Engineering
98,648 rows, by stacks then stars
arcjet/skills/.agents/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
kaposty/saop/skills/saop Skill
1★ repoPlan a non-trivial task with the SAOP method before starting the work: Sketch, Analyze, Optimize, Partition. It first locks the goal with you, grounds itself in the real context, then returns a decomposed plan pyramid whose endpoints are each checkable, ready for approval, and never implements a planned task until you approve. Domain-agnostic: a new project or subproject, a feature, a migration, a security hardening, a compliance review, a backend. Invoke it explicitly with /saop; it does not fire on its own. Skips routine or well-understood tasks where a full four-phase pass would be overkill.
markus-smile/ios-app-agentic-engineering/skills/ios-app-agentic-engineering Skill
1★ repoEnd-to-end agentic engineering for iPhone apps, from idea to a secure App Store release through 8 gated phases. Use when someone wants to build, plan, or ship an iPhone/iOS app — especially a non-programmer ("vibe coder") asking to create an app, pick a tech stack (SwiftUI, React Native, Flutter), choose a backend (CloudKit, Supabase, Firebase), publish to the App Store, or make their app secure. Also use when an iOS project shows symptoms of skipped planning - hardcoded API keys, no threat model, Firebase test mode, missing privacy manifest, or App Store rejection.
Pragmatic laravel layered architecture
yuriymarad/laravel-skills/skills/pragmatic-laravel-layered-architecture Skill
no license1★ repoUse this skill for Laravel backend tasks where implementing, changing, or reviewing functionality requires architecture decisions. This skill defines the project's custom architectural approach and should be treated as the source of truth for architecture, layer placement, and responsibility boundaries. Use it when deciding where code belongs, how to split responsibilities, how to wire a use case end-to-end, or whether something should be a Controller, Form Request, MCP Tool, Action, Core class, Value Object, Data object, Enum, Model, Event, Listener, Job, Contract, Integration, or Provider.
Resume optimerzer claude skill
DhruvkrSharma/Resume-optimerzer-claude-skill Skill
no license1★AI/ML Career Copilot. ATS analysis, resume optimization, keyword research, GitHub review, LinkedIn review, project evaluation, interview preparation, market fit analysis, and career readiness scoring.
Abhishek-Chougule/website-standards-auditor/skills/website-standards-auditor Skill
1★ repoAudit and fix any website (new, in development, or already live) against the organization's mandatory engineering and web standards, then scaffold or repair the gaps after the user approves. Use this whenever the user wants an SEO, GEO, AEO, accessibility, performance, structured data, schema, sitemap, robots.txt, llms.txt, Core Web Vitals, Lighthouse, mobile, metadata, canonical, hreflang, redirects, or internal linking review, or asks to check a repository against the .gitignore and README policy, or mentions auditing, gap analysis, compliance, standards review, or "make my site follow our rules". Always use this for any website quality, discoverability, or standards conformance task even if the user does not name the standard, and follow its two phase flow that produces gap_identification.md first, then fixes only after explicit approval.
dayvisonassis/sdd-skills/skills/architecture-analyzer Skill
1★ repoPerforms a comprehensive surface-area analysis of any codebase scope (a component, module, service, layer, or the full project). Inventories every entry point, dependency, pattern, and integration, scores complexity, and produces a structured Architecture Analysis Report consumed by the deep-analyzer skill. Analysis/reporting only — never modifies the codebase. In the SDD flow this is the first setup step for an existing (brownfield) project; it feeds deep-analyzer and then gate-builder.
jyuwaaw/dianpo-skill/skills/dianpo Skill
1★ repo点破一段技术机制背后不明显的心智模型——角色是谁、token/凭证/密钥/证书归谁所有、谁在向谁证明什么、为什么设计成这个形状。资深工程师一句话能点明的东西("这个 token 是 OpenAI 的"),这个 skill 负责替用户点明。Use this whenever the user pastes a config, endpoint, protocol description, PR/work note, or auth flow and wants to understand it — trigger on "帮我理解", "点破", "这是谁的 token/key", "谁验证谁", "为什么要这么设计", "为什么非要这样/绕一圈", "没看懂这个流程", "who owns this token", "whose cert/key is this", "who signs what", "who is verifying whom", "who trusts whom", "give me the mental model", "explain this mechanism/design", "why is it designed this way" — and also proactively whenever explaining any challenge/verification/handshake/webhook/signature/receipt/attestation/OAuth-like mechanism, or certificate/CA/mTLS/SSO/SAML trust chains, where credential ownership is easy to misread.
