agentsclimarketplace

Engineering

98,648 rows, by stacks then stars

  • Github vault search

    generalbusiness-ai/keep-hermes-skills/skills/github/github-vault-search Skill

    3★ repo

    Search GitHub for Obsidian vaults (or any topic-tagged repos) by subject keyword. Covers multi-strategy API search, vault confirmation via directory check, and quality sampling via clone+analyze.

  • Agent boundary design

    MedocMay/ai-native-builder-consultant-skills/ai-native-builder-consultant-skills/skills/agent-design/agent-boundary-design Skill

    no license3★ repo

    Define what an agent owns, delegates, and refuses. Use when scoping a new agent, splitting a complex agent into multiple agents, or debugging low user trust caused by the agent doing too much or too little.

  • Agent calibration

    Shad0wMazt3r/The-Scaffolding/.agents/skills/agent-calibration Skill

    3★ repo

    Improve future activation behavior by capturing missed dependencies, split quality regressions, and workflow friction, then codifying minimal corrections in local instructions.

  • Claude agent converter

    dceoy/ai-coding-agent-skills/skills/claude-agent-converter Skill

    3★ repo

    Agent skills for AI coders

  • Audit common

    Yue-Zhou1/zkcrypto-audit/.codex/skills/audit-common Skill

    3★ repo

    Provides shared severity, testing-evidence, and finding-contract references for ZK and cryptographic audit skills. Use when classifying findings, checking whether test evidence is sufficient, or writing findings in a consistent structure.

  • Restassured skill

    jovd83/restassured-skill Skill

    3★

    Use when Codex needs to design, implement, run, document, or report Rest Assured API tests for REST services, contract-driven service tests, JUnit 5 automation, CI pipelines, or test-management integrations.

  • Einstein simplify

    jmsmrgn/einstein-simplify Skill

    3★

    Rewrites complex technical explanations, presentations, scripts, or any dense content so that a non-technical person sitting next to an expert could follow every word. Use this skill whenever the user wants to simplify a technical topic, make something ELI5, prepare an explanation for a mixed audience, strip jargon without losing accuracy, or says anything like 'explain it simply', 'make this accessible', 'dumb this down', 'non-technical version', 'teach this to a layman', or 'my audience isn't technical'. Also trigger when preparing presentations, demos, or scripts that will be delivered to audiences of mixed technical backgrounds. The Einstein frame: if you can't explain it simply, you don't understand it well enough. This skill enforces that standard.

  • Lever init

    fmind/agent-levers/skills/lever-init Skill

    3★ repo

    Bootstrap a repo for agent-levers. Creates .agents/levers/, wires CLAUDE.md/GEMINI.md to import AGENTS.md, writes an AGENTS.md skeleton when missing. Hands off via /lever-new.

  • Agent orchestra

    MarecGents/marec-agent-skills/skills/agent-orchestra Skill

    3★ repo

    多智能体协作 SKILL —— 拥有 251 个专业 Agent(覆盖 19 个部门)的完整多 Agent 协作系统。包含总调度 Agent、专业部门 Agent 和审查 Agent。当用户需要完成复杂任务、跨领域协作、多阶段工作流,或涉及前端/后端/设计/营销/安全/金融/GIS/游戏等专业领域时,使用此 SKILL。即使是单领域但高复杂度的任务也应启用。注意:不要因为用户没有明确提到"多智能体"就不使用——任何涉及多种技能或专业知识的任务都是此 SKILL 的适用场景。

  • Secretgate

    maxgfr/secretgate/skills/secretgate Skill

    3★ repo

    Use when the user wants to protect secrets/credentials from being sent to an LLM by a coding agent, install or manage a local secrets firewall, or scan text/files/repos for leaked credentials. secretgate detects secrets (221 gitleaks-derived rules + entropy + Luhn, zero-dependency engine, `node scripts/secretgate.mjs`) in prompts, file reads and tool output BEFORE they reach the LLM API, redacts them to stable placeholders (SECRETGATE_xxx) and restores the real values locally when the agent writes them back to files. Ships installers for Claude Code (hooks), OpenAI Codex CLI (hooks) and OpenCode (plugin). Triggers: 'protect my secrets', 'secrets firewall', 'stop sending credentials to the LLM', 'install secretgate', 'scan for secrets', 'redact secrets before sending', 'block credentials in prompts'.

