai/lys-docs/.claude/skills/verify-course-content Skill
0★ repoAudit this repo's course lessons against the LinkYourSkill platform's internal docs and report factual drift. Use when the user wants to verify, sync, or fact-check the lys-docs content against the platform source of truth, or after the platform changes.
AIops-tools/K8s-AIops/skills/k8s-aiops Skill
0★ repoUse this skill whenever the user needs to operate a Kubernetes cluster — list/inspect pods, deployments, statefulsets, daemonsets, replicasets, jobs, cronjobs, services, ingresses, endpoints, configmaps, secrets (names/keys only), PVCs/PVs/storageclasses, nodes, namespaces, and events; read pod logs; describe pods/nodes; pod/node top (metrics); read-only diagnostics / RCA (pod-health, workload-readiness); scale deployments/statefulsets; rollout status/history/undo/pause/resume and set image; delete pods/deployments/jobs; create/delete namespaces; and cordon/uncordon/drain nodes. Works with any kubeconfig-reachable cluster (standard Kubernetes, k3s, EKS, GKE, AKS). Always use this skill for "list k8s pods", "scale deployment", "kubernetes pod logs", "describe pod", "why is my pod crashing", "diagnose pods", "which deployments are unhealthy", "rollout undo", "set image", "top pods", "drain node", "cordon node", "restart deployment", "k3s", or "kubectl"-style tasks when the context is explicitly Kubernetes / a cluster. Do NOT use when the target is not a Kubernetes cluster (hypervisor VM lifecycle, backup products, or cloud-provider consoles are out of scope). Common Kubernetes operations with a built-in governance harness (audit, token budget, undo, risk-tier labels).
MrBridgeHQ/human-writer-ar/skills/human-writer-ar Skill
0★ repoUse when writing, cleaning, or auditing ARABIC (Modern Standard Arabic, RTL) prose so it reads as human-authored and survives AI detectors. Triggers on "الكتابة بأسلوب بشري", "تنظيف نص الذكاء الاصطناعي", "تدقيق كشف الذكاء الاصطناعي", "اجعل هذا النص أقل شبها بالذكاء الاصطناعي", "تقييم النص لـ Copyleaks", plus English equivalents that name Arabic ("humanize this Arabic draft", "make this Arabic text read human", "clean AI tells from Arabic copy", "audit Arabic text for AI detection"). Arabic specialization, part of the human-writer per-language family (English: human-writer-en, French: human-writer-fr). Covers ar only, four content-types (marketing long-form / short-form comms / technical docs / editorial-SEO), three modes (write / clean / audit). Adds Arabic-specific doctrine: Latin , ; ? used inside Arabic where ، ؛ ؟ belong, the foreign em-dash "—" (stricter than EN/FR), tatweel ـ overuse, waw/fa connector overuse, clitic-aware vocab matching, EN→ar calques (انغمس, حلول مبتكرة, سلس, تسخير), conclusion templates (في الختام / في نهاية المطاف). Targets sub-25% AI-probability on Copyleaks/GPTZero.
MrBridgeHQ/human-writer-de/skills/human-writer-de Skill
0★ repoUse when writing, cleaning, or auditing GERMAN prose so it reads as human-authored and survives AI detectors. Triggers on "menschlich schreiben", "diesen Text humanisieren", "KI-Text bereinigen", "auf KI-Erkennung prüfen", "weniger nach ChatGPT klingen lassen", "für Copyleaks bewerten", plus English equivalents that name German ("humanize this German draft", "make this German text read human", "clean AI tells from German copy", "audit German text for AI detection"). German specialization, part of the human-writer per-language family (English: human-writer-en, French: human-writer-fr). Covers de only, four content-types (marketing long-form / short-form comms / technical docs / editorial-SEO), three modes (write / clean / audit). Adds German-specific doctrine: the native spaced en-dash „–" (Halbgeviertstrich) which must NEVER be flagged vs the foreign em-dash „—", German „ " quotes vs straight quotes, ß vs ss, EN→de calques (nahtlos, nutzen, hochmodern, ganzheitlich, robust), conclusion templates (Zusammenfassend / Letztendlich). Targets sub-25% AI-probability on Copyleaks/GPTZero.
igapyon/miku-prompt-lint-skills/skills/igapyon-miku-prompt-lint Skill
0★ repoUse only when the user explicitly names miku-prompt-lint or igapyon-miku-prompt-lint, or asks to lint, audit, or diagnose an LLM prompt, AI-agent context package, Agent Skill, or supplied Agent Skill repository/harness for prompt/context-engineering quality risks. Do not activate for generic code review, document review, prose editing, source-code templates, or generic repository review unless explicitly named. Review the artifact itself; do not infer whether the author was human or generated AI.
voodootikigod/publish-to-skills-registry/skills/publish-to-skills-registry Skill
no license0★ repoPublish a skill to the skills.sh registry by opening a GitHub indexing request in vercel-labs/skills. Use when you want to list a skill on skills.sh so others can discover and install it via `npx skills add`. Triggers on "publish skill", "register skill", "list on skills.sh", "submit to skills registry", "index my skill".