valorisa/Claude-Skill-Creator/skill-creator Skill
1★ repoA meta-skill for Claude Code (Anthropic CLI) that guides you through creating, testing, and iterating custom skills via structured conversation. Designed with LLM Council methodology: interview intent, generate draft, smoke-test immediately, refine until satisfied. A skill is just a markdown file — this tool embraces that simplicity.
zavora-ai/skill-mcp-registry-management Skill
no license1★Manage the MCP server registry — register servers, discover tools, configure allow-lists, monitor health, restart unhealthy servers, and export inventory. Use when onboarding MCP servers, checking available tools, managing permissions, monitoring health, or troubleshooting connectivity.
luminary19/atelier/skills/atelier-components Skill
no license1★ repoAtelier suite — turn the design system into real, accessible, production code. Scaffold a premium React/Next + Tailwind v4 + shadcn/ui project, wire the atelier-foundations tokens into shadcn's theme variables, install the best-in-class single-purpose components (Vaul drawer, Sonner toast, cmdk command palette, Tremor dashboards), set up Storybook, and assemble pages from a copy-paste premium section-block library (hero variants, bento, feature rows, pricing, nav, footer, dashboard shell, data tables, forms, empty states). Use whenever building/scaffolding a frontend project, implementing components or page sections, setting up shadcn/Tailwind, adding a drawer/toast/command-palette/charts, or assembling marketing or app UI. Default stack: React/Next + Tailwind v4 + shadcn — with a no-framework path (Basecoat / Franken UI) for vanilla HTML / Rails / Laravel / Django / Astro. Part of the Atelier suite.
iggmasterdev/badquality-lab/agile-tester/skills/bug-triage-advisor Skill
1★ repoTriage a bug using a clear decision model: is it a defect or a feature/change request? should it be logged at all, or just discussed? fix now, later, or never? and which medium — defect tracker, task card, a failing test, or nothing? Use this whenever someone is deciding what to do with a bug, asks "should I log this", "is this a bug or a feature", "fix now or later", how to handle a defect found mid-iteration vs in regression vs in production, or how to set up a lightweight bug policy / zero-bug approach. It adapts to your team's policy if you provide one, and otherwise uses sensible defaults. Trigger even when the user just describes a bug and asks "what do I do with this".
pipipip169/fable5-handoff Skill
no license1★Claude Fable 5's retirement handoff (2026-07-10): the thinking, reasoning, and operating techniques that separated Fable 5 from Opus/Sonnet, distilled by Fable 5 itself into domain-neutral files ANY model, any project, any domain can load and follow. Synthesized from 7 sources (fable5-methodology, adamentwistle/fable-skills 35-skill set, goat-fable, DizzyMii/fable-skills, cozytab/fable5-mode, the Fable 5 consumer system prompt, and self-assessment). Read when the session runs on a non-Fable model, at the start of any hard multi-step task, when a task is looping, or before any claim ships to a human. Trigger: fable, handoff, model migration, thinking moves, turn discipline, done gate, coherence, recall, taste, discipline gap.
Dolphinllc/claude-security-skills/skills/defensive/genai/anthropic-sdk-security-scan Skill
1★ repoDefensive security scan for code using the Anthropic SDK (@anthropic-ai/sdk, anthropic Python SDK). Detects prompt-injection vectors via untrusted attachments and tool results, system prompts containing secrets, prompt-cache breakpoints over user data, missing tool input validation, and unsafe execution of model output. Invoke when the user asks to "review", "audit", or "scan" code that calls messages.create, tool_use, prompt_caching, or related APIs.
zavora-ai/skill-a2a-agent-orchestration Skill
no license1★Orchestrate remote AI agents via A2A protocol — discover agent cards, dispatch tasks, stream results, cancel tasks, and manage push notifications. Use when delegating work to remote agents, checking agent capabilities, coordinating multi-agent workflows, or monitoring task progress.
