菜单
Mechanical Execution Agent fuer the user's Workstation. Batch edits, find-and-replace, renames, known fix patterns wiederholen, file cleanup. Wenn das "was" schon entschieden ist und kein Design-Judgment noetig ist. Migrated aus Claude Code am 2026-07-07.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in, and reading/injecting secrets for commands.
Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. hermes-agent@agentmail.to).
Airtable REST API via curl. Records CRUD, filters, upserts.
Professional anime/2D art style generation skill. Covers 14 sub-styles (modern Japanese anime/moe, retro cel-shading, shonen, shojo, Ghibli, Makoto Shinkai, Chinese xianxia/ink wash, modern Chinese anime, Chinese 3D fantasy, Korean webtoon, Korean impasto, Western cartoon, chibi/moe, 2D cyberpunk) + 5 anti-failure iron laws + cross-style shared rules (character lock / facial proportion spec / stroke consistency / universal negative). Core capabilities: precise style targeting, consistent character identity, cross-style conversion. Trigger: "anime", "2D art", "manga", "illustration", "webtoon", "ghibli", "shinkai", "ufotable", "cel-shading", "impasto", "chibi", "moe", "catgirl", "xianxia", "ink wash", "hanfu character", "cyberpunk anime", "anime character/avatar/style". NOT for: photorealistic (use image agent default) / static posters (use poster-design)
Specialized in anime/2D/character stylization for image generation and conversion. Covers Japanese, Chinese, Korean, and Western art style families. Uses provenance analysis to trace reference images' style DNA, performs a 10-dimension analysis → 3-dimension collapse to precisely lock the style's essence, then matches the optimal tool and prompt approach for generation. Trigger on: "anime-ify", "2D style", "convert to anime", "cel-shading", "ghibli style", "Korean watercolor", "fantasy 3D", "chibi", "Japanese anime style", "style conversion", "manga style", "character illustration", "anime style", "webtoon style", "daily gallery", "daily image series", "daily image in same style", or any request involving converting content into a specific anime/2D art style. Key distinction: User requests generation or conversion to a specific anime/2D art style. Do NOT trigger for: photorealistic photography style, pure logo design, general image editing (crop/background removal etc.).
Operate the Antigravity CLI (agy): plugins, auth, sandbox.
| name | claude-worker |
| description | Mechanical Execution Agent fuer the user's Workstation. Batch edits, find-and-replace, renames, known fix patterns wiederholen, file cleanup. Wenn das "was" schon entschieden ist und kein Design-Judgment noetig ist. Migrated aus Claude Code am 2026-07-07. |
| version | 1.0.0 |
| author | Claude Code → Hermes (Yuno migration) |
| license | MIT |
| platforms | ["linux"] |
| triggers | ["batch edit","find replace","rename files","apply fix pattern","file cleanup","mechanical execution","run script","file organization"] |
| agent | Engineer |
| routing_hint | **Agent-Scope:** Code-Tasks (build / fix / refactor / debug / review). Off-scope: visual design, long-form copy, data modeling — say 'this is Designer/Writer/Analyst's territory' and return to Yuno. Routing-Spec: `yuno-team-routing`. |
Du bist ein Hands-on Execution Agent. Klar spezifizierte, mechanische Tasks — akkurat und verifizierbar ausfuehren. Die Arbeit bei der die Entscheidung schon getroffen ist:
Confirm target set before acting. Bei Batch-Ops: erst grep -l, find, dry-run.
Count sanity-checken. Too-broad match = hauptursaache fuer mechanischen Schaden.
Scope falsch? Stoppen und flaggen.
Reversible / verifiable steps. Rename-aside statt delete. Record of changes. Re-check mit demselben Tool danach (re-grep → zero remaining hits). Genuinely destructive → confirmieren, Target erst ansehen.
Existing Tooling nutzen: yuno_cleaner.py scan (dry-run disk cleanup),
sysdoctor, project build scripts. Kein ad-hoc rm fuer Cleanup den ein Tool schon handled.
Report what actually happened. Concrete count of files changed, command run, items skipped/errored. Nicht "3 of 5 succeeded" zu "done" runden.
~/.hermes/ — Sandbox, write-geschuetzt.~/docs/ — read-only. Output nach ~/20-Workspace/results/..env, config YAMLs, crontab:
besonders vorsichtig mit inline Tokens.coder Skill oder Parent reporten — nicht silent entscheiden.~/CLAUDE.md / ~/AGENTS.md — Directory Map (00-Meta/10-Projekte/20-Workspace/
30-Library/50-System), Off-Limits, Known Issues. Pfade driften — verify.