agentsclimarketplace

Engineering

98,276 rows, by stacks then stars

  • Add agent hooks claude code

    yukihirop/nagi/.claude/skills/add-agent-hooks-claude-code Skill

    0★ repo

    Add agent-hooks plugin for sending tool execution and session start notifications to chat channels. Triggers on "add agent hooks", "enable hooks", "setup agent hooks", "add hooks".

  • Api design

    BTN101/claude-skill-pack/skills/engineering/api-design Skill

    0★ repo

    REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.

    The same file is in 11 other repositories

  • Cron postflight

    vdk888/bubble-skills/cron-postflight Skill

    0★ repo

    Cron-fire post-flight scaffolding. Audit-log INSERT, git commit + push, notification send. Replaces inline wrap-up boilerplate across scheduled tasks.

  • Oracle diagnostic lite

    1marcelserrano/oracle-diagnostic-lite/skills/oracle-diagnostic-lite Skill

    no license0★ repo

    Mini-diagnóstico estratégico grátis — a porta de entrada do Creative Oracle™. Roda 3-5 perguntas curtas sobre o negócio do usuário e devolve uma leitura de superfície: aponta EM QUE dimensão a tensão se concentra (quem você é pra quem, como você soa, por que compram, como você entrega) sem dizer como resolver. Termina com handoff explícito para o Diagnóstico Oracle completo — o motor pago que faz a leitura cruzada das quatro dimensões ao mesmo tempo. TRIGGERS: diagnóstico grátis, mini diagnóstico, self-assessment, me avalia, onde meu negócio trava, qual meu gargalo, o que está travando, raio-x do negócio, check-up estratégico, diagnóstico estratégico, oracle diagnostic, por onde começo, o que eu priorizo, qual meu maior problema, me dá um norte, diagnóstico rápido, avalia minha marca, avalia meu posicionamento, o que está errado no meu negócio, quero entender meu gargalo, leitura do oracle, testar o oracle, experimentar o oracle, amostra do oracle. Use SEMPRE que alguém pedir uma avaliação rápida ou gratuita do próprio negócio/marca, quiser descobrir onde está o gargalo estratégico, ou pedir uma amostra do Oracle — mesmo sem citar "diagnóstico". É a única entrada grátis do Oracle e ativa o funil isca→motor pago. NÃO use para diagnóstico profundo, plano de ação, reestruturação de posicionamento ou qualquer entrega que prescreva COMO resolver — isso é o motor pago, faça o handoff.

    The same file is in 1 other repository

  • Token efficiency

    Naimul-islam-bd/token-efficiency Skill

    0★

    Cuts token consumption on every task by enforcing lean responses, smart tool usage, and zero redundant work. Use this skill on ALL tasks by default — coding, writing, analysis, file work, Q&A, anything. It should trigger even when the user doesn't mention tokens, cost, or efficiency, because the whole point is saving usage silently in the background. Especially important for long sessions, large files, multi-step tasks, and repeated tool calls.

  • Handoff

    AshExplained/roblox-skills/handoff Skill

    0★ repo

    Compact the current conversation into a durable handoff document for another agent or future session to pick up. Use when the user says "handoff", "handoff to /prototype", "summarize for next session", "another agent should continue", or when switching skills/sessions after substantial context has accumulated.

  • Claude sync by skill

    JonMcMillan/claude-sync-by-skill Skill

    0★

    Read-only status/preview for claude-sync-by-skill — show what would change between this machine and the shared sync folder in both directions, without modifying anything. Use when the user types /sync-envs or asks to preview/check their Claude environment sync status. To actually move files, use /sync-env-up (push local → folder) or /sync-env-down (pull folder → local). For first-time configuration, run the engine with --setup.

  • Supabase owasp audit

    thiagoferal-ia/thiago-feral-skills/skills/supabase-owasp-audit Skill

    0★ repo

    Rigorous OWASP-aligned security audit of a Supabase-backed app, combining static repo review with live database inspection (RLS, policies, grants, advisors, storage, auth). Use whenever the user wants to analyze, audit, or review the security of an app using Supabase — especially if they mention OWASP, RLS, "security score", vulnerabilities, "is my app secure", edge functions, leaked keys, or provide a repo ZIP plus a connected Supabase project. Produces a first report IN CHAT: a textual situation report, a 0–10 score per OWASP Top 10 category as wireframes, and wireframes for app structure, strong points, weak points, and the correction pipeline (plus extras as warranted) — then offers a Markdown audit report and remediation plan. Trigger even if the user just says "audit my app" or "check my Supabase security".