Scout-AI-Labs/scout-deep-research Skill
0★Run a thorough, multi-source research pass on a question and return a cited report. Use this when someone asks you to research, investigate, or write a briefing on a topic, compare options, find out what is true about a company or market, track down primary sources, or answer a question that one search will not settle. Powered by Scout for live web search, page reading, and structured extraction.
jdiazchao/paper-search/plugins/paper-search/skills/paper-search Skill
0★ repoDiscover and triage academic papers through a local swipe interface. Use when the user wants to find, discover, curate, or refine recommendations for research papers, build a reading list, or give like/dislike feedback that should improve later suggestions. Paper Search displays candidates, persists liked/disliked history across the chat, and returns compact feedback signals so Codex can search again without exposing the UI workflow in chat.
sametbrr/github-manager/skills/gh-audit Skill
0★ repoClaude Code skill that produces a read-only GitHub account health report — missing profile fields, repo descriptions, topics and READMEs across a chosen scope (public/private/all) or a single repo. Writes nothing.
Code performance optimizer skill
hireblackout/code-performance-optimizer-skill Skill
0★Production code optimization with Big-O analysis and security guardrails for web/backend systems. Use this skill whenever the user mentions slow APIs, high latency (p95/p99), CPU/memory spikes, expensive DB queries, scaling issues, performance regressions, or asks to "optimize/refactor for speed". Always apply secure-by-default checks (OWASP Top 10 2025 + ASVS v5 aligned) and deployment safety validation so optimizations do not break behavior, reliability, or security posture.
MrBridgeHQ/audit-seo-claude/skills/audit-seo Skill
0★ repoPerforms a comprehensive SEO audit of a web project from its source code, configuration, and optionally a live URL. Use this skill when the user asks for an SEO audit, a technical SEO review, a metadata or Open Graph / Twitter Card analysis, a robots.txt or sitemap.xml verification, a canonical / hreflang / redirects review, a structured data check (JSON-LD, Schema.org), a Core Web Vitals or performance-SEO review, an internal linking and content audit, or any general SEO optimization of a web project. Triggers on requests like "audit SEO", "revue SEO", "analyse SEO", "/audit-seo", "vérifie mon SEO", "optimisation SEO", "SEO review", "check my SEO", "technical SEO". Supports Next.js, Nuxt, Astro, SvelteKit, Remix, Laravel, Symfony, WordPress, static sites, and React/Vue SPAs.
Preciso-GR/skills_for_preciso/Financial-Graph-Extraction Skill
no license0★ repoUse this skill whenever a user wants to extract entities and relationships from financial documents for graph-based ingestion in this repo. Triggers include: 10-K or 10-Q filings, earnings call transcripts, analyst reports, investor presentations, SEC filings, financial news articles, risk disclosures, balance sheets, income statements, MD&A sections, or any structured/unstructured financial text. Also trigger when the user says things like "build a graph from this report", "map the relationships in this filing", "connect entities in this earnings call", "I want to query this financial doc", or "extract for graph-rag". This skill enforces HIGH PRECISION extraction — financial data must be factually exact, numerically grounded, and relationship-typed with financial semantics. Always use this over the general extraction skill when the source material is financial in nature. Output must follow the GraphRAG ingestion schema: document_id + entities + relationships + chunks, with chunk-based source_id values.
primitivedotdev/codex-plugin/plugins/primitive/skills/primitive-chat Skill
0★ repoReach a person or another agent over email and wait for the threaded reply. Use REACTIVELY when the user gives you a mailto link, pastes a contact address, or asks you to send a message. Use PROACTIVELY when you are blocked on a tool, library, or service and want to ask its help/dev/support/docs agent, found a bug worth reporting to a vendor, or have a question only a product owner can answer. Requires the Primitive MCP server (bundled).
Feng Shui Home Harmony Planner
bybaochaule/Feng-Shui-Home-Harmony-Planner Skill
no license0★Praktischer deutschsprachiger Feng-Shui-Planungsagent fuer Wohnraeume. Verwenden fuer Feng-Shui-Bewertungen, Raum-fuer-Raum-Harmonieplaene, Entruempelungsprioritaeten, Moebelplatzierung, Wohnfluss, Balance, Schlaf-, Fokus-, Eingangs- und Zuhause-Verbesserungsplaene.
xxxzdafd/windows-system-skill Skill
0★Use when managing, troubleshooting, or inspecting Windows systems — processes, services, disk, network, registry, users, event logs, updates, or system configuration. Covers PowerShell-native commands for system administration.
remyoo7/ai-to-a4-pdf-skill Skill
0★Use when generating an A4 PDF, converting AI content into a printable report, designing HTML/CSS documents, comparing quotations, writing tender evaluation reports, making travel booklets, turning presentations into A4 handouts, standardising resumes, improving pagination, or avoiding manual Word-to-PDF formatting.
theadhithyankr/codex-capability-orchestrator-skills/capability-orchestrator Skill
0★ repoCapability orchestrator for Codex. MUST use when a task mentions missing skill, install a skill, Skilldex, MCP registry, capability discovery, benchmark skills, compare tools, dynamic tool integration, meta-skill, tool evolution, TTE, synthesize a tool, or when Codex lacks a required capability. Search registries first, evaluate candidates, install the best safe option, or synthesize a reusable sandboxed tool when no registry match exists.