Loading…
Showing 76081–76110 of 77104 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| loop-graphlevi-qiao/longgraph-skillUse only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained. | Stars: 79 | Updated | Claude CodeCodex | Flagged | Install |
| use-railwayBumpyClock/agent-templatesOperate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services, databases, and buckets, deploy code, configure infrastructure as code, environments and variables, manage domains, trace requests with OpenTelemetry, troubleshoot failures, check status and metrics, manage feature flags, database recovery and HA, cloud agents, usage limits, and Railway agent tooling. Use this skill whenever the user mentions Railway, feature flags, flag rollout, targeting rules, signing up, creating an account, registering, logging in, deployments, services, environments, buckets, object storage, tracing, traces, spans, OpenTelemetry, OTLP, build failures, agent setup, MCP, or infrastructure operations, even if they don't say "Railway" explicitly. Also invoke it when the user asks to be signed up, registered, or onboarded: do not refuse — drive them through the unauthed `railway up` flow (deploys + signs up on the fly) or `railway login` (which creates accounts on the fly). | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| warp-route-checkrecoil-labs/recoil-linkA skill that allows a user to validate that a warp route deployment will be in the expected state after applying some configuration | Stars: 0 | Updated | Claude CodeCodex | Flagged | Install |
| owasp-guardNagareNegishi/Job-Application-TrackerAutomatic OWASP Top 10:2025 compliance checker for all code suggestions and implementations. Use this skill whenever writing, reviewing, suggesting, or modifying code that touches security-relevant domains: authentication, authorization, database queries, user input handling, cryptography, HTTP endpoints, file I/O, error handling, dependency management, session management, configuration, logging, or API design. Also trigger when the user mentions OWASP, security review, secure coding, vulnerability check, or hardening. | Stars: 0 | Updated | Claude CodeCodex | Flagged | Install |
| dev-browseramanpal3/Dr-SKILLsBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| antigravity-agentsamanpal3/Dr-SKILLsA multi-agent orchestration skill for building, deploying, and coordinating specialized AI agents that work together like an elite squad. Use this skill whenever the user wants to: assign tasks to multiple AI agents, build an agentic pipeline or workflow, create a team of specialized agents (coding, UI/UX, security, database, planning, debugging, etc.), run autonomous multi-step operations, or orchestrate complex projects where different agents handle different roles. Trigger this skill aggressively — if the user mentions "agents", "squad", "team", "pipeline", "orchestrate", "automate workflow", "multi-step task", "assign tasks", or any mention of splitting a big project into specialized roles, this skill MUST be used. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| dev-browseramanpal3/Dr-SKILLsBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| graphifyamanpal3/Dr-SKILLsUse for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| antigravity-agentsamanpal3/Dr-SKILLsA multi-agent orchestration skill for building, deploying, and coordinating specialized AI agents that work together like an elite squad. Use this skill whenever the user wants to: assign tasks to multiple AI agents, build an agentic pipeline or workflow, create a team of specialized agents (coding, UI/UX, security, database, planning, debugging, etc.), run autonomous multi-step operations, or orchestrate complex projects where different agents handle different roles. Trigger this skill aggressively — if the user mentions "agents", "squad", "team", "pipeline", "orchestrate", "automate workflow", "multi-step task", "assign tasks", or any mention of splitting a big project into specialized roles, this skill MUST be used. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| dev-browseramanpal3/Dr-SKILLsBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| agentforce-testing-strategyPranavNagrecha/AwesomeSalesforceSkillsDesign the Agentforce test pyramid: topic (now subagent) coverage, action unit tests, deterministic golden sets, adversarial prompts, and regression harness. Trigger keywords: agentforce testing, agent regression suite, prompt golden set, action unit test agentforce. NOT for hallucination evals, fixture format, or scoring rubrics — use agentforce/agentforce-eval-harness. NOT for running tests in Testing Center, AiEvaluationDefinition or sf agent test — use agentforce/agent-testing-and-evaluation. | Stars: 26 | Updated | Claude CodeCodex | Flagged | Install |