  • Workflow builder

    LuckyCody/workflow-builder Skill

    0★

    Build, track, and resume hierarchical workflows. Every workflow is a tree of nodes (Goal → Phases → Tasks → Sub-tasks). When work hits a "we need data/tool we don't have yet" moment, spawn a SUB-WORKFLOW node — and resume the parent automatically when the sub completes. State persists per-project so any session (and any future agent) can pick up exactly where the last one paused. Use when you say "start a workflow", "we hit a fork", "resume X", "show me where we are in Y", or whenever beginning a non-trivial multi-step build that may discover unknown unknowns mid-flight.

  • Mcp auth helper

    sanjibani/mcp-skills-pack/skills/mcp-auth-helper Skill

    0★ repo

    Diagnoses MCP authentication failures and prescribes the right env var, OAuth flow, or scope fix. Use when an MCP tool returns 401, 403, or a credential-shaped error. Triggers on "auth failed", "invalid token", "missing credentials", "set FIELDROUTES_MCP_AUTHENTICATION_KEY", "OAuth scope", "401", "403", "permission denied".

  • Unreal mcp setup

    GergelyKrista/my-skills/unreal-mcp-setup Skill

    no license0★ repo

    Set up or troubleshoot the Unreal Engine 5.8 Model Context Protocol (MCP) server so Claude Code can drive the Unreal Editor. Use when a user is connecting Claude Code to Unreal Engine, sees only the AgentSkillToolset (missing Scene/Actor/Blueprint toolsets), gets "could not connect" / no MCP tools, has port/.mcp.json questions, or asks how to wire UE to Claude. UE 5.8 specific.

  • Claude Code Skills Custom DevTools Pack

    Mattakushi432/Claude-Code-Skills-Custom-DevTools-Pack/.agents/skills/Claude-Code-Skills-Custom-DevTools-Pack Skill

    0★ repo

    A curated pack of custom Claude Code skills for developers — installable as a Claude Code plugin marketplace.

  • Ab test analysis

    vermapragya/analytics-skill/skills/ab-test-analysis Skill

    0★ repo

    Analyzes A/B test results with significance testing, confidence intervals, sample ratio mismatch check, guardrail evaluation, and a stakeholder-ready readout. Use when the user mentions A/B test results, experiment readout, test analysis, lift, significance, p-value, treatment vs control, or asks "did the experiment work."

  • Dev guide

    Punpun1643/claude-skills/dev-guide Skill

    no license0★ repo

    Create and maintain a repository's developer guide — the document that explains the system's architecture, components, data flow, and design decisions to new contributors. Use this skill WHENEVER the user wants to write, update, regenerate, fact-check, or extend developer/architecture documentation, including phrasings like "update the dev guide", "the architecture doc is out of date", "document this module", "add X to the developer guide", "the DG", "regenerate the architecture docs", or "make a developer guide for this repo". Also use it proactively after significant structural code changes (new / removed / renamed components, reworked data flow) when the user mentions docs. The skill enforces that every description is grounded in the actual code and that diagrams use the correct type for what they illustrate.

  • Llm wiki

    myersguo/llm-wiki Skill

    0★

    Maintain a persistent, compounding LLM-maintained markdown wiki for daily AI conversations and sources. Use when the user asks to 沉淀/记录/归档/整理 AI 对话、更新或查询 llm_wiki、ingest a source into the wiki, file an answer back into the knowledge base, run wiki lint/health checks, or apply Karpathy's LLM Wiki pattern to personal/team/research notes.

  • Cleaner

    Swellshinider/janitor/integrations/codex/skills/cleaner Skill

    0★ repo

    Use when AI-generated code has bloated the repo: oversized files or classes, dead or unused code (functions, imports, variables, types, whole files), or duplicated blocks that need merging. Behavior-preserving cleanup only. Run when the user says "clean up this code", "remove dead code", "split this file", "this file is too big", "deduplicate", or "refactor without changing behavior". Not for new features, bug fixes, performance work, or over-engineering review.

  • Build spec

    robdasi/skills/build-spec Skill

    0★ repo

    Write the spec before you let an AI build an automation. Turns a one-line "build me a thing that..." into a reviewable build spec: the job, the trigger, inputs and outputs, the happy path, state and idempotency, failure modes, rate limits, observability, a cost ceiling, and acceptance criteria. Use this BEFORE asking Claude (or any agent) to build a workflow, integration, or scheduled job, so it builds the thing that survives week two instead of the thing that demos. It stops at the spec. Building to the spec is the next step.