PrecisionUtilityGuild/virtual-monorepo/skills/virtual-monorepo Skill
1★ repoInvoke when the user wants Claude Code to work across MULTIPLE related repos at once — mentions of a "virtual monorepo", "multi-repo workspace", "give Claude my whole system", "wire up my microservices/frontend+backend together", stale workspace symlinks, or "regenerate the workspace CLAUDE.md". Sets up a symlink-based workspace directory with a system-level CLAUDE.md written by reading each repo once. Strictly one-shot Bash (mkdir, ln -s, write file); never builds an index, database, daemon, or per-file catalog.
Hekouwang claude skill doctor skill
huiyonghkw/hekouwang-claude-skill-doctor-skill Skill
1★会勇禾口王的AI笔记 · Agent Skill(SKILL.md)体检器。检查一个 Claude/Agent Skill 是否 符合"按需加载的指令包,不是单文件巨石"的最佳实践——评 description 触发质量、SKILL.md 篇幅、渐进披露(references/ 拆分)、脚本外置、可移植性(无硬编码绝对路径)、安全(无硬编码 密钥),给出评分卡 + 按优先级的修复建议,并可代为重构。触发:用户说「检查我的 skill / SKILL.md 体检 / 这个 skill 规范吗 / claude-skill-doctor / audit skill / lint SKILL.md / 我的 skill 太长了 / skill 拆分 / 看看我的 skill 合不合规 / skill 对齐官方规范」。 任何"评估/审查/优化某个 Agent Skill 质量或结构"的请求都应触发。
sarveshtalele/reverse-engineering-skill/skill-packages/01-claude-code-skill/.claude/skills/reverse-engineer Skill
no license1★ repoYou can reverse engineer any open source project using public github repo link in Claude code or Github Copilot
cacaoapps/e2e-test-plan Skill
1★MANDATORY for any artifact that walks a tester through a real product. Invoke this skill BEFORE writing any of: E2E test plan, end-to-end test plan, user journey tests, QA test plan, manual test script, regression test plan, smoke test plan, acceptance test plan, tester runbook, manual QA runbook, release-check runbook, browser-MCP walkthrough, device verification checklist, or any "Phase X — E2E" / "Phase X — manual QA" deliverable in a project plan. Also invoke when the user asks to validate a feature manually, hand testing off to a QA person, prepare tests for a tester agent, or document how to verify a build before shipping. The skill produces ONE OR MORE realistic user journey stories — complete sessions from app open to close — NOT a feature matrix, NOT an area-grouped checklist (e.g. "5.1 Login, 5.2 Pipeline flow, 5.3 Tasks flow…"), NOT a per-screen test case grid. Each story is a real mission a real user pursues; features get exercised as a natural consequence. Output is a markdown plan with checkboxes a tester runs top to bottom without artificial state setup. If you find yourself about to write section headings like "5.X Feature Flow" or "Test Case N", STOP and invoke this skill instead — that format is the exact anti-pattern this skill exists to prevent.
Skill security vulnerability management
zavora-ai/skill-security-vulnerability-management Skill
no license1★Manage security vulnerabilities — search advisories (CVE/GHSA/OSV/RustSec), audit dependencies, score risk, generate remediation plans, and export findings. Use when checking for vulnerabilities, auditing dependencies, assessing security risk, planning patches, or generating security reports.
nimrodfisher/data-context-layer-studio/.claude/skills/context-onboarding Skill
1★ repoInterview a data team and build their domain context skill through conversation. Use when someone wants to create, populate, or onboard a new domain context skill, gather the context an AI agent needs to answer data questions correctly, or build a SKILL.md for a data domain without using the web UI. Guides a non-technical analyst step by step, gathers real evidence, writes a project.json, and exports the skill.
pol-cc/agentic-data-engineer/skills/add-dbt-model Skill
1★ repoAdd a new dbt model (staging, intermediate, or marts) to an existing MDS deployment. Invoke when the user wants to transform raw data, build an analytics table, or expose a new metric in BigQuery.
omarfarahatoglu-tur/ai-agent-skills/skills/ai-team/ai-agent-debugger Skill
1★ repoOpen-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.
pem725/ai-rosetta-stone Skill
1★Translates Claude concepts and terminology to ChatGPT, Gemini, and Microsoft Copilot (consumer, Microsoft 365, and GitHub variants) equivalents. Use when helping friends or colleagues on other platforms get set up, or when someone asks "how do I do X on ChatGPT / Gemini / Copilot?"