  • Topease customs mcp

    TopEase-AI/topease-customs-mcp-skill/plugins/topease-customs-mcp/skills/topease-customs-mcp Skill

    no license3★ repo

    通过 TOPEASE/Tradee Customs MCP 查询和分析全球海关贸易记录。用于用户要求查询进出口海关数据、买家或供应商出货记录、产品关键词贸易数据、HS 编码贸易数据、国家或市场进出口记录、进口商/出口商线索,或要求配置、接入、排查 TOPEASE 海关数据 MCP 服务时。

  • X9 agent instructions

    xonika9/agent-skills/skills/x9-agent-instructions Skill

    3★ repo

    Use when writing a prompt or task brief for another agent without executing it, or when reviewing and improving an existing prompt or agent-instruction file — «напиши промпт», «нужен промпт под задачу», «посмотри инструкции в этом файле и предложи правки», «поправь глобальные правила», "write an agent prompt", "review these agent instructions". Global CLAUDE.md and AGENTS.md are one review target among others. Do not select this as the primary workflow for repository onboarding files (x9-context-files-generator), skill authoring (x9-skill-creator), ordinary prose, or actually handing a task to Codex (x9-codex-delegation); x9-context-files-generator and x9-skill-creator may load it as a subordinate instruction-quality rubric.

  • Agent creator

    coroboros/agent-skills/skills/agent-creator Skill

    3★ repo

    Create, configure, and orchestrate Claude Code subagents — specialized Claude instances with focused roles and limited tool access. Covers YAML frontmatter (name, description, tools, model, permissions, hooks, MCP servers), system prompt design, tool restriction patterns, background execution, and multi-agent orchestration. Use whenever the user mentions subagents, delegation, specialists, agent configs, `.claude/agents/`, the `/agents` command, or wants to parallelize work — even when they just say "background agent" or "delegate this".

  • Kill test first

    redamancy231-create/claude-skills/kill-test-first Skill

    3★ repo

    [决策:预注册] Pre-registration audit for new research directions, quant strategies, or thesis topics: falsifiable hypothesis, prior-art check, strongest counter-argument, death criteria before results, cheapest falsification with strong baseline, three-state verdict (GO/STOP/REDESIGN). Use before committing resources to a new direction. Not for bug fixes, experiment reproduction, or routine controlled experiments.

  • Promptize

    netcopilot-labs/promptize/skills/promptize Skill

    3★ repo

    Turn a rough ask into a structured prompt that the user reviews before execution. When the user invokes "/promptize <rough-ask>", Claude parses the ask, clarifies until ≥95% confidence, assembles the prompt using a 9-field canonical structure (Goal, Context, Inputs, Expected output, Scope, Constraints, Success criteria, Open assumptions, Examples), shows it for approval, then executes (in-session by default; optionally in an isolated subagent to avoid context contamination). Approved prompts auto-save to ~/.claude/prompts/ as a versioned history. User-initiated only — never convert a normal request into promptize mode proactively.

  • Skill

    lythos-labs/lythoskill/packages/lythoskill-arena/skill Skill

    3★ repo

    Test play for skills and deck configurations. DEFAULT: agent reads config, spawns parallel subagents via native Agent tool, judges outputs. Single-deck test AND multi-deck A/B comparison both run agent-orchestrated (no CLI). Cross-player comparison (kimi vs codex) is the ONLY case that needs the CLI runner. Always restores parent deck. No install, no working-set pollution, no deck overwrite. Subagent-friendly: resumes interrupted runs from saved state. CRITICAL: experiments run in `/tmp`, never in committed directories. Subagent inherits parent CWD — prompt must explicitly set workDir.

  • Architecture docs

    Flowerf19/agents-skills/architecture-docs Skill

    3★ repo

    Create and maintain concise project architecture and agent guidance docs and root README files based on real repository evidence.

  • Release

    joshsmithxrm/ppds-skills/.claude/skills/release Skill

    3★ repo

    Cut a PPDS Skills package release — get the recapture, decide the version bump, clean up prose, update CHANGELOG, tag + GitHub Release. Use when PPDS ships a new stable CLI/MCP that the skills package must track, or to publish any skills-package version bump.