  • Agent orchestration

    SkillMedev/ai-engineer-toolkit/skills/agent-orchestration Skill

    0★ repo

    Designs reliable multi-agent LLM systems - choosing a topology, writing handoff contracts between agents, deciding what runs in parallel vs series, and setting context, retry, and cost budgets that stop runaway loops. Use when someone asks "should I split this into multiple agents", "my agents keep looping", "how do I pass context between agents", "orchestrator vs pipeline vs router", or is architecting an agent workflow. Do NOT use for tuning a single prompt - use prompt-engineer instead; do NOT use for measuring agent output quality - use llm-evaluation instead; for making a product agent-operable end to end, use build-on-agent-native.

    The same file is in 1 other repository

  • Ab test analyzer

    SkillMedev/performance-marketing/skills/ab-test-analyzer Skill

    0★ repo

    Analyzes an A/B experiment to a defensible verdict - sample-size and minimum-detectable-effect math, two-proportion significance testing with confidence intervals, and checks for the traps that fake a win (peeking, sample ratio mismatch, multiple comparisons). Use when someone asks "is this test significant", "did variant B win", "how long should I run this experiment", "what sample size do I need", or shows experiment results and asks whether to ship. Do NOT use for logging and organizing ML training runs - use experiment-tracking instead; for causal questions without a randomized experiment use causal-inference; for general funnel or metric investigation use funnel-analysis or product-analytics.

    The same file is in 2 other repositories

  • Claude skill sansheng

    DQT-bit/claude-skill-sansheng Skill

    0★

    三省(sansheng)——多 Agent 并行调研工坊。把 OpenRouter Fusion API 的"panel + judge + 综合"多模型协作思路映射到 Claude Code 原生 Agent tool。 名字典故:曾子"吾日三省吾身"(独立反思)+ 三省六部(多部独立议事综合决策),三 = 推荐的 sub-agent 数。 方法论:spawn N 个 sub-agent 从互补角度并行调研 → 主 agent 做 Judge 交叉评审(标共识/分歧/缺口/独特观点)→ 综合输出敢下判断的结论。 当用户需要做"开放性研究、对比、评审、选型、风险盘点、跨领域调研"时使用。最终产出一份带共识/分歧/缺口标记的综合判断,以及可立即落地的下一步。 触发词包括但不限于:研究下 X、对比 X 和 Y、评审这个方案、X 的选型建议、X 有哪些风险、分析下 X、调研一下 X、X 和 Y 哪个更适合 Z、帮我看看 X 怎么选、X 方案有什么坑、三省一下 X、让三省看看。 即使用户只是丢一个开放性问题"应该 A 还是 B"、或要"全面看一下 X",只要任务有多个合理答案、需要多视角综合,都应该触发。 不要用于答案唯一的任务(bug 已定位、格式转换、单函数实现、删除冗余代码);不要用于用户在线等结果的实时迭代场景(spawn + 综合至少要 1-2 分钟);不要用于单页 web 查询能搞定的轻量问题。

  • Agent team

    0jg/skills/agent-team Skill

    no license0★ repo

    Configures and invokes the Claude Code subagent team for implementation tasks. Use this skill whenever a task involves more than one file, any physics or ML logic, or any implementation that warrants specialist review. Triggers on: "implement", "write the code for", "build", any task moved to In Progress on the board, or whenever the implementer produces code touching physics equations, numerical methods, ML architectures, or training loops. Always invoke this skill for non-trivial work — do not let the main agent implement and review its own code.

  • Last 90

    Avanderheyde/webapp-last-90/plugins/last-90/skills/last-90 Skill

    0★ repo

    The last 90% of shipping a web app — everything agents skip: authz, monitoring, legal, backups, rate limits, CI/CD, ops. Run it after deploying (the follow-on to vps-saas / levels.io) to make a freshly-launched web app actually safe and set up properly. Goal-driven: keeps working until the launch gate is 10/10, checking in only when it needs your accounts or a decision. Pass 'explain' for teaching mode that explains what the last 90 is and why each item matters.

  • App analyzer optimizer

    roedyrustam/claudevibeskills/src/app-analyzer-optimizer Skill

    no license0★ repo

    Deeply analyzes application architecture, dependencies, and performance configurations, and executes targeted optimizations aligned with active project skills. Use whenever the user wants a full project health check, dependency audit, performance review, or asks "analyze my codebase" or "optimize my app." Trigger on phrases like "audit my project", "analyze the architecture", "find performance issues", "optimize this app", or "review my dependencies".

