菜单
这个仓库中的 skills
SkillsMP 已收集 gmackie/agent-skills 中的 113 个 Skill。打开任一 Skill 可查看来源和详情。
gmackie/agent-skills已展示 40 / 113 个已收集 Skill。
Generate a project-local verification skill that drives your app the way a user does, in any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove…
原文语言：英语
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
原文语言：英语
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
原文语言：英语
Initialize a new ESP32 project with proper structure and configuration using ESP-IDF. Use when creating ESP32 embedded projects, IoT devices, or microcontroller applications.
原文语言：英语
Configure and implement WiFi connectivity in ESP32 projects using ESP-IDF
原文语言：英语
Use when an Expo app is already validated and you need to build or upload it with EAS Build and EAS Submit. Handles profile selection, credential assumptions, TestFlight or Play upload flow, and submission sequencing after technical readiness and QA are…
原文语言：英语
Use when validating an Expo app before internal release, TestFlight, Play testing, or store submission. Checks project config, EAS profiles, identifiers, assets, environment handling, and build-significant drift so the app is technically ready before QA…
原文语言：英语
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for…
原文语言：英语
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
原文语言：英语
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
原文语言：英语
Compact the current conversation into a handoff document for another agent to pick up.
原文语言：英语
Use when provisioning, reviewing, or hardening infrastructure that runs on Hetzner Cloud. Inventories hcloud, Terraform, cloud-init, and service bootstrap signals in the repo, then writes an operations plan for server lifecycle, networking, bootstrap, and…
原文语言：英语
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding…
原文语言：英语
Author plans (implementation plans, migration plans, design docs, PRD-style plans) as rich, themed, self-contained HTML documents with mermaid diagrams rendered to inline SVG, and publish them with `npx postplan upload`. Use whenever creating or updating any…
原文语言：英语
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
原文语言：英语
Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository. Use whenever a user asks to add anti-slop lint rules, copy the anti-slop plugin, configure opinionated Oxlint rules, or migrate an existing local anti-slop setup.
原文语言：英语
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
原文语言：英语
Use when reviewing recent Codex, Claude Code, or repo planning work to extract reusable patterns, mistakes, and candidate skills. Automatically searches the current repo, nearby repos, and home skill/session directories, then writes a retrospective report,…
原文语言：英语
Use when an agent should discover relevant local context on its own before asking for pasted files or paths. Scans the current repo, nearby working repos, and local Claude or Codex directories for plans, docs, reviews, TODOs, and skill artifacts so later…
原文语言：英语
Use when a React Native or Expo app needs report-only mobile QA with Maestro on a simulator or emulator. Verifies local prerequisites, runs flows with explicit artifact and report output, captures screenshots and logs, classifies severity, and produces exact…
原文语言：英语
Use when a React Native or Expo app needs local mobile QA with Maestro plus targeted fixes. Starts with a report-only Maestro pass, isolates one verified failure at a time, maps it back to app or flow code, applies the smallest fix, and reruns the narrowest…
原文语言：英语
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
原文语言：英语
Migrates Next.js projects to vinext (Vite-based Next.js reimplementation for Cloudflare Workers). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compatibility scanning, package replacement, Vite config generation, ESM…
原文语言：英语
Use when planning or reviewing domain and DNS operations for domains registered at Namecheap. Inventories domain, nameserver, and host-record signals in a repo, checks whether the workflow belongs in Namecheap or a third-party DNS provider, and produces a…
原文语言：英语
Use when adopting, validating, or hardening a Next.js deployment on Cloudflare Workers via OpenNext. Maps the repo shape, checks adapter and Wrangler prerequisites, reviews bindings and local-dev setup, and produces an adoption plan before deeper…
原文语言：英语
Initialize a production-ready Next.js web application with TypeScript, an application auth layer, Stripe payments, and database setup. Use when creating SaaS applications, e-commerce sites, or full-stack web applications.
原文语言：英语
Use when a web app or product surface needs PostHog instrumentation reviewed or added with discipline. Inventories SDK setup, provider wiring, event capture calls, identify/group usage, and feature-flag boundaries, then produces a concrete instrumentation…
原文语言：英语
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
原文语言：英语
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can…
原文语言：英语
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
原文语言：英语
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
原文语言：英语
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
原文语言：英语
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
原文语言：英语
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
原文语言：英语
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
原文语言：英语
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
原文语言：英语
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
原文语言：英语
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
原文语言：英语
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a…
原文语言：英语
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
原文语言：英语