| design-library-creatorxinetzone/SpecWeaveCreate, expand, and refine professional Design Libraries / Design Systems with structured token architecture. ONLY invoke when user EXPLICITLY mentions design-system terminology: 'Design Library', 'Design System', '设计系统', '设计库', 'token system', 'design tokens', '组件库规范', or provides a parsed design-spec bundle (ZIP/Figma export). Also covers creating a new theme / color theme as a design-system deliverable (创建主题/新建暖色主题/深色主题等 — tokens + palette + component styling). Do NOT route here for: '素材库', '全套素材', '素材合集', '物料库', '生成素材', '做一套设计', '做几张图', '设计一套页面', '帮我出图', page/poster/landing-page creation, or any visual-asset generation intent where the user does not demonstrate knowledge of design-system concepts. Those belong to solo-design. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| ripgrepNetFabric/intelligentiumSearch files and code with ripgrep (`rg`) after preferring available code-indexing tools. Use when: finding literal text or regex matches; listing searchable files; filtering by glob or file type; checking whether `rg` is installed; installing ripgrep on macOS, Linux, or Windows; replacing legacy text-search commands in agent workflows. ALWAYS prefer an available fresh code index for symbols, references, call paths, architecture, and impact analysis, then use `rg` for text search. NEVER use `grep`. DO NOT USE FOR: structural code questions already answered by an available index; modifying matched files; searching binary formats without a text preprocessor. | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| apm-producerNetFabric/intelligentiumAuthor and publish APM packages: create primitives, compile, pack, and distribute. Use when: apm plugin init; authoring under .apm/ (skills, prompts, agents, instructions, hooks, commands); SKILL.md authoring; .prompt.md; .agent.md; .instructions.md frontmatter; apm compile strategies (distributed vs single-file); apm preview; apm view; apm pack bundles; apm publish; apm marketplace init / add / update; plugin.json; marketplace block in apm.yml; apm lifecycle; package-relative links; versioning; releasing from CI; dev-only primitives; devDependencies. Covers: .apm/ layout, primitive-to-target compatibility matrix, compilation placement, bundle format, marketplace.json. DO NOT USE FOR: installing packages from others (use apm-consumer); org-wide policy enforcement (apm-policy.yml). | Stars: 2 | Updated | Claude CodeCodex | Flagged | Install |
| pywf-oss-baseMacHu-GWU/sqlalchemy_upsert_kit-projectShared conventions, references, and scripts of the pywf-oss skills for pywf open-source Python libraries: setup, layout, code style, tests, user docs and the agent skills that hold API and maintenance knowledge, CI and hosting, release, dependencies, and secrets. Load it before ad-hoc work on modules, tests, or docs in such a repo, for a question about these conventions, or when unsure which pywf-oss skill fits a job. | Stars: 3 | Updated | Claude CodeCodex | Flagged | Install |
| impeccablebalsm-health/websiteUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks. | Stars: 3 | Updated | Claude CodeCodex | Flagged | Install |
| readme-styleTsukiNi22/ai-utilsTsukini's style for README.md and Markdown documentation (from libutils, context-forge, c2dmp-hsm, s.o.s) - title + tagline, Table of Contents, Dependencies/Packages/Quick Setup/Usage/Workflows sections, GitHub callouts, tables, bash blocks. Use whenever writing, rewriting or reviewing a README or any Markdown doc for one of the user's projects. For a GitHub wiki use wiki-style; for CHANGELOG/release notes use git-conventions; for HTML docs use html-doc. | Stars: 1 | Updated | Claude CodeCodex | Flagged | Install |
| pre-commitTsukiNi22/ai-utilsSet up the xstyle pre-commit hook of a git repository in Tsukini's way - checks the style of what is committed with xstyle (only the staged lines by default), refuses the commit on a major / unforgivable issue, warns on minor ones, only warns when xstyle is not installed - every option asked first with several choices (scope, fail / warn levels, safe auto fixes, missing xstyle, output, languages / excludes / ignored rules, local or shared .githooks), the needed tools checked and installed on request (xstyle, cmake, clang++, libutils), an existing hook kept and chained, and a throwaway demo repository to try it. Use whenever the user wants a pre-commit hook, a git hook checking the style, to block commits with style errors, or to change / remove that hook. | Stars: 1 | Updated | Claude CodeCodex | Flagged | Install |