  • Spike first

    AllenShi100/spike-first Skill

    no license0★

    在写任何代码或计划之前,对抓取/爬虫/API集成/第三方服务/自动化对接类任务强制做一道"可行性闸门"—— 先用一次性探针对真实目标验证最大未知点(先打靶再造枪),探针通过才放行到设计和实现,不通过当场喊停换方案。 Use this skill whenever the user asks to scrape a website, crawl data, integrate with an external or third-party API/service, build an automated data pipeline against a system you don't control, or any task where "can we even reliably get the data or access we need?" is still an open question — even if they don't explicitly ask for validation. 触发词:抓取、爬虫、采集、集成、对接、API、第三方服务、自动化对接、 反爬、scrape、crawl、integrate、webhook。务必在这类任务一出现就触发,不要等撞墙了才想起。 但以下情况**不要触发**(即使句子里带了上面的关键词):维护或调试**已经在跑**的抓取/集成代码、 处理已经拿到的数据、纯本地的重构或性能优化、跑测试(含"集成测试")、写文档、 纯概念问答(如"解释 REST 和 GraphQL 的区别")。判据只有一条——有没有一个开工前还不确定 "能不能稳定拿到"的外部数据或访问;没有,就不是这个 skill 的活。

  • Prompt lint

    fxw-labs/prompt-lint Skill

    0★

    评估和审计 AI prompt 的质量。检测常见错误模式,输出 8 维度雷达图评分和改进建议。仅在用户明确要求评估/检查/lint prompt 时激活。不激活于正常对话、编码、文档编写。

  • Tdd

    kongyo2/TDD/tdd Skill

    0★ repo

    Strict t-wada style Red-Green-Refactor TDD for TypeScript + Vitest projects. Use when implementing features, fixing bugs, changing runtime behavior, or refactoring logic — any task that adds or modifies production code. Enforces test-first development with a verified Red, minimal Green, and disciplined Refactor, plus agent-safe Vitest execution rules.

  • 6502 assembly

    Yuki001/nes-skills/skills/6502-assembly Skill

    no license0★ repo

    Write, read, debug, and optimize 6502 assembly language code. Use this skill whenever the user asks about 6502 assembly, MOS 6502, 6510, 65C02, or 65C816 programming, or is working on projects for the NES, SNES, Commodore 64, Apple II, Atari 2600/8-bit, VIC-20, BBC Micro, or any other 6502-based platform. Also trigger when the user mentions opcodes, addressing modes, zero page, stack operations, or assembly language concepts in the context of 8-bit/retro computing. Covers instruction set, addressing modes, common algorithms (16-bit math, multiplication, division), memory layout, optimization, and platform-specific patterns. Even if the user just says "assembly" in a retro computing context, use this skill.

  • Ax2012 aos crash triage

    whobat/AI-Agent-skills/skills/ax-retail/ax2012-aos-crash-triage Skill

    0★ repo

    Triage Microsoft Dynamics AX 2012 / R3 AOS (Ax32Serv.exe) crashes and the RPC session-allocation cascade. The bundled script collects, server-side, AOS process crashes (Application 1000 / Ax32Serv.exe), unexpected service terminations (System 7031 / "Object Server"), and the kernel session precursors (Dynamics Server 110 "Session Allocation Failed: already allocated" + 180 "invalid session ID"), then correlates AOS terminations with AX rich-client (Ax32.exe) crashes on the RDS/Citrix farm to expose the "AOS dies -> every client drops at once -> reconnect storm" cascade. Use when an AX AOS service crashed/restarted, users got disconnected en masse, or you see Event 7031/110/180 — e.g. "why did the AOS crash", "AX kicked everyone out", "Ax32Serv keeps restarting". Do NOT use for AX SQL/database slowness (that is ax2012-sql-performance) or generic non-AX event-log triage (that is win-eventlog-triage). Requires PowerShell 7+ and WinRM + an admin credential (always prompted).

  • Dependency risk audit

    SkillMedev/security-compliance-hardening/skills/dependency-risk-audit Skill

    0★ repo

    Audits third-party dependencies for exploitable CVEs, abandonment, license exposure, and supply-chain hygiene, and delivers a ranked findings report with a remediation order. Use when someone asks "is this package safe to add", "audit our dependencies", "npm audit is screaming, what actually matters", "can we use this GPL library", or is preparing a security review or vendor questionnaire. Do NOT use for triaging vulnerabilities in first-party code or a full CVE queue - use vulnerability-triage instead; for reviewing the code you wrote for security flaws - use secure-code-review instead; for how secrets are stored and rotated - use secrets-hygiene instead; for assembling compliance evidence - use soc2-evidence-helper instead.

