Showing 6871–6900 of 10205 skills
Primeiro agente do Time de Migração. Detecta o paradigma do sistema legado a partir das specs, infere o paradigma natural da stack alvo, alerta sobre gaps e força uma decisão consciente do usuário. Produz paradigm_decision.md, leitura obrigatória de todos os agentes posteriores. Ativação: /reversa-paradigm-advisor (geralmente invocado por /reversa-migrate).
stribus/pygerengastos
Esboça a abordagem técnica como delta sobre o legado, gerando roadmap, investigation, data-delta, onboarding e interfaces da feature ativa. Use quando o usuário digitar "/reversa-plan", "reversa-plan", "esboçar plano técnico" ou pedir para virar requirements em desenho de solução. Terceiro skill do ciclo forward, depois de `/reversa-requirements` e (opcionalmente) `/reversa-clarify`.
stribus/pygerengastos
Terceiro agente do Time de Migração. Propõe estratégias de migração com trade-offs explícitos, considerando brief, paradigma e apetite. Recomenda uma estratégia mas deixa a escolha como decisão humana. Produz migration_strategy.md, risk_register.md e cutover_plan.md. Ativação: /reversa-strategist (geralmente invocado por /reversa-migrate).
stribus/pygerengastos
Decompõe o roadmap em ações atômicas com IDs sequenciais, dependências e marcador de paralelismo. Use quando o usuário digitar "/reversa-to-do", "reversa-to-do", "decompor em tarefas" ou pedir para virar o roadmap em uma lista executável. Quarto skill do ciclo forward, depois de `/reversa-plan`.
stribus/pygerengastos
Use when the user explicitly enables an automated same-project multi-thread development loop that keeps peer Codex tasks progressing, recovers conflicts or stale coordination, integrates verified work into local main, and closes cleanup without repeated gates; do not use before opt-in, for one-off coordination, remote publication without permission, or subagent creation.
CCDawn/briefbound-skills
Use when two or more existing independent Codex App threads in the same project can benefit from bounded peer coordination through BRT trusted relay, while each thread retains its original task, permissions, branch, and completion responsibility.
CCDawn/briefbound-skills
Use when Chinese-first active intent discovery, local context probing, user calibration before downstream skill selection, owner/workflow routing, continuation, permission inference, or multi-thread/conflict coordination is needed.
CCDawn/briefbound-skills
Use when existing independent Codex App threads in one project need peer advice, target/ACK validation, file or runtime-process ownership and shared data-root arbitration, conflict recovery, discussion, merge coordination, status exchange, or native-thread handoff without creating subagents.
CCDawn/briefbound-skills
Be the foreman on a big job. One lead model plans the work, hands pieces to helper agents in lanes that never share files, checks everything before accepting it and reports the cost; or runs a long solo build with an owner in the loop. Covers the North Star plan of record, briefs that carry the lead's reasoning, measured gates plus the owner's judgement, strike-based promotion between model tiers, a cost ledger and a mistake register every pass is checked against. Use it when the user types /foreman, says "be the foreman", "be the lead" or "orchestrate this", asks to delegate to subagents or run lanes or passes, or mentions a North Star, three strikes, tiers or promotion between models. Also load it when a task looks too big for one context or needs several agents or days, even if not asked by name; the skill then has you offer it and wait for a yes. Also use it to resume such a project, close a pass, report a session's cost or record a mistake. Not for a change one agent can finish in one sitting.
mattvideoproductions/MVP-Prompts
后端架构与工程规范。适用于构建或评审 agent/LLM 后端、任何涉及数据库(DB)的后端,以及建立或评审后端仓库工程门禁。
martin1847/evolab
生产级 Git 协作 SOP:受保护分支按仓库 tier 门禁、改动从 feature 分支起、集成默认 squash、rebase 判据、提交不加 AI 签名。任何 git commit / push / 开 PR / 建分支 / rebase / 合并场景加载;agent 写完代码准备提交前必读。Use when committing, pushing, opening a PR, branching, rebasing, or merging.
martin1847/evolab
适用于编写或评审任何后端服务,包括普通服务与 agent/RAG 系统。覆盖日志、tracing、OpenTelemetry、上下文传播、日志级别、trace/log/DB 关联、边界类型及 LLM/工具/检索调用观测。用户说“加点日志”“接一下 trace / instrument this”“set up observability”“这个错误怎么查不到”“这个请求怎么追踪”也触发。
martin1847/evolab
多智能体编排的领域无关内核。适用于抽象编排模式、创建新领域编排者,或设计多智能体架构。实际软件交付编排使用 cto-orchestration。不用于单 agent 一次性小任务或纯文档初始化。
martin1847/evolab
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
oberconcejo/VS-CODE
Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through the upstream x402 packages with facilitator-based settlement. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.
oberconcejo/VS-CODE
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.
oberconcejo/VS-CODE
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
oberconcejo/VS-CODE
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.
oberconcejo/VS-CODE
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects: one-PR-sized steps with self-contained context briefs, dependency graph with parallel-step detection, adversarial review gate, and plan mutation protocol. Use when planning a large feature, refactor, or roadmap that spans multiple PRs or sessions; not for single-PR tasks or when the user says "just do it".