Pr1ncePandey/RepoMind/repo-mind Skill
1★ repoAutomatically analyze GitHub repositories and reverse engineer software architecture. Activate when a user provides a GitHub link (github.com/...), asks to analyze a repository, understand a codebase, reverse engineer a project, evaluate SaaS potential, or improve a GitHub project.
amansingh909/claude-bounty-skills/skills/recon-triage Skill
1★ repoUse when a bug bounty recon phase has produced a large list of hosts/subdomains/endpoints and you need to decide what to look at first. Symptoms: hundreds of lines of subfinder/amass/httpx output, "which of these is interesting", "what should I look at first", "triage this recon", a wall of live hosts with tech/status/port data.
ujjwalks/buyer-lens Skill
1★Reviews a website, landing page, or product concept through the eyes of its real buyers and reports purchase intent. Builds attribute-conditioned buyer personas, runs a synthetic panel using the SSR method, maps workflow-coverage gaps and incumbent alternatives, and returns scored segments, verbatim objections, and prioritized fixes. Use whenever the user wants a landing page, website, pricing page, or product idea reviewed from the customer's perspective, asks "would people buy this", "validate my idea", "test this concept", "how will my target audience react", wants purchase-intent or pricing feedback, a synthetic panel, focus group, or market research on a startup or product concept, or asks you to act as their customers or buyers — even if they never mention personas, surveys, or purchase intent. NOT for signal inventory or instrumentation planning: if the user asks what buying or intent signals to track, collect, or instrument, use signal-lens instead.
heyashishsaini/dotnet-skills/skills/dotnet-architect Skill
no license1★ repoSenior .NET solution architect and enterprise software engineer persona. Use this skill whenever the user asks about designing, building, or architecting .NET projects, full-stack applications, or backend systems. Trigger on any mention of ASP.NET Core, Web API, EF Core, Clean Architecture, SQL Server, PostgreSQL, JWT, Docker, Azure, Redis, Semantic Kernel, or OpenAI integration in a .NET context. Also trigger for: "design a system", "architect a project", "how should I structure", "help me build X in .NET", "what's the best way to do X in .NET", project setup advice, database schema design, API design, auth flows, deployment strategy, or scalability discussions. Always include interview tips and production concerns in responses. Adapt output depth to what was asked — don't dump all 10 sections when the user asks a targeted question. Respond with detailed mentor-style prose, not terse bullets.
Sarakael78/Bridge-Search Skill
1★Set up and operate the WSL2-to-Windows search bridge for Everything (`es.exe`), AnyTXT via its HTTP Search Service only, and the `bridge_search` MCP package. Use when working across `/mnt/c` and Windows drive paths such as `C:\`, `D:\`, `E:\`, `F:\`, and `X:\`, when you need fast Windows filename search, full-text file-content search on Windows, or when enabling this repo’s MCP server (`scripts/server.py` wrapper or `python -m bridge_search`). Do not look for or rely on an AnyTXT CLI binary; in this workflow AnyTXT is HTTP-only.
Github actions security review
Fyzel/claude-skills/skills/github-actions-security-review Skill
1★ repoAudits and hardens GitHub Actions workflows against the OWASP GitHub Actions Security Cheat Sheet: dangerous triggers (pull_request_target, workflow_run, issue_comment), unpinned or impostor third-party actions, GITHUB_TOKEN over-permissioning, script injection, secrets handling (static creds, secrets: inherit, masking, secret scanning, persist-credentials), artifact/cache poisoning, self-hosted runner risk, egress restriction, repo hardening, AI-assistant-in-CI/CD risk, and static analysis (CodeQL actions, Zizmor). Use whenever a user asks to review, audit, secure, or harden a GitHub Actions workflow or CI/CD pipeline; mentions .github/workflows, GITHUB_TOKEN, pull_request_target, workflow_run, self-hosted runners, action pinning, OIDC/trusted publishing, or Zizmor/CodeQL for Actions; or wants a new workflow written securely. Always run the Security Gate before returning Actions YAML, whether reviewing existing files or generating new ones.