    The same file is in 2 other repositories

  • Axioblade

    TobiZhao/axioblade Skill

    0★

    Use this skill for complex problem analysis, architecture and system design, engineering planning, research validation, product strategy, academic research design, and agent workflow design when the task requires first-principles reasoning, information-gain-driven boundary clarification, complexity control, sustained operating-cost constraints, external verification, or adversarial review.

  • Symlink skills

    usrrname/agent-skills/.agents/skills/symlink-skills Skill

    no license0★ repo

    Symlink every skill in this repo into one or more agent skills directories (defaults to ~/.claude/skills/ and ~/.agents/skills/) so the skills become globally discoverable. Use when the user says "install these skills", "make these skills global", "symlink skills to ~/.claude", "symlink skills to ~/.agents", "register the skills", or wants to update the global skill set after editing skills here.

  • Gpt tasteskill

    Fldicoahkiin/agent-skills-card/.claude/skills/gpt-tasteskill Skill

    no license0★ repo

    Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

    The same file is in 13 other repositories

  • Kiss blast radius

    Pr1m4lc0d3/KiSYSTEM/skills/kiss-blast-radius Skill

    0★ repo

    Use before editing, refactoring, moving, or deleting existing code — to keep the change contained to its bounded unit and prevent collateral damage to surrounding services and functions. Use whenever a change touches a file other code depends on, or whenever a refactor could ripple beyond the thing you were asked to change.

  • Claude

    giljr/claude Skill

    no license0★

    Complete guide to installing, configuring, and running bundler-audit in Ruby/Rails projects. Use this skill whenever the user mentions bundler-audit, gem auditing, vulnerabilities in Ruby gems, dependency CVEs, secure gem updates, or wants to ensure security in a Rails project's dependencies. Also trigger for bundler-audit result analysis, CVE/GHSA interpretation, and safe production update strategies.

  • Context portfolio interview

    KyleBehrend/context-portfolio-interview Skill

    0★

    Build or refresh the user's context portfolio — a portable pack of markdown files about who they are, their work, voice, tools and current projects that makes any AI session smarter. Use when the user asks to build a context portfolio, set up CLAUDE.md or custom instructions about themselves, or says "interview me about my work". Source what you already know from memory and past conversations first; interview only for the gaps.

  • Claude skill session handoff

    txampa/claude-skill-session-handoff Skill

    0★

    Produce structured end-of-session summary for seamless handoff to fresh context. Use when user says "session handoff", "wrap up", "hand off", or before /clear. Output is chat-only (no files).

  • Changelog release

    kwangsing3/claude-skills-toolkit/plugins/git-tools/skills/changelog-release Skill

    no license0★ repo

    Use when the user explicitly wants to cut a release, bump the version, or (re)generate CHANGELOG.md from git history — phrases like "release", "bump version", "update changelog", "cut a new version". Determines the semver bump from Conventional Commits since the last tag, updates the version manifest, writes CHANGELOG.md, and (only with confirmation) creates the release commit + tag. Prefers the `changelogen` CLI when available, otherwise does it by hand. This is a deliberate, opt-in release action — never run it as part of a routine commit+push.

  • Amortized intelligence

    Sapien3/amortized-intelligence Skill

    0★

    A compile-time doctrine for frontier models: intelligence has two timescales — frontier tokens spent once at design time become durable artifacts (harnesses, rubrics, skills/SOPs, evals) that cheap models execute at near-zero marginal cost. Read when: (1) a Fable/frontier session is doing work shaped like it will recur, (2) before CLOSING any substantive frontier session (the exit ritual: what judgment dies here as chat?), (3) deciding whether a recurring workflow can downgrade to a cheaper model, (4) authoring or updating any skill, harness, rubric, or eval, (5) the user says compile / amortize / down-shift / make-this-survive-the-session. Pairs with whatever runtime routing doctrine governs your live session — that one decides who executes now; this one decides what must outlive the session.

  • Clickhouse analytics

    SkillMedev/data-engineering-pipeline/skills/clickhouse-analytics Skill

    0★ repo

    Designs ClickHouse schemas and queries for fast analytics - MergeTree engine selection, ORDER BY key design, partitioning, materialized views, and projections. Use when someone asks "why is my ClickHouse query slow", "how should I order my sorting key", "should I use a materialized view or projection", "how do I deduplicate events", or is modeling an event or metrics table for OLAP. Do NOT use for tuning row-store OLTP databases like Postgres or MySQL - use sql-query-optimizer instead; for general relational schema design use database-schema; for reading query plans on traditional databases use explain-plan-reader; for the streaming ingestion side use kafka-pipelines.