oberconcejo/VS-CODE
AI KEY ——两套技能的总入口:做内容(选题/写稿/审核/复盘)+ 看生意(组合体检/营收归因/客户集中度/依赖风险/拿不准的决策)。三种模式:新手上路演示、任务前路由(按你的需求和丢进来的材料自动挑技能,把握大就直接开跑)、任务后导航。不知道用哪个就回这里。 触发方式:/aikey、/新手上路、/aikey 教程、「做条视频」「出个口播」「今天拍什么」「内容下一步怎么走」;新手教程:/aikey 新手指南、/aikey 新手、「这个怎么用」「第一次用,带我走一遍」「不知道能干嘛」 Single entry point for both skill sets — content (topic, script, review, retro) and business (portfolio, revenue, concentration, dependency, decisions). Three modes: guided onboarding demo, pre-task routing, post-task navigation. Trigger: /aikey, "make a short video", "what should I shoot today", "how do I use this" —— AI KEY · 不给公式,给判据。每条规则都标了实测代价。
iamzifei/aikey
AI KEY·做成一个技能 ——把这次会话里已经跑通的做法固化成一个新技能。不是从想法造技能——是从**已经产生过正确结果的那一段过程**里提炼,所以只在事情做完之后用。 触发方式:/aikey-skillify、/固化、/做成技能、/aikey-固化、「这次的做法留下来」「把刚才那套变成技能」「下次别再重新想一遍」「这个流程以后还要用」 Turn a method that already worked in this session into a reusable skill. Extracts from a completed run, never from an idea — so it only fires after the work is done. Trigger: /aikey-skillify, "make this a skill", "save this workflow", "I don't want to re-derive this next time" —— AI KEY · 不给公式,给判据。每条规则都标了实测代价。
iamzifei/aikey
Keep code edits and judgment in the main thread; dispatch lookups, research, and parallel pieces to Haiku, Sonnet, or Opus subagents by task.
simonwong/skills
Builds and runs a one-person AI-native creative service firm that takes repeat marketplace jobs (Upwork, Fiverr) and fulfils them with Astra orchestrating creative models through the Higgsfield API. Use when the user wants to turn freelance creative demand into an AI-fulfilled service business, for example "set up an AI agency that does Upwork jobs for me", "build a Studio Operator style job system with Astra and Higgsfield", "which Higgsfield model should I route this client job to", "how do I pick which AI service firm to start". Not for one-off image or video generation with no business around it, or for fully autonomous agents with no human approval step.
robert-botto/skipwatch
Builds an app that uses TypeSafe's Jev decision model through a coding agent such as Cursor, from getting an API key to a running demo. Use when the user wants to build something on the Jev API, for example "build an app with the Jev API", "set up Jev in my project", "use Jev to make fast decisions in my app", "improve my agent's memory with Jev". Not for apps that need a model to write text or code, or for training or fine-tuning a model.
robert-botto/skipwatch
Turns a tutorial video (YouTube, X, TikTok, Instagram, Facebook or any yt-dlp URL) or a local screen recording into an installed Agent Skill whose steps cite timestamps. Use when the user runs /skipwatch, or shares a video link or recording and asks to make, capture or save it as a skill. Also handles /skipwatch doctor, resume, list, pack, install and share. Not for requests to summarize, download or transcribe a video, or to follow its steps right now.
robert-botto/skipwatch
Use when the user wants to set up the skipdemo demo project, for example "initialise a skipdemo project", "run the skipdemo tutorial", "set up skipdemo with a prompt". Not for other demo CLIs or for installing skipdemo itself.
robert-botto/skipwatch
Use when working with navigation in an Expo + React Native app: adding routes, building tab/stack/drawer layouts, modal routes, dynamic segments (e.g. /profile/[id]), typed routes, deep linking, search params. Triggers on: "add a route", "wire up tabs", "open as modal", "set up deep linking", "configure navigation", or whenever an agent is about to touch a file under app/. Not for: styling navigation chrome (rn-styling), animating transitions (rn-animations-gestures, Wave 3), or non-RN web routing.
lukedj78/dev-flow
Use at the start of any React Native or Expo task to lock in foundational choices: Expo managed workflow as default, latest Expo SDK with New Architecture ON, TypeScript, npm. Triggers on: "starting a new RN/Expo project", "what is the right architecture for an Expo app", "managed vs bare workflow", questions about Fabric/Hermes/JSI/New Architecture, "differences between RN and React web". Also triggers as a precondition when any other rn-* skill is selected and project setup is unclear. Not for: styling (rn-styling), navigation (rn-expo-router), data (rn-data-fetching).
lukedj78/dev-flow
Measure and reduce a Skill's token footprint (always-loaded description + on-trigger SKILL.md body) without regressing routing accuracy or losing instructions. Use when a SKILL.md feels oversized, repeats rules, or has a vague description that might mis-route.
oliverweissl/context-garden
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
yeaight7/agent-powerups