malkreide/mcp-audit-skill Skill
1★Reproduzierbares Audit von MCP-Servern gegen einen versionierten Best-Practice-Katalog. Verwende diesen Skill wenn der User (1) einen MCP-Server gegen Best Practices prüfen will, (2) Sicherheitsfindings für einen Server dokumentieren möchte, (3) den MCP Audit Tracker (Notion) abarbeitet, (4) fragt «ist mein Server sicher / production-ready / standard-konform», (5) den Begriff «Audit», «Findings», «Compliance-Check», «Best Practice» im MCP-Kontext erwähnt, (6) einen Refactoring-Plan für einen bestehenden Server erstellt, oder (7) für mehrere Server einen vergleichenden Audit-Report erstellen möchte. Auch bei allgemeinen Aussagen wie «ist der Server gut gebaut?», «was muss ich noch fixen?», «entspricht das den Standards?» diesen Skill anwenden.
myceldigital/goal-prompt-architect Skill
1★create, audit, and improve high-performance /goal prompts for autonomous coding agents and long-running agent workflows. use when the user asks for a /goal prompt, goal prompt template, codex/claude code/hermes mission prompt, long-running agent prompt, multi-day autonomous execution prompt, marathon agent prompt, repo-specific autonomous task prompt, or wants to transform a vague task into a measurable, risk-bounded, verification-driven execution contract.
tokyubevoxelverse/detox Skill
1★Hunt down and fix flaky tests. Use when a test suite fails intermittently, CI needs re-runs to go green, or the user wants to know which tests are flaky versus genuinely broken — and why.
Muzili919/claude-skills-finder Skill
1★Search GitHub for Claude Code skills, plugins, and agents. Use when the user asks to find, discover, or list community Claude Code skills, or asks "what skills exist for X" (e.g. SEO, testing, deployment, content).
Aidress skill find verified interview scheduling agent
Aidress-ai/aidress-skill-find-verified-interview-scheduling-agent Skill
1★Find a Verified Interview Scheduling Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for hr agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
alexmmatos/essentials-claude-code/.claude/skills/add-agent-template Skill
no license1★ repoAdds a new subagent template to the catalog used by --generate-all-agents and --generate-essential-agents
hlsitechio/claude-skills-security/appsec-stack-pack/angular-security Skill
1★ repoSecurity audit for Angular applications including DomSanitizer bypassing (bypassSecurityTrust*), innerHTML binding, dynamic component loading, route guards (CanActivate, CanLoad), HttpClient interceptors, environment.ts file leakage, and Angular-specific patterns. Use this skill whenever the user mentions Angular, @angular/core, DomSanitizer, bypassSecurityTrustHtml, route guards, HttpInterceptor, environment.ts, Angular CLI, ng build, or asks "audit my Angular app", "Angular security review", "DomSanitizer safe". Trigger when the codebase contains `@angular/core` in package.json, `angular.json`, or `*.component.ts` files.
princekrz/skills-builder Skill
no license1★Build, review, and improve any Claude skill interactively. Use when user says "build a skill", "create a skill", "review my skill", "improve this skill", "I need a skill for", "skill template", or "help me write a skill". Do NOT use when user wants to build an actual app, website, or API — only when they want to create a SKILL for Claude.
hugoassisj/argus-db/skills/review Skill
1★ repoPrincipal-engineer database review board. Reviews the database layer of a change: relational schema design, Prisma models, migrations, indexes, query performance, scalability, DB security, and DB-related backend code (transactions, connection pools, caching, pagination). Produces evidence-first findings with severity, confidence, trade-offs, and an explicit approval decision. Use when: reviewing a schema.prisma change, reviewing a database migration or SQL DDL, reviewing Prisma Client or repository query code, adding or changing indexes, designing or changing a data model, auditing a schema for scale, checking a PR that touches the database, or when asked to review database, Prisma, schema, migration, indexing, query, or data-access changes.