    The same file is in 1 other repository

  • App store release prep

    SkillMedev/mobile-app-engineering/skills/app-store-release-prep Skill

    0★ repo

    Produce a reproducible signing, versioning, and store-declaration pipeline so an iOS or Android build passes App Store Connect / Play Console submission. Use when building or uploading a distribution .ipa/.aab, fixing signing/provisioning-profile or entitlement errors, bumping CFBundleVersion/versionCode, filling App Privacy / Data safety forms or PrivacyInfo.xcprivacy, wiring Fastlane lanes, or diagnosing a store rejection. Do NOT use for general (non-mobile) release steps like changelogs, tagging, or backend deploys - use prepare-release instead; do NOT use for store listing titles, descriptions, or keywords - use app-store-copy instead.

    The same file is in 1 other repository

  • Dispatch agent

    tobyrosen/dispatch-agent Skill

    0★

    Use when a Claude team leader (or a teammate) decides a scoped task should run on a non-Claude model. Covers model-matching by task type, spec discipline, a stateless dispatch tool, a web-browsing dispatch mode (agentic web research — search + fetch + verify live links), concurrency, and escalation.

  • Circuit breaker

    prkash1704/claude-skills/circuit-breaker Skill

    0★ repo

    Diagnose-before-thrash discipline that breaks debugging death-spirals. Trigger this the moment fixing starts going in circles: the same error keeps returning, two or more fix attempts have failed, the user says "still broken", "I've tried everything", "why isn't this working", or "stuck on this for ages", or you notice yourself proposing repeated edits to the same code without having confirmed the cause. Fire proactively, without being asked, whenever a bug is taking longer than it should. Supports intensity levels: lite, full (default), ultra. Once active, STAY active until the original symptom is confirmed gone -- do not drift back to guessing.

  • Llm council

    1marcelserrano/llm-council/skills/llm-council Skill

    no license0★ repo

    Passa qualquer pergunta, ideia ou decisão de alto custo de erro por um conselho de 5 conselheiros de IA que analisam o caso de forma independente, revisam o trabalho uns dos outros de forma anônima (peer review) e sintetizam um veredito final. Baseado no método LLM Council de Andrej Karpathy. Cada conselheiro pensa por uma lente diferente — o Contrário, o Pensador de Primeiros Princípios, o Expansionista, o Forasteiro e o Executor — que criam tensão proposital entre si. Entrega onde o conselho concorda, onde diverge, os pontos cegos que só a revisão cruzada pegou, uma recomendação direta e o primeiro passo concreto. Gera relatório HTML + transcrição. TRIGGERS: passa no conselho, roda o conselho, convoca o conselho, leva pro conselho, conselho disso, conselho dessa decisão, war room isso, sala de guerra, põe à prova, pressiona essa ideia, stress test disso, testa essa decisão, debate isso, debate essa ideia. TRIGGERS FORTES (quando vier com decisão real e trade-off): devo fazer X ou Y, X ou Y, qual das opções, qual opção, o que você faria, é a jogada certa, esse é o movimento certo, valida isso, me dá várias perspectivas, não consigo decidir, tô dividido entre, tô em dúvida entre. NÃO dispare em pergunta de sim/não simples, busca factual com uma resposta certa, nem "devo" casual sem trade-off de peso (ex.: "devo usar markdown?" não é pergunta de conselho), nem em tarefa de criação (escrever um tweet) ou de processamento (resumir um artigo). DISPARE quando o usuário traz uma decisão genuína com risco, opções e contexto que pede pra ser pressionada de vários ângulos.

    The same file is in 1 other repository

  • Ai workflow architect

    torykovdya/ai-workflow-architect Skill

    0★

    Platform-agnostic AI skill: transform any project idea into a complete technical blueprint — stack, schema, API, roadmap, and risk report.

  • Ai code governance skill

    Wyattputrescent882/ai-code-governance-skill Skill

    0★

    Governance workflow for AI coding agents such as Codex, Claude Code, Cursor, and Copilot Workspace. Use when implementing features, fixing bugs, refactoring, reviewing AI-generated code, adopting governance in an existing project, creating or updating AGENTS.md, CLAUDE.md, CODEX.md, architecture docs, project indexes, dependency policies, and coding standards. Enforces search-before-write, reuse of existing components/hooks/services/stores/utils/types, dependency control, small maintainable changes, verification, and clear change reports.

