Menu
O SkillsMP coletou 56 skills de zeero/dotfiles. Abra uma skill para revisar a origem e os detalhes.
Mostrando 40 de 56 skills coletadas.
Use when launching a long-running CLI in the background (external review CLIs, builds, batch jobs) or deciding how to capture its output; when a subagent is stalled, its completion is overdue, or its completion notification arrives while the work it launched…
Idioma do texto original: japonês
Use when asking an external agent or subagent to review something or give a second opinion, applying review feedback, deciding whether to accept a finding, running two reviews at once, or before calling work "reviewed" and merging it. Triggers:…
Idioma do texto original: japonês
Moomoo API (ex-Futu) Python SDK reference. Use for stock prices, orders, positions, or OpenQuoteContext/OpenTradeContext usage.
Idioma do texto original: japonês
Common procedure and pitfalls for launching another coding agent's CLI (codex / claude / gemini) as a subprocess from the current session. Use before running `codex exec`, `claude -p`, or `gemini -p` — whether a review / second-opinion skill routes here, or…
Idioma do texto original: japonês
Reviews Python code for type safety, async patterns, error handling, and common mistakes. Use when reviewing .py files, checking type hints, async/await usage, or exception handling.
Idioma do texto original: inglês
user invoke only
Idioma do texto original: japonês
Reviews and improves existing Claude skill files (SKILL.md) against Anthropic's best practices. Use this skill whenever a user shares a SKILL.md or skill folder, asks to "review", "refine", "improve", "audit", or "check" a skill, reports that a skill isn't…
Idioma do texto original: inglês
user invoke only
Idioma do texto original: japonês
user invoke only
Idioma do texto original: japonês
user invoke only
Idioma do texto original: japonês
Extract lessons that make next time easier. Firing means invoking this skill now, mid-turn — naming it in the closing next-action list does not count as firing it. Fire when: (1) a reusable insight emerges at a work boundary — a bug workaround found, a gotcha…
Idioma do texto original: japonês
auto-memory に溜まった学びを永続度の高い層 — グローバル CLAUDE.md / rules / スキル / プロジェクト CLAUDE.md — へ蒸留・昇格し、 昇格済みエントリをメモリから除去する。
Idioma do texto original: japonês
Use when writing a pull request description, or when responding to review comments — including automated review bots. Triggers on PR作成, PR本文, レビュー指摘への対応, nits, bot レビュー, レビュー返信文案.
Idioma do texto original: japonês
user invoke only
Idioma do texto original: japonês
Official Claude Code reference for agent skills. Use this when configuring frontmatter or other settings for agent skills.
Idioma do texto original: japonês
Official Mermaid diagram syntax reference covering every diagram type (flowchart, sequence, class, state, ER, gantt, git graph, mindmap, and 24 more). Use whenever writing, editing, or debugging any Mermaid diagram, even if the user doesn't say "mermaid" and…
Idioma do texto original: japonês
A skill where the LLM manages the Wiki of an Obsidian Vault (memos). Always use this skill in situations such as: - 「WikiにXXを取り込んで」「ingestして」「このメモをWikiに追加して」「Wikiを更新して」 - 「Wikiで調べて」「Wikiを検索」「WikiでXXについて教えて」 - 「Wiki lint」「Wikiの健全チェック」「stale な refs を確認」「orphan…
Idioma do texto original: japonês
A skill for applying the defined coding rules to Kotlin coding. Always activate this skill and apply the rules when writing Kotlin code or when asked to modify .kt files.
Idioma do texto original: Vários idiomas
Generate self-contained HTML visual explanations for systems, code changes, plans, data, and technical concepts. Use for diagrams, architecture overviews, diff or plan reviews, project recaps, comparison tables, slide decks, and other visual explanations.
Idioma do texto original: inglês
Use this to consult the official Pi coding agent reference when investigating, designing, or implementing Pi — setup, configuration, providers/models, skills, extensions, packages, prompt templates, sessions, SDK, RPC, JSON event stream, and terminal setup.
Idioma do texto original: japonês
trigger is `visualize`
Idioma do texto original: japonês
Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl…
Idioma do texto original: inglês
user invoke only
Idioma do texto original: japonês
An orchestration skill that collects references from documentation URLs on the web and chains into skill creation (skill-creator). Always activate it for requests like 「URLからスキルを作って」「このドキュメントを元にスキル化したい」「firecrawlでリファレンスを集めてスキルを作って」.
Idioma do texto original: japonês
GitHub issue を sub-issue に分解し、worktree 分離した並行エージェントで実装、読み取り専用の検証ゲートを経て、コンフリクト検知とマージ順序決定まで行う並行開発オーケストレーション手順。/parallel-issues <issue番号 or タスク概要> で起動する。
Idioma do texto original: japonês
Raindrop.io REST API reference. Use for bookmarks (raindrops), collections, highlights, tags, filters, user, import/export/backups endpoints, OAuth authentication, or building Raindrop.io integrations/bots.
Idioma do texto original: inglês
Harvest un-distilled reusable knowledge from agent memory stores (Claude Code auto-memory, Serena memories) and promote it into the learning tiers (global CLAUDE.md / skill / <repo>/.learnings/), then dispose of the source entries to avoid dual management.…
Idioma do texto original: japonês
Conventions for the file format and structure of documents (Markdown, etc.). Always use this skill when creating, editing, or formatting Markdown files such as documents, READMEs, design docs, research notes, or procedure guides.
Idioma do texto original: japonês
Delegate small, well-scoped coding tasks to the local pi worker through Ollama. Use when Codex needs a secondary pass for lightweight implementation work such as fixing pyright, type-checker, linter, or warning output; writing focused tests to improve…
Idioma do texto original: inglês
A skill for designing Claude Code agent team configurations. Use it proactively in situations such as: - When agent teams or multi-agent setups come up - When you want multi-angle verification such as architecture review, domain-expert review, or testing -…
Idioma do texto original: japonês
Comprehensive official reference for Hermes Agent. Whenever the user asks about or requests building Hermes Agent deployment, configuration, or Slack integration, always activate this skill and read the appropriate file under references/.
Idioma do texto original: japonês
Writing standards for Japanese technical documents and book manuscripts. Use when writing or revising/rewriting chapters, drafts, articles, or explanatory text for Japanese technical books.
Idioma do texto original: japonês
Uses Jules (an asynchronous AI agent) to automate and manage large-scale codebase changes, test additions, refactoring, and dependency updates. Always use this skill when the user mentions 「大規模な修正を依頼したい」「時間がかかる作業をバックグラウンドでやってほしい」「Julesを使って」, or when a…
Idioma do texto original: japonês
Automatically organizes an Obsidian vault. Use for requests such as "Obsidian整理", "vault整理", "ダッシュボード整理", "inbox整理", "メモ整理".
Idioma do texto original: japonês
A skill that delegates code review and fixes to a subagent. Use when instructed with 「セルフコードレビューして」「サブエージェントにレビューさせて」.
Idioma do texto original: japonês
A skill for applying the defined coding rules to Swift coding. Always activate this skill and apply the rules when writing Swift code or when asked to modify .swift files.
Idioma do texto original: japonês
A TDD-style procedure for safely carrying out refactoring. Always propose this procedure before starting code refactoring, structural improvement, internal cleanup, renaming, or deduplication. Applies to any change that improves internals without altering…
Idioma do texto original: japonês
user invoke only
Idioma do texto original: japonês
user invoke only
Idioma do texto original: japonês
user invoke only
Idioma do texto original: japonês