skshadan/kage/skills/kage Skill
no license1★ repoLocal pentest sandbox for a full black-box engagement. Triggers on "kage", "pentest", "security audit on", "audit the security of". Runs recon, deep testing, exploit verification, and judging inside a per-engagement Kali Docker container. Each host working directory gets its own isolated sandbox. Produces `./results/<target>/audit-report.md`.
rammc/salesforce-agent-script Skill
1★Implement, review, or improve Salesforce Agentforce agents written in Agent Script — the declarative DSL for hybrid reasoning in the Agentforce Builder. Use when working with Agent Script syntax (blocks, expressions, variables, hooks, transitions, action chaining); when designing topics or subagents and the start_agent block; when exposing actions as tools to the LLM via reasoning actions; when balancing deterministic logic instructions against LLM prompt instructions; when migrating between Topics and Subagents terminology (April 2026 rename); when building agents in Agentforce Builder Canvas or Script view; when using Agentforce DX CLI or the Agentforce DX VS Code extension; or when writing agents with Agentforce Vibes. Trigger this skill whenever the user mentions Agentforce, Agent Script, agent topics, subagents, Atlas Reasoning Engine in a scripting context, agent transitions, reasoning actions, @utils, @variables, or @actions — even if they don't explicitly name the skill.
Criss404/agent-kb-toolkit/skills/archive-sessions Skill
1★ repo把各家 agent harness(Qoder/OpenCode/Claude Code)的 session 对话记录逐字导出为 markdown 备份档案,存到 ~/sessionbackup/<harness>/ 下。触发场景:用户说"备份会话/归档对话/导出session/完全记录/archive sessions"等。这是确定性转录(transcription),与知识库策展(save-to-kb)互补,备份档案不进知识库。
shubhamaniket/Code-Optimizer Skill
1★Interactive code intelligence tool that audits, rewrites, and guards code across 8 quality dimensions (SOLID, design patterns, architecture, SDLC, security, code smells, error handling, performance) plus optional concurrency and API design layers. Scores code 0–100 per layer, identifies anti-patterns before prescribing fixes, and cites a named principle for every finding. Use when the user wants to analyze, optimize, or build code with quality guardrails.
viktor-milev/claude-skills/business-decoder Skill
1★ repoBuild a first-principles, plain-English understanding of any publicly listed company — the front-of-funnel lens applied BEFORE any valuation or thesis work. Covers what they do, how they make money, the need they serve, their customers, value-chain seat, ownership and control, the tailwind or headwind they ride, and whether it is a good, mediocre, or fragile business — translating ALL domain jargon (biology, physics, chemistry, engineering) into plain analogies a finance generalist gets. Trigger on "decode this business/company," "what does X actually do," "how does X make money," "understand this business," "is X a good business," "explain this company in plain English," "first-principles read on X," "I just heard about X." Industry-agnostic — biotech, photonics, industrials, software, anything. NOT for valuation, multiples, margins, or estimates (use a dedicated valuation skill); NOT for a buy/sell/short/mispricing view or sizing (use investment-council); NOT for fund or manager due diligence.
bacsystem/skills/git-flow Skill
1★ repoUse when changes are ready to ship and you need to go from working tree to pull request — staging, reviewing, conventional commit, version bump, and PR. Triggers include "commit and open a PR", "ship this", "create the PR", finishing a feature/fix, or preparing a release.
avikbal-dm/claude-seo-skills/plugins/growth-os/skills/ai-search-visibility Skill
1★ repoGet a brand cited inside AI answers across Google AI Overviews, AI Mode, ChatGPT, Perplexity, Gemini, Copilot, and Claude. The tactical GEO and AEO module: baselines citation share, finds the citation gaps, restructures content for extraction, builds the evidence and entity signals AI engines reward, fixes crawler access, and tracks share of voice over time. Use when someone wants GEO, AEO, or AI Overview optimization, asks why AI engines do not cite their brand, wants to be the answer ChatGPT or Perplexity gives, or needs an AI search visibility plan. Strategy comes from cited-framework. This is the hands-on execution.
