探索开发、内容、数据与办公效率等 AI 技能。先比较用途和仓库热度，再查看技能说明与来源。
Force verification before claiming success or completion. Prevents false "it works" claims. Triggers when about to say "done", "complete", "works", "fixed", or "the implementation is ready". Requires actually r...
Use when operating the Codex delegation MCP server and tools (delegate.spawn, delegate.question.*, delegate.cancel, github.merge confirmation flow), or when configuring delegation mode/tool_profile with delegat...
Ensures Claude verifies both local tests AND remote CI before claiming completion. Use BEFORE any completion claims, commits, or pull requests. Mandatory verification with evidence.
Release workflow for naruto-skills plugin. Use when user says "release", "发布", "push", "推送", "new version", "新版本", "bump version", "更新版本", or wants to publish changes to remote. Analyzes changes sinc...
Generate an ops/runbook spec from a tech spec with SLOs, alerts, dashboards, and rollback steps. Use when operational readiness must be defined.
Generate a migration plan from a tech spec with phased rollout, rollback, and validation. Use when schema or data changes require controlled execution.
Set up a production-ready Anchor workspace: program/client layout, env config, testing, and build hygiene. Use when starting new Anchor projects or re-baselining repos.
安全扫描器。检测 Claude Code 自定义 skills 中的潜在恶意代码。当用户提到"安全扫描"、"检测恶意代码"、"skill 安全"或需要扫描 skill 时使用。
Manage world permissions, namespaces, resource registration, and access control. Use when configuring world ownership, setting up authorization policies, or managing resource permissions.
Independent verification of task completion - eliminates self-attestation
Force verification before answering questions involving versions, dates, status, or "current" state. Prevents hallucinations at the REASONING level by checking assertions.yaml and WebSearch before forming belie...
Drops random fun facts, jokes, stories, or wild ideas tailored to tech wizards like you
Automatically activated when user asks how something works, wants to understand unfamiliar code, needs to explore a new codebase, or asks questions like "where is X implemented?", "how does Y work?", or "explai...
Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.
Write the test first, watch it fail, write minimal code to pass
Write code by first creating tests that define expected behavior. Use when implementing business logic, algorithms, utilities, or when the user provides test cases, mentions TDD, asks to write tests first, or w...
Write tests for Dojo models and systems using spawn_test_world, cheat codes, and assertions. Use when testing game logic, verifying state changes, or ensuring system correctness.
Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available browser tools, or when configuring browser-based documentation collection.
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional...
将零散灵感扩展为深度推文。当用户需要"扩展灵感"、"生成推文"、"构思内容"、"写作辅助"、"丰富想法"、"深化思考"或提供零散想法需要系统化表达时使用此skill。
Create viral X/Twitter posts based on the official X algorithm (Phoenix/Grok). Generates and improves posts optimized for maximum engagement. Use when (1) creating X posts for products, services, or information...
SEO intelligence engine for competitive analysis. Estimates Q*, P*, and T* signals, analyzes NavBoost and E-E-A-T factors, identifies ranking gaps, orchestrates audit workflows, and provides actionable SEO stra...
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format...
Run comprehensive codebase audit for gaps, deprecated code, TODOs, FIXMEs, architectural anti-patterns, type issues, and code smells. Use when user asks to audit code, find issues, check code quality, or identi...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。