  • Goal creator

    mysticaltech/goal-creator-skill/goal-creator Skill

    3★ repo

    Compile plain-language work into concise, host-aware, verifiable agent goals. Use when drafting, rewriting, tightening, auditing, or deciding whether to use a /goal-style contract for Codex, Claude Code, Cursor, OpenClaw, GitHub Copilot, orchestrators, CI agents, background workers, coding agents, review agents, research agents, migrations, debugging, refactors, audits, long-running tasks, or any multi-step work that needs explicit done criteria, proof, stop policy, anti-gaming constraints, review depth, and a completion receipt.

  • Indie app shipping

    cuongdev/indie-app-shipping/indie-app-shipping Skill

    3★ repo

    A solo/indie playbook for shipping small mobile apps fast on iOS/macOS (App Store) and Android (Google Play), testing real demand, and deepening only the apps that show signal. Use whenever the user is shipping a mobile app — scaffolding app structure, wiring onboarding/settings/paywall/restore/legal screens, writing or reviewing store metadata (title, subtitle, keywords, short/long description, promo text), planning screenshots/feature graphics, running a pre-submission Apple App Review or Google Play policy compliance check, writing review notes, setting up Play closed testing, handling a rejection, or deciding which shipped apps deserve more investment. Trigger even when the user doesn't say "checklist" — any mention of a new app idea, App Store or Play Store submission, App Store Connect, Play Console, IAP/subscription/paywall, screenshots, app rejection, ASO, Data safety form, closed testing, or the "ship many small apps" workflow should pull this in.

  • Improve

    nbialk/quiver-cli/.agents/skills/code/improve Skill

    3★ repo

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

    The same file is in 5 other repositories

  • Demo setup

    AlexAnsart/demo-studio/skills/demo-setup Skill

    3★ repo

    One-time setup that analyzes the current project and configures it to use the film-demo / narrate / sync-narration / produce-video skills — detects the dev server and framework, asks only when necessary, generates demo.config.json and .env entries, vendors the recording engine and project helpers, and scaffolds a first demo from reference patterns. Use when the user asks to set up, configure, or install demo-studio / video-recording skills for this project, or before running produce-video for the first time in a new codebase.

  • Grill me plus

    yuexiongHNU/grill-me-plus/skills/grill-me-plus Skill

    3★ repo

    Pressure-test a plan, design, decision, or idea with a branch-aware interview that balances full-map coverage and adaptive follow-ups. Best suited to sustained collaboration between a user and an Agent on large or evolving proposals, where scope, decisions, and unresolved risks must remain coherent across many turns. Use when the user invokes the host-specific command for grill-me-plus, such as $grill-me-plus in Codex, /grill-me-plus in slash-command hosts, or @skill:grill-me-plus in WorkBuddy; asks to be grilled or rigorously questioned; wants a proposal stress-tested; needs configurable follow-up limits; or wants both breadth and depth without getting trapped in one conversational branch.

  • Cliwright

    jjuanrivvera/cliwright/skills/cliwright Skill

    3★ repo

    Forge a complete, production-grade, agent-ready command-line tool (CLI) for any REST/HTTP API. Use when the user wants to build, scaffold, generate, or create a CLI; wrap an API in a command-line tool; turn an API into a CLI; or make a `gh`-style tool for a service. Produces a Go + Cobra + GoReleaser binary with OS-keyring auth, named profiles, an MCP server, an agent guard, CI/CD, and packaging — and drives the build to completion against a deterministic acceptance gate (`make verify`) so every quality criterion is provably met, not merely asserted. Triggers: "build a CLI for X", "scaffold a CLI", "wrap the X API in a CLI", "make a command-line tool for X", "API to CLI", "create a gh-style CLI".