mb3rgel-ui/atlas-claude-skill/skills/coding-agent-loops Skill
no license1★ repoAtlas autonomous coding loops — run multi-step coding tasks with task-level checkpoints, automatic progress tracking, and blocker detection. Use when executing a coding task autonomously, running a build-fix loop, or implementing a sprint task end-to-end.
lilianobennett-ai/events-agent-skill Skill
no license1★Researches, evaluates, and recommends conferences, summits, and trade shows for B2B partnerships and growth teams. Use this skill whenever a user asks about events, conferences, sponsorships, speaker opportunities, CFP deadlines, trade shows, summits, or which events to attend. Also use when a user wants help comparing event ROI, evaluating sponsor packages, scoring events against their ICP, or building an events calendar. Trigger even when the user does not explicitly say "use the events skill" — any partnerships, BD, or marketing question about industry events should activate this.
HDHNezherParking-cum-Y638-Intl-Ltd/titan/skills/ops Skill
1★ repoSession operations spine — one continuous workflow: PREFLIGHT (verify repo state before trusting anything) → work → LAND (gate, commit, ledger, lessons, staleness sweep), plus DECIDE (owner-decision interview → dated record → propagation sweep) and COMMISSION (external template/prompt intake → conflict adjudication by the record). Use at session start ('preflight', 'resume', 'where were we'), when finishing a chunk ('land this', 'ship and log', 'wrap up'), when an owner-only decision is needed ('decide X', 'founder decision', 'interview me'), or when an outside prompt/template/brief arrives ('audit this commission', 'a template says...').
nyldn/fable5-optimizer/skills/fable5-optimizer Skill
1★ repoLoad this skill before answering whenever a request mentions Codex, GPT-5.5, codex commands, or Fable 5, or asks which model or agent should handle, review, implement, or verify something. That includes advisory questions (should Claude or Codex handle this, who should review this branch diff, is this worth delegating), not just direct commands. Also covers delegating bounded implementation, independent code review, data gathering, or runtime verification to Codex; optimizing Fable 5 usage or effort settings; and requests to test a flow, verify UI behavior, inspect a running app, or capture screenshots needing local browser/computer-use automation. Do not use for ordinary implementation or review with no model-ownership question, and not for generic prompt rewriting.
SkillMedev/technical-writing-studio/skills/api-design Skill
1★ repoDesigns REST API surfaces - resource naming, HTTP method and status-code semantics, error shapes, pagination, and filtering - and delivers an endpoint spec a consumer can build against without asking questions. Use when someone asks "how should I name this endpoint", "what status code should this return", "should this be PUT or PATCH", "how do I paginate this list", or is reviewing an API before it ships to external consumers. Do NOT use for planning breaking-change rollouts and deprecation windows - use api-versioning-strategist instead; for GraphQL type and resolver design - use graphql-schema instead; for generating client SDKs from an existing spec - use api-client-generator instead; for designing inbound webhook endpoints - use webhook-receiver-hardener instead.
The same file is in 3 other repositories
Fantasymax/easy-build-skills/plugin/user-research-for-ai-config/skills/user-research-for-ai-config Skill
no license1★ repoCRITICAL: If user says "design/make a skill for X" / "我想做一个 XX 的 skill" / "帮我做个 AI 写 XX 的 skill" — DO NOT write it yourself, USE THIS SKILL to interview them first. That IS the purpose. Use for personalized AI config or custom skill via structured self-interview, not copying templates. Two outputs: (A) Principles — CLAUDE.md / AGENTS.md / .cursorrules / system-prompt for Claude Code / Cursor / Codex / OpenCode / Aider etc. (B) Custom skill — design from scratch OR extract recurring task; works whether user has a clear task or needs AI to discover one. Trigger: 我的 principles / 自己的 skill / 个性化 AI / 帮我设计一个 skill / 我想做一个 XX 的 skill / 让 AI 写 XX 的 skill / 把我会的事教给 AI / build my own CLAUDE.md / make a custom skill / design a skill from scratch / build a skill for X / AI that understands me. Do NOT use for customer research, product discovery, market research.