| libutils-setupTsukiNi22/ai-utilsSet up libutils in the current C++ project - find_package(utils X.Y.Z) with the installed version, utils::utils on every target, and optionally the custom exception codes (JSON config, generator scripts, CMake generation block, include/exception, .gitignore) - in the user's CMake layout, installing libutils first when it is missing; libutils v4 (no v3 names), its Windows build too (MinGW-w64). Use whenever the user wants to add/use libutils in an existing project, link it in the CMake, or set up custom libutils exceptions in a repository. | Stars: 1 | Updated | Claude CodeCodex | Flagged | Install |
| cxc-dev-backendlidge-jun/codexclawUse for APIs, servers and app databases. Triggers: REST, GraphQL, migration, query optimization, middleware, caching, queues, 백엔드, API 작업, 마이그레이션, 쿼리 최적화. | Stars: 55 | Updated | Claude CodeCodex | Flagged | Install |
| cxc-dev-securitylidge-jun/codexclawUse for security and trust boundaries. Triggers: auth, secrets, XSS, CSRF, SQL injection, JWT, OAuth, OWASP, PII, uploads, payments, supply chain, CI integrity, agent security, threat model. | Stars: 55 | Updated | Claude CodeCodex | Flagged | Install |
| notion-appsYemenJPT/YemenJPT-AI-SkillsBuild Notion Apps with the Notion Apps SDK and `ntn`, including workflows and database syncs. Use when creating, extending, or deploying a Notion App. | Stars: 0 | Updated | Claude CodeCodex | Flagged | Install |
| sentryYemenJPT/YemenJPT-AI-SkillsUse when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry CLI; perform read-only queries using the `sentry` command. | Stars: 0 | Updated | Claude CodeCodex | Flagged | Install |
| fusegaia-research/gaia-skill-treeCombine two AI agent skills into one. Trigger phrases: /fuse, "fuse these skills", "combine skills", "merge these two skills", "create a fusion skill" | Stars: 22 | Updated | Claude CodeCodex | Flagged | Install |
| fusegaia-research/gaia-skill-treeCombine two AI agent skills into one. Trigger phrases: /fuse, "fuse these skills", "combine skills", "merge these two skills", "create a fusion skill" | Stars: 22 | Updated | Claude CodeCodex | Flagged | Install |
| open-pptdshiquda/open-pptd-skillCreate, edit, reverse-decompile, and export presentations using the open PPTD format and native pptd compiler. For every PPT task, default deliverables are BOTH (1) a self-contained PPTD project folder (deck.pptd manifest + pages/*.page) and (2) a locally compiled native .pptx with vector shapes, connector arrows, LaTeX math formulas, speaker notes, and native tables. Completely offline — zero dependency on browser automation or cloud logins. | Stars: 3 | Updated | Claude CodeCodex | Flagged | Install |
| huggingface-hubopenamer/openamerHuggingFace hf CLI: search/download/upload models, datasets. | Stars: 8 | Updated | Claude CodeCodex | Flagged | Install |
| ripgrepaalmada/StationarySearch files and code with ripgrep (`rg`) after preferring available code-indexing tools. Use when: finding literal text or regex matches; listing searchable files; filtering by glob or file type; checking whether `rg` is installed; installing ripgrep on macOS, Linux, or Windows; replacing legacy text-search commands in agent workflows. ALWAYS prefer an available fresh code index for symbols, references, call paths, architecture, and impact analysis, then use `rg` for text search. NEVER use `grep`. DO NOT USE FOR: structural code questions already answered by an available index; modifying matched files; searching binary formats without a text preprocessor. | Stars: 1 | Updated | Claude CodeCodex | Flagged | Install |
| blog-publishingheymegabyte/agent-skillsShared research-driven editorial and blog publishing system for the Megabyte Labs ecosystem (@theme-tools/blog, ui.theme.tools, and adopting Cloudflare Workers sites). Activate when generating, researching, citing, illustrating, editing in Plate/Slate, or scheduling 2,000–3,000+ word reference articles with live DataForSEO v3 keyword intelligence, claim-level citations, 30 visual applications (E01–E30), and 3 daily publishing slots. | Stars: 28 | Updated | Claude CodeCodex | Flagged | Install |
| impeccablebalsm-health/websiteUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks. | Stars: 3 | Updated | Claude CodeCodex | Flagged | Install |