  • Debug issue

    MiaoY0uShan/FP/.claude/skills/debug-issue Skill

    3★ repo

    Systematically debug issues using graph-powered code navigation

  • Solana fuzz

    belumume/solana-fuzz/solana-fuzz Skill

    3★ repo

    Use when fuzzing a Solana program or writing a Trident fuzz test: property and invariant testing of a program's state transitions, finding runtime logic bugs that happy-path and example-based tests (LiteSVM, Mollusk, Surfpool) miss, hardening an Anchor or native program before a mainnet deploy, or adding regression fuzzing across program versions. Trident is the Solana Foundation supported fuzzer by Ackee Blockchain. Dynamic, dev-loop property testing, not a static security auditor.

  • Herdr

    yangyang0507/herdr-skill/herdr Skill

    no license3★ repo

    Use this skill when running inside Herdr to coordinate workspaces, tabs, panes, sibling agents, server/test/log panes, agent-to-agent messages, or multi-agent delegation. Send a lightweight herdr-msg (reply-to + task), then stop and end the turn. Do not poll siblings and do not block-wait for replies; handle the peer message when it is injected into your pane.

  • Delegation strategy

    forjd/mythos-delegation-skill/skills/delegation-strategy Skill

    3★ repo

    Decision guide for choosing between inline work, one subagent, parallel subagents, and workflow orchestration. Use when planning a task that could involve searching many files, independent parallel strands, large-scale fan-out, specialized agents, or when tempted to spawn agents, so the agent picks the cheapest level that fits.

  • Config

    Hebbian-Robotics/nbx/skills/config Skill

    no license3★ repo

    Manage nbx NetBox URL, token, and named contexts in ~/.config/nbx/config.toml.

  • Claude mythos scaffold

    kasparovabi/claude-mythos-scaffold Skill

    3★

    Push Opus 4.x-class and smaller models toward Mythos/Fable-grade agentic behavior. Kernel of Fable-distilled patterns (decomposition, verification, next-action, context economy) plus demand-loaded skills, persistent mission files, named sub-agents, enforcement hooks, and domain modes (research, migration). Use when starting complex multi-step work, long-horizon tasks, or anything needing systematic persistence and verification. Do NOT fully load on Claude 5 models (Fable 5 / Mythos 5 / Opus 5 and later); over-scaffolding degrades them.

  • Web3 ai tools

    Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills/web3-ai-tools Skill

    3★ repo

    AI-powered tools for Web3 bug bounty automation. Use when you want to automate recon, run autonomous audits, or use AI agents for vulnerability discovery.

  • Agenzaar

    federiconuss/agenzaar Skill

    3★

    Register as an AI agent on Agenzaar, a real-time public and private chat platform where AI agents talk to each other. Teaches agents how to register, post in channels, send DMs, solve verification challenges, and manage their profile.

  • Skill

    Berektassuly/solana-audit-skill/skill Skill

    3★ repo

    Use when the user asks to audit a Solana or Anchor codebase, explain report-backed Solana vulnerability classes, review signer or PDA bugs, analyze CPI trust boundaries, assess Token-2022 or payment integrations, digest a public Solana audit report, investigate an exploit path, plan formal verification or invariant testing, or generate audit-readiness, release-gate, remediation, and final-report workflows.

  • Recursive agent improvement

    H-Ali13381/recursive-agent-improvement/.agents/skills/recursive-agent-improvement Skill

    3★ repo

    Use when an agent repeatedly fails at a narrow measurable subtask, the user wants a trainable specialist tool instead of more prompting, or the task needs an evaluator, reranker, classifier, detector, verifier, or small PyTorch model exposed to an agent.

  • Gpt image 2 search

    Ryan-yang125/gpt-image-2-skills/skills/gpt-image-2-search Skill

    no license3★ repo

    Use this skill whenever a user needs GPT Image 2 or ChatGPT image generation prompt ideas, Image2Studio prompt examples, visual references, style inspiration, reusable prompts, or examples for a subject, scene, product shot, poster, UI mockup, character, portrait, social media visual, composition, lighting setup, camera style, or aesthetic direction.

  • Spec crlp

    H2Sxxa/spec-coding-skills/skills/spec-crlp Skill

    3★ repo

    Run a spec-driven correction loop for code that already exists by comparing the current implementation against the spec and using linter output, test failures, runtime logs, and review feedback to diagnose and fix gaps. Use this whenever code is failing checks, drifting from acceptance criteria, regressing after changes, or needs a fix-verify-repeat loop after CI, tests, logs, or review comments.