  • Contract test writer

    SkillMedev/qa-test-automation/skills/contract-test-writer Skill

    0★ repo

    Writes consumer-driven contract tests at service and API boundaries - Pact consumer tests, provider verification, broker publishing, and can-i-deploy gates - so an incompatible change fails a build instead of breaking integrations in production. Use when someone asks "how do I stop the backend breaking my client", "set up Pact between these services", "a renamed field broke a consumer that unit tests passed", or two separately deployed services must stay in sync. Do NOT use for designing a new API contract from scratch or reviewing its design - use api-design instead; do NOT use for end-to-end user-journey tests - use e2e-scenario-author instead; do NOT use for calls inside a single deployable - write a unit test.

    The same file is in 1 other repository

  • Prompt to loop

    tmanish/prompt-to-loop/prompt-to-loop Skill

    0★ repo

    Convert any build, make, create, design, or develop prompt into a structured agentic loop with elicitation, verification grounding, and termination. Use this skill whenever a user asks to build, make, create, design, develop, generate, scaffold, or produce any artifact (website, dashboard, app, design, document, agent, script, deck) — even if they don't explicitly ask for a "loop." Triggers on phrases like "build me a...", "create a...", "design a...", "make me...", "develop a...", "help me build...", "I want to make...", or any task that involves producing an artifact with measurable success criteria. Especially valuable when the user prompt is sparse or underspecified. Do not use for lookups, definitions, single-shot edits to existing files, or debugging existing artifacts.

  • Nestjs

    iamursky/nestjs-skill/skills/nestjs Skill

    0★ repo

    Build server-side applications with NestJS (Nest) — the progressive, TypeScript-first Node.js framework. Use when working with `@nestjs/*` packages, the `nest` CLI (`nest new`, `nest g`), or any NestJS building block: controllers & routing (`@Controller`, `@Get`/`@Post`), providers & dependency injection (`@Injectable`, custom providers, injection scopes), modules (`@Module`, dynamic/shared/global modules), and the request pipeline — middleware, guards (`@UseGuards`), interceptors, pipes & validation (`ValidationPipe`, class-validator), exception filters, and custom decorators. Covers configuration (`@nestjs/config`), databases (TypeORM, Sequelize, Mongoose, Prisma, MikroORM), techniques (caching, queues/BullMQ, scheduling, events, logging, serialization, versioning, file upload, SSE), security (Passport/JWT auth, RBAC/CASL authorization, helmet, CORS, CSRF, rate limiting/throttler), GraphQL (code-first & schema-first, Apollo, federation), WebSockets (gateways), microservices (TCP/Redis/Kafka/NATS/MQTT/RabbitMQ/gRPC transporters), OpenAPI/Swagger, testing (`@nestjs/testing`), and deployment. Targets NestJS v11.

  • Disciplined delivery

    nhattrung0911/shipwright/skills/disciplined-delivery Skill

    0★ repo

    Use at the start of and throughout any non-trivial build — web app, API, LLM app, ML/data pipeline, CLI, or library. Triggers on "build/create/implement X", new project or feature, multi-step work, or before claiming work complete. Enforces plan-first, phase/slice gating, per-slice testing, and evidence-based "done". Stack- and agent-agnostic (Claude Code, Codex, Gemini CLI).

  • A12 dmtool bug report

    mbackschat/a12-dmtool-releases/codex/skills/a12-dmtool-bug-report Skill

    0★ repo

    Produce a well-isolated bug-and-findings report for the dmtool CLI (a12-dmkits / A12 kernel) and save it to a folder the user picks. Use when a user hits an error, crash, internal error, or unexpected behaviour in dmtool, when they want to capture findings / DX friction / improvement notes, or when they ask to write or file a bug report against dmtool. Covers reading the result envelope (telling an internal tool error apart from a rejected input), shrinking to a minimal repro, an affected-vs-unaffected table, classifying genuine defects vs. your own input mistakes, a verbatim replay log, and a self-audit — then writing the report to a folder the user can upload or send however they like.

  • Docker compose wizard

    SkillMedev/devops-platform-engineer/skills/docker-compose-wizard Skill

    0★ repo

    Produces production-minded docker-compose configurations - pinned images, healthchecks with real intervals, health-gated startup ordering, named volumes, explicit networks, and env-file secrets - plus the matching .env.example. Use when someone asks "write a compose file for this stack", "why does my app start before the database is ready", "how do I add a healthcheck", "my compose setup works on my machine but not in CI", or is reviewing a docker-compose.yml before it ships. Do NOT use for orchestrating across multiple hosts or cluster workloads - use kubernetes-basics instead; for provisioning the underlying cloud infrastructure - use terraform-expert instead; for CI pipelines that build and push the images - use github-actions instead; for auditing how secrets are stored and rotated - use secrets-hygiene instead.

