tomevault-io/skills-registry - 第 92 页

terraform

Use when writing Terraform — AWS modules, resources, variables, outputs, remote state — even when the user just says 'provision this infra' or 'add an S3 bucket' without naming Terraform.

原文语言：英语

new-branch

Create a branch following the project's GitFlow Lite model Use when this capability is needed.

原文语言：英语

process-issues

Resolve all open GitHub issues. Each issue becomes exactly one shipped PR. Trigger when user says "process issues", "work through issues", "resolve issues", "handle open issues", "fix all issues", or asks to resolve GitHub issues end-to-end. Use when this…

原文语言：英语

ai-code-review

Code review rigoroso de codigo gerado por IA, explicado em linguagem simples para nao-desenvolvedores (vibe coders). Cobre seguranca, bugs, arquitetura, performance, tipagem, testes, manutenibilidade e escalabilidade, com priorizacao por risco, antes/depois e…

原文语言：葡萄牙语

flutter-overflow-guard

Previne, diagnostica e prova ausencia de overflow de layout em Flutter/Dart - barras listradas de RenderFlex e seus primos (unbounded constraints, form empurrado pelo teclado, texto que nao cabe). Use ao construir, revisar ou debugar UI Flutter com Row,…

原文语言：葡萄牙语

flutter-pro-polish

>- Use when this capability is needed.

原文语言：葡萄牙语

git-workflow-standards

Padroes de fluxo de trabalho Git para qualquer time/host (GitHub/GitLab/Bitbucket/Azure DevOps) — convencao de nomes de branch (feature/fix/hotfix/chore), Conventional Commits no formato tipo(escopo) descricao, e babysitting de PR (monitorar CI, corrigir…

原文语言：葡萄牙语

openseo-release-notes

Cut an OpenSEO release — bump the version, draft user-facing release notes from commits since the last tag, run a review + subagent-verification pass, and open a "release: vX.X.X" PR. Use when the user asks to prepare a release, bump the version, or write…

原文语言：英语

ce-code-review

Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. In interactive mode it applies safe, verified fixes and commits them when the working tree is clean (it never pushes); in mode:agent it reports only and…

原文语言：英语

claude-only-skill

Use when working with a skill restricted to Claude Code only

原文语言：英语

ci-cd-patterns

>- Use when this capability is needed.

原文语言：英语

jest-patterns

>- Use when this capability is needed.

原文语言：英语

kubernetes

>- Use when this capability is needed.

原文语言：英语

pytest-patterns

Pytest testing patterns, anti-patterns, and quality rules Use when this capability is needed.

原文语言：英语

templates

Document template collection; read when creating docs; includes all KB templates and plan file templates Use when this capability is needed.

原文语言：英语

ui-ux-pro-max

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance,…

原文语言：英语

rpa-gen-rules

> Use when this capability is needed.

原文语言：英语

voltaire

Build Ethereum applications with typed errors, composable workflows, and testable code using Effect.ts. Use when this capability is needed.

原文语言：英语

gpt-image-2-gen

GPT Image 2 AI image generation via EvoLink API. Supports text-to-image, image-to-image editing, batch generation. Multiple sizes (ratio & pixel), resolutions (1K/2K/4K), quality levels (low/medium/high). Works with OpenClaw, Claude Code, OpenCode, Cursor.…

原文语言：英语

contract-review

Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents. Identifies unfavorable terms, suggests redlines, and compares to market standards. Use for contract analysis, due diligence, or negotiation prep. Use when this capability is…

原文语言：英语

legal-redline-tools

You are a contract review assistant that analyzes legal agreements and produces structured redlines using legal-redline-tools. Use when this capability is needed.

原文语言：英语

add-convention

Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY…

原文语言：英语

llava-onevision2-consistency

Bilingual guide for running and interpreting LLaVA-OneVision2 HF vs Megatron consistency checks across TP and PP settings Use when this capability is needed.

原文语言：多语言混合

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…

原文语言：英语

experiment-iterative-coder

Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to…

原文语言：英语

implement-uutils-command

> Use when this capability is needed.

原文语言：英语

profile-shuck-script

Profile shuck scripts and large-corpus fixtures, especially requests to profile a corpus script/fixture, reprofile after a shuck performance change, or produce a hotspot table from a samply profile. Use when Codex needs to run the shuck large-corpus profiling…

原文语言：英语

search

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'. Use when…

原文语言：英语

stripe-best-practices

Best practices for building a Stripe integrations Use when this capability is needed.

原文语言：英语

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include…

原文语言：英语

building-native-ui

Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs. Use when this capability is needed.

原文语言：英语

upgrade-validator

Upgrades the npm `validator` dependency and syncs express-validator chain types, implementations, options, and `declarations/validator.d.ts` with validator.js releases. Express-validator intentionally pins `validator` to patch-only semver (see PR

原文语言：英语

plan-decompose

> Use when this capability is needed.

原文语言：英语

subagent-artifact

Validate, diagnose, and understand subagent definitions (agents/*.md) — frontmatter format, delegation model, and vendor support across Claude Code, Cursor, and Codex. Use when this capability is needed.

原文语言：英语

terraform-backend-aws

Create an S3 + DynamoDB Terraform backend on AWS — guided setup with bootstrap, apply, and state migration workflow. Use when this capability is needed.

原文语言：英语

ezorm-write-yaml-mysql

Write ezorm YAML schema files for this repo (mysql/mysqlr). Prefer mysqlr unless the user explicitly asks for mysql. Output YAML only (no Go code). Use when this capability is needed.

原文语言：英语

create-audit

Create a new audit module for the check-ai scanner. Use this skill when the user wants to add a new audit section that checks for specific files, directories, or patterns in a repository. The skill generates a properly structured .mjs file in src/audits/ that…

原文语言：英语

capture-usage4claude-screenshots

Automate Usage4Claude interface screenshots with CleanShot X on macOS. Use when Codex needs to capture localized Usage4Claude menu-bar popover screenshots, switch Usage4Claude display/language settings, save files such as detail.claude.en@2x.png, or…

原文语言：英语

forge-graphql-design

GraphQL schema design. Nullable defaults, connections (cursor pagination via Relay spec), errors as data not throws, DataLoader for N+1, persisted queries for caching, schema versioning via deprecation, no overfetch via fragments. Contains paste-ready schema…

原文语言：英语

forge-mcp-server

Designing an MCP server LLM agents actually use well. Transport choice (stdio vs HTTP streaming), capability scoping, structured error responses the model can recover from, tool count limits, telemetry, auth, versioning. Contains ready-to-paste stdio server…

原文语言：英语