  • Wick automate

    agoradynamics/wick/.claude/skills/wick-automate Skill

    no license3★ repo

    Detect when a task is being repeated often enough to be worth automating, then propose the right automation — a PROGRAM (deterministic script) or a SKILL (reusable judgment procedure). Analyzes the current session, the memory/ record, or an observation log; classifies program-vs-skill; estimates payoff; drafts the automation. Proposes, never auto-builds. Use when you catch yourself or the user repeating a multi-step task, or to mine an observation log periodically.

  • Agent fleet

    samhcus/skills/skills/agent-fleet Skill

    no license3★ repo

    Manage the Mad House agent fleet. List all agents in the central registry, check which repos have which agents deployed, and sync agents from the registry to target repos. Use when adding a new agent to the fleet, syncing agents across repos, auditing what agents are deployed where, or rebuilding the agent registry. Triggers on "sync agents", "deploy agents", "what agents are deployed", "add agent to repo", "agent fleet", "update agents".

  • Project memory skill

    tasuku-9/project-memory-skill Skill

    3★

    Use when resuming work after chat loss, switching AI models, migrating context to a new agent or workspace, or maintaining long-running research and project memory across sessions. Manages roadmap, decision log, hypotheses, research evidence, and recovery checkpoints as separate canonical files so no single transcript becomes the source of truth. Also use when you want to ensure no insight, decision, or failed experiment is lost — structured accumulation makes the project knowledge base analysable over time: which hypotheses were tested, which decisions were made and why, which blockers recurred, and how confidence evolved. Trigger phrases: resume work, context lost, switch model, handoff brief, update project docs, classify decisions, audit memory, migrate context, log experiment, track hypothesis, what did we decide, why did we choose, manage paper, track literature, log figures, thesis management, publication-grade traceability.

  • Nginx

    tensorshift/claude-nginx-skill/nginx Skill

    3★ repo

    Expert assistant for nginx — for everyday config work AND tricky debugging. Use it to set up a new site from scratch, write or refactor server/location blocks, configure a reverse proxy (proxy_pass, upstreams, load balancing), set up TLS/SSL and certificates, enable HTTP/2 or HTTP/3, wire up WebSockets, serve a SPA/Next.js/React frontend, proxy S3/MinIO, add caching/gzip/brotli, rate limiting, security headers, or real-IP behind a CDN. Also use it to review/harden an existing config, or to debug problems: a site that "won't load", is "slow on mobile", "works through VPN but not directly" (or vice-versa), returns 502/504/413, has redirect loops, or cert/SNI errors. Keywords: nginx, reverse proxy, proxy_pass, location, server block, virtual host, certbot, letsencrypt, websocket, upstream, load balancer, 502 bad gateway.

  • Ui design workflow

    FrozenMoon/ui-design-workflow Skill

    3★

    MUST use when implementing UI components or frontend pages in this project. Triggers: designing UI, implement page, develop UI, write component, frontend development, create component, build interface, style page, button, form, modal, toast, card, input, styling, interface, shadcn, ant design, antd, element plus, component library, UI library, 设计UI, 实现页面, 开发UI, 写组件, 前端开发, 创建组件, 构建界面, 页面样式, 按钮, 表单, 弹窗, 提示, 卡片, 输入框, 样式, 界面, 组件库, UI组件, 设计规范, 生成规范, 实现功能, 检查代码, 迭代规范, 切换组件库. Before writing any UI code, load this skill to read the project's design spec.

  • Devops sre

    Ow1onp/hermes-agent-skills/agents/devops-sre Skill

    3★ repo

    Use when the user needs DevOps or SRE help including CI/CD pipelines, Docker optimization, Kubernetes manifests, infrastructure safety, or production log analysis.

  • Architectural planning

    bhaumikmaan/claude-code-master-skills/skills/architectural-planning Skill

    3★ repo

    Read-only codebase analysis and implementation planning. Produces step-by-step plans with tradeoff analysis and critical file lists. Use when planning a feature, designing architecture, evaluating approaches, or when asked to plan before implementing.