enmr10/token-doctor/skills/token-doctor Skill
1★ repoAudits and reduces token usage in context files (CLAUDE.md, AGENTS.md, memory files, docs). Measures token cost per file, finds waste (filler words, verbose phrases, blank bloat, oversized blocks), and safely compresses prose while preserving all code, inline code, URLs, file paths and tables. Use when your context files feel bloated, prompts are expensive, or you want to trim CLAUDE.md without losing meaning. Trigger: "reduce tokens", "token usage", "trim my CLAUDE.md", "compress context", "shrink memory file", "context too big", "save tokens", "audit token cost", /token-doctor. For skill description collisions, see skill-doctor.
dootask/skills/skills/claude-md Skill
1★ repo创建或优化仓库的 CLAUDE.md。
daiyanHasin/chat-snapshot-skill Skill
1★Compresses and exports the entire current conversation into a compact, portable JSON file that can be downloaded and used to resume context in any new chat or LLM (Claude, ChatGPT, Gemini, etc.). Also restores context from a previously uploaded JSON snapshot file. TRIGGER this skill automatically when the user types: - /export — compress entire chat into a downloadable JSON snapshot - /snapshot, /save, /compress — same as /export - "save my chat", "export context", "compress this conversation" - "running out of tokens", "context is full", "quota is low", "save before I run out" ALSO TRIGGER when the user uploads a .json file and says anything like: - "resume", "restore context", "load my snapshot", "continue from this" - "here is my context", "here is my json", "I uploaded my snapshot" - or simply uploads a .json file without saying anything — check if it looks like a chat snapshot Use this skill even if the user phrases it casually like "save this" or "I want to continue later".
Skill knowledge base management
zavora-ai/skill-knowledge-base-management Skill
no license1★Manage knowledge base — search articles, find related content, create drafts, publish articles, collect feedback, and detect knowledge gaps. Use when searching for solutions, creating KB articles, finding related content, identifying gaps, or improving article quality.
kora-projects/kora-skills/plugins/kora-v1 Skill
1★ repoBuild Java/Kotlin services on Kora Framework (ru.tinkoff.kora). Compile-time DI, reflection-free, annotation-processor (Java) or KSP (Kotlin) driven. Triggers - any Kora task, @KoraApp, @Component, @Module, @KoraSubmodule, @HttpController, @HttpClient, @Repository, @Query, @KafkaListener, @KafkaPublisher, gRPC, SOAP/WSDL, @S3.Client, MapStruct, @KoraAppTest, Testcontainers, @ConfigSource HOCON/YAML, OpenAPI codegen, @Json, metrics (Micrometer/Prometheus), tracing (OpenTelemetry OTLP), logging, probes, @Valid/@Validate, @Log/@Mdc, @CircuitBreaker/@Retry/@Timeout/@Fallback, @Schedule*, @Cacheable/@CachePut/@CacheInvalidate, JDBC/Hikari/Undertow. Use when - Kora build/setup/project/dependency/services/concept/asks mentioned.
hootbu/llm-wiki-mind/skills/vault-init Skill
1★ repoMevcut bir projeye llm-wiki-mind pattern'ına göre yeni bir Obsidian bilgi arşivi (vault) kur ve projeye bağla. Kullanıcıdan proje yolu ve vault yolunu alır, GitHub'daki Hootbu/llm-wiki-mind template'ini kullanarak kurar, projenin CLAUDE.md'sine vault işaretçisi ekler. Proje yolu olmadan (salt-vault) da kurulabilir. Yazılım, araştırma, kitap okuma, kişisel günlük gibi her alan için kullanılır.
tokyubevoxelverse/handoff Skill
1★Write an end-of-session handoff note — what changed, what's half-done, what's risky, exact next steps — for a teammate or future self. Use at the end of a work session, before a vacation, or when transferring work-in-progress to someone else.
kostiantyn-matsebora/canopy/skills/canopy-debug Skill
1★ repoTrace any Canopy skill with live phase banners and per-node tree tracing. Respects the current mode — in plan mode no changes are applied; in edit mode the skill executes normally.