    The same file is in 1 other repository

  • How am i driving

    brunodantas/how-am-i-driving/skills/how-am-i-driving Skill

    0★ repo

    Score your recent Claude Code prompting and produce a graded, evidence-backed report card — how good were my prompts, measured? Reads your recent session transcripts, computes deterministic measures (prompt length, prompts/session, context front-loading), then judges the semantic measures (rework rate, clarification, steering) and five 1–5 qualitative grades with quoted evidence. Renders a Markdown Full Report, an optional HTML report, and a shareable HTML Scorecard (scores only, no quotes). Use when the user asks "how am I driving", "grade my prompting", "score my prompts", "make a scorecard", or wants measured feedback on their own Claude Code prompting.

  • Safe multi session deploy

    Madwr1d/skills/skills/safe-multi-session-deploy Skill

    0★ repo

    Use BEFORE committing or shipping any project that more than one AI agent or person works on at the same time. When you push code to a live website, app, or server — via any host (Vercel, Netlify, Cloudflare, Railway, Render, Fly, AWS/S3, a VPS over SSH/rsync, Docker, or FTP) — three things go wrong with concurrent sessions: one session's unsaved work gets clobbered, the deploy lands on the wrong target/environment so the real site never updates, and afterward nobody can tell which session's build is actually live. This skill is the checklist + scripts that prevent each, by isolating work, gating the deploy, and stamping + verifying a build-provenance marker on the live artifact.

  • Backend code review

    vipincode/exr-agent-skills/.claude/skills/backend-code-review Skill

    no license0★ repo

    Review backend / server-side code (Express, Node, TypeScript, Mongoose APIs) for correctness, security, convention adherence, and duplication. Use whenever the user asks to review, audit, critique, or sanity-check backend code — "review this service", "code review the auth module", "review my changes / this PR / the diff", "is this production-ready", "check this for issues". It reads ARCHITECTURE.md + MODULE_REGISTRY.md so it reviews against THIS project's conventions and flags code that duplicates existing registry entries (DRY). Standalone and read-only — run anytime, never auto-chained, and it does not modify source unless explicitly asked to apply fixes. Tuned for backend; not for frontend/React review. This is static code review only — it does NOT run the app or confirm a change behaves correctly at runtime; requests like "verify it works", "does it run", or "check that my change actually works" are run/verify intent (/verify or /run), not review.

  • Wiplash agent skill

    Wiplash-ai/wiplash-agent-skill Skill

    0★

    Use this skill when an AI agent needs to join Wiplash.ai, search the Waterpark-ranked feed, publish posts including externally hosted apps, leave feedback, vote, use private Cabanas, or inspect agent profiles through the Wiplash Agent Network API.

  • Generating arc42

    alicommit-malp/generating-arc42 Skill

    no license0★

    Use when asked to generate, create, write, scaffold, or bootstrap arc42 architecture documentation for any software codebase, repository, service, library, or component — including a doc/architecture folder or arc42 chapters derived from source code.

  • Claude dependency mapper

    Bakoware/claude-dependency-mapper/skills/claude-dependency-mapper Skill

    0★ repo

    Map a project's dependency graph. Generates an Obsidian vault (obsidian-graph/) for human visualization and, for medium/large codebases, a compact PROJECT_MAP.md for token-efficient AI navigation. Decides the route by file count, wires up CLAUDE.md, adds .gitignore entries so the graphs are not committed, and installs a PostToolUse hook that auto-refreshes the graphs on source edits. Use when the user runs /claude-dependency-mapper or asks to set up / refresh the project dependency graph.

  • Agent email patterns

    kumard3/lumbox-skills/agent-email-patterns Skill

    no license0★ repo

    Production patterns for AI agents that use email - signup-and-verify, email-based 2FA during browser automation, multi-agent inbox isolation, agent-to-human threads, and security hardening against prompt injection. Use when architecting reliable agent workflows that depend on receiving or sending email.

  • Karvey architecture

    MauricioQuezadaHaintech/karvey/plugins/karvey/skills/karvey-architecture Skill

    0★ repo

    Generate enterprise architecture design with explicit security controls, component boundaries, and integration patterns. Use after karvey-design-graphic. Triggers include "karvey architecture", "diseño técnico", "technical design", "arquitectura", "architecture", "diseño de sistema", "system design".

  • Skill adoption feedback

    onyx679/automotive-ve-ai-skills-kit/skills/skill-adoption-feedback Skill

    0★ repo

    Track AI Skill usage, user feedback, productivity impact, quality issues, and iteration priorities for internal business-process Skills. Use after piloting Claude Code, Codex, OpenCode, or similar agent Skills with business teams.