  • Agent rongchi

    CercaTrovato/agent-rongchi Skill

    3★

    General discipline rules for coding agents. Use when any agent performs coding, debugging, refactoring, architecture changes, repository edits, test writing or running, tool-driven implementation, or code review. Enforces query-before-guessing, ask-before-ambiguous-execution, human confirmation for business assumptions, reuse before new interfaces, active validation, architecture compliance, honest uncertainty, and cautious refactoring. Chinese triggers: 认知纪律, 八荣八耻, 荣耻, 编码纪律, 主动测试, 遵循规范.

  • Code simplification

    momentmaker/kaijutsu/skills/community/code-simplification Skill

    3★ repo

    Reduce code without changing behavior. Apply Chesterton's Fence (don't remove what you don't understand) and the Rule of 500 (files over 500 lines usually need splitting). Use when the user says "simplify this", "clean up", "remove dead code", "tighten", or invokes /simplify. Composes polish (review-fix loop) and blunder-hunt (regression risk).

  • Framework skill authoring

    grusin-db/framework-skill-authoring/framework-skill-authoring Skill

    no license3★ repo

    Generate a complete, self-contained Agent Skills family for any code framework or library, so that a coding agent which only has the installed package (no source) can use the framework at full capacity. Use when asked to create skills for a framework, document a library for AI agents, build a skill pack / skill family, reverse-engineer a codebase into Agent Skills, turn a framework into something a notebook or IDE assistant can drive from just the installed wheel/jar, or author an entry-router skill plus granular capability skills. Walks an agent that HAS the source through four phases -- analyze, map to a universal capability taxonomy, generate, validate -- and emits an entry router, an always-injected workspace-instructions file, and one capability skill per domain.

  • Apply tdd loop en

    roebi/agent-skills/skills/apply-tdd-loop-en Skill

    no license3★ repo

    Applies the Test-Driven Development (TDD) cycle as an agentic loop of RED -> GREEN -> REFACTOR iterations until all requirements are covered or all existing code paths are tested. Use when a user or agent wants to write code strictly test-first, add missing tests to existing code, or drive a full TDD session for a module, class, or function. Activate for trigger phrases like: "apply TDD", "write this test-first", "do a TDD loop", "TDD cycle for", "drive TDD on", "red green refactor", or "add tests then implement".

  • Architecture satisfaction

    leek/agent-skills/skills/architecture-satisfaction Skill

    3★ repo

    Run a bounded architectural refactor loop toward a stated design.

  • Gpt 5 6 prompt engine

    wp-a/gpt-5.6-prompt-engine/skills/gpt-5-6-prompt-engine Skill

    3★ repo

    Use when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.

  • Agent introspection debugging

    uzysjung/uzys-agent-harness/.claude/skills/agent-introspection-debugging Skill

    3★ repo

    Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

    The same file is in 5 other repositories

  • Prompt forest

    herehere14/Cascade-An-AI-Agent-World-Simulator/extensions/prompt-forest/skills/prompt-forest Skill

    no license3★ repo

    Adaptive prompt routing for planning, verification, critique, code review, and confidence-qualified responses via the Prompt Forest plugin tools.

  • Agent context generator

    tjmaynes/skills/skills/agent-context-generator Skill

    3★ repo

    Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks. Use when a repository needs clear agent onboarding covering structure, tooling, testing, task flow, README expectations, and conventional commit summaries.

    The same file is in 5 other repositories

  • Api key leak checker leop

    leo-cheung-itlger/api-key-leak-checker-leop/skills/api-key-leak-checker-leop Skill

    3★ repo

    Check GitHub repositories, local Git projects, AI coding projects, and Vibe Coding apps for possible API key, token, secret, .env, and config leaks. Use when the user asks to scan for leaked keys, exposed credentials, GitHub secret scanning, Gitleaks, TruffleHog, .gitignore hardening, push protection, API key rotation, or remediation after accidentally committing secrets.

  • Architecture doc

    arsudsandesh97/Revoact/skills/architecture-doc Skill

    3★ repo

    Generate a complete ARCHITECTURE.md file for any software system. Use whenever the user asks to create, write, generate, or draft an ARCHITECTURE.md — a system-wide architecture document that explains the big picture: how major components fit together, what patterns are used, infrastructure decisions, and cross-cutting concerns. This skill triggers when users need to document: overall system architecture, infrastructure setup, deployment architecture, architectural patterns (microservices, event-driven, layered), technology stack decisions, scalability strategy, or cross-cutting concerns (auth, logging, monitoring across the system). Do NOT trigger for single-feature technical designs (use Design.md skill), UI/visual design, or code-level implementation details.

  • Skill

    GerardoRdz96/rlsgate/skill Skill

    3★ repo

    Run the rlsgate pre-deploy security gate on a Supabase-backed project. Use when about to deploy a vibe-coded / Supabase / Lovable / Bolt / Cursor app, or when the user asks to check for RLS holes, exposed secrets, anon-readable tables, public buckets, or unverified webhooks before shipping.

  • Agent system prompt

    Ahoo-Wang/skills/plugins/ahoo-agent-skills/skills/agent-system-prompt Skill

    3★ repo

    Use this skill when the user needs to write the actual instructional text that defines how an AI agent behaves. This is the skill for crafting the core "brain instructions" — the system prompt, persona, or behavioral rules that go into making an AI assistant, chatbot, or agent act in a specific way. Trigger for requests to: - Create or design a system prompt, instruction set, or persona for any AI agent - Write the "instructions" field for a custom GPT, Claude project, or similar platform - Define what an AI should or shouldn't do, how it should talk, or what tasks it handles - Help someone make their AI follow specific rules or adopt a particular personality - Improve, refactor, or debug an existing system prompt Also trigger for Chinese queries mentioning: 系统提示词, system prompt, AI 助手, 智能体, 机器人, 人设, or similar terms about defining agent behavior. If the user's goal is to produce written text that controls AI behavior, use this skill. If they need to write code, set up APIs, build infrastructure, or handle technical implementation, they need a different skill. This skill guides you through a structured interview-and-draft process to produce clear, effective system prompts grounded in prompt engineering best practices.

  • Requirements engineering

    SwiftyJourney/requirements-engineering-skill/requirements-engineering Skill

    3★ repo

    Use this skill to turn vague, ambiguous, or "lousy" requirements into precise, testable specifications BEFORE any code is written -- even when the user never says "BDD", "use case", or "acceptance criteria". Trigger when someone has a half-baked feature idea, an under-specified ticket, or a business brief that's "open to interpretation" and needs it pinned down: clarifying questions, As-a/I-want/So-that narratives, Given/When/Then acceptance criteria, use cases (data inputs, happy path, error and cancel courses), model-spec tables, request/response payload contracts, flowcharts, and module-dependency diagrams. This is the SPECIFICATION altitude -- WHAT to build and the contracts to honor. Hand off the implementation to the iOS architecture skill (composition root, layers, packages, concurrency), SwiftUI view code, and Swift Testing syntax -- do NOT use this skill to write or refactor that code, only to define what it must satisfy.

  • Bazel expert

    kinhluan/rules-quarkus-skills/.agent-skills/bazel-expert Skill

    3★ repo

    Expert knowledge for writing idiomatic Bazel rules, Starlark best practices, and build performance optimization. Use for Bazel build system questions.

  • Claude sync

    SamTerces/claude-sync/skills/claude-sync Skill

    3★ repo

    Sync the user's entire Claude brain — memory files, skills, agents, CLAUDE.md rules, and settings — across machines and teammates using a shared Git repository. Trigger this skill when the user wants to: push their Claude context to a remote, pull a teammate's context, see what's different between their local brain and the remote, merge a specific teammate's learnings into their own, onboard Claude on a new machine, or set up auto-sync. Also trigger on: /sync, "sync my claude", "push my memory", "pull team context", "share my brain", "sync to GitHub", "onboard new machine", "what's different from the team", "merge alice's context".

  • Cardano skill

    ADAvault/cardano-skill Skill

    3★

    Write, test, and debug Aiken smart contracts for Cardano. Use when writing validators, minting policies, or any on-chain Plutus code. Triggers on: Aiken, validator, smart contract, Cardano on-chain, Plutus, minting policy, spend validator, datum, redeemer, plutus.json, blueprint. Covers language syntax, validator patterns, property-based testing, security best practices, stdlib usage, and off-chain MeshJS integration.