一键导入
calibre
Use when the user wants to search, retrieve, send, add, update, sync, export, convert, or clean books from the managed Calibre library runtime.
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。
菜单
Use when the user wants to search, retrieve, send, add, update, sync, export, convert, or clean books from the managed Calibre library runtime.
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
Single-agent paper review workflow.
Comprehensive guide and reference for the Antigravity Customization System. Use to explain how customizations work, their loading priority, discovery mechanisms, and to guide the creation of skills, rules, plugins, hooks, and MCP servers.
Provides a comprehensive guide, quick reference, and sitemap for Google Antigravity (AGY), including the Antigravity CLI (agy), Antigravity 2.0, Antigravity IDE, Python SDK, slash commands, keybindings, and customizations (skills, rules, MCP, sidecars). Activate this skill when the user asks questions about how to use, configure, or customize Antigravity, AGY, the agy CLI, the Antigravity IDE, or Antigravity 2.0.
Guidelines for interacting with GitHub and request permissions from the user when commands fail due to restrictions in the agent environment.
ALWAYS use this skill when the user asks to send, get, retrieve, find, share, add, or search for a paper. This skill manages the user's Zotero library with 10,000+ papers and can retrieve PDFs, create share links, add new papers, and search. Prefer this over getscipapers for any request involving sending/getting/finding papers.
Use when the user asks to send, get, retrieve, find, share, add, or search for a paper. This is the live OpenClaw Zotero workflow adapted for Codex and should take priority over external paper retrieval.
| name | calibre |
| description | Use when the user wants to search, retrieve, send, add, update, sync, export, convert, or clean books from the managed Calibre library runtime. |
| metadata | {"short-description":"Calibre library management via managed runtime"} |
This skill is installed as an OpenCode-native SKILL.md. For runtime-backed
helpers, prefer the shared ai-agents-skills runtime root and the
AAS_RUNTIME_ROOT override instead of assuming a Codex-specific runtime
path.
On native Windows, use the managed Windows runner and the native runtime command target. Set $runtime to the installed runtime root. Multi-agent installs usually use %LOCALAPPDATA%\ai-agents-skills\runtime. Then run:
$runtime = if ($env:AAS_RUNTIME_ROOT) { $env:AAS_RUNTIME_ROOT } else { "$env:LOCALAPPDATA\ai-agents-skills\runtime" }
& "$runtime\run_skill.bat" "skills/calibre/run_cal.bat" <args>
POSIX examples below use run_skill.sh and .sh command targets; use the Windows command target above on native Windows.
This uses the managed ai-agents-skills runtime copy of the Calibre workflow.
zotero for generic "find/get/share/download a paper, DOI, ISBN, or book" requests; the top-level routing rule handles those with Zotero first.getscipapers-requester only after the user explicitly says not to check/use
the library or confirms outside retrieval after the library-first result is
reported. Return to calibre only if the resulting file should be added to
the ebook library.$AAS_RUNTIME_WORKSPACE/skills/calibre/Use the managed runtime runner rather than invoking run_cal.sh directly.
Shared runner:
bash "$AAS_RUNTIME_ROOT/run_skill.sh"Do not assume Calibre settings, library, or metadata.db locations. Before
library-changing work, run or rely on a profile-aware read-only audit from the
canonical installer:
cd ~/ai-agents-skills && make library-profile-audit ARGS="--profile library --json"
Discovery only lists candidates. It must distinguish authoritative Calibre
libraries from runtime caches before any add, update, remove, convert, or sync
operation. If no authoritative local Calibre database is found, mark the
profile local-db-missing; do not create a library and do not treat cache DBs
as writable libraries.
Supported system profiles:
linux-localwindows-mounted for Linux-side inspection of /windows/Users/...windows-native for native Windows executionCalibre candidate validation must check metadata.db, quick-check status, book
count, author/book file-tree consistency, canonical real path, symlink/mount or
cloud-backed classification, and runtime-cache roots. Runtime caches are never
mutation-authoritative even when their book count matches the real library.
Writes prefer a detected calibredb or calibredb.exe backend with an
explicit library path. Guarded direct SQLite is fallback only and requires
backup, lock, selected library root, and explicit warning. Windows-mounted or
cloud-backed Calibre libraries are read-only from Linux unless the profile
explicitly opts in after dry-run review.
Use functions.exec_command.
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh search "<query>" [--format epub] [--tag fiction] [--limit 50] [--series "Series Name"]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh get "<query>" [--format pdf] [--send "telegram:CHAT_ID"]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh get --id 42 [--send "zulip:Research:books"]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh get "ring" --index 0 [--send "telegram:CHAT_ID"]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh add /path/book.epub [--isbn 9780140449136] [--title "X" --author "Y"] [--dry-run]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh update --id 42 --title "X" --author "Y" --tags "a,b" --year 1965 --publisher "P" [--series "S" --series-index 1 --isbn 9780441013593]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh add-tag --id 42 --tag "to-read"
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh remove-tag --id 42 --tag "to-read"
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh list-shelves [--tags|--series|--publishers]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh sync [--force] [--progress]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh remove "query" [--dry-run]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh remove --id 42 [--dry-run]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh convert --id 42 --to epub [--from pdf]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh export --id 42 [--format bibtex]
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh doctor
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/calibre/run_cal.sh clean
get returns multiple matches, show candidates and ask the user to pick instead of guessing.--index only after showing candidates and receiving the user's selected
index.remove.add, update, add-tag,
remove-tag, remove, convert, sync, clean, get --send, or share),
run the relevant dry-run/preview/search first when available, state the exact
book/library/tag/channel to be affected, and get explicit confirmation unless
the user's latest request already approved that exact action.ebook-convert are present; use doctor when conversion health matters.--send uses channel:target syntax such as telegram:CHAT_ID, zulip:Stream:topic, googlechat:SPACE, or whatsapp:PHONE.add --isbn enriches metadata from Open Library before the library write.update --tags replaces the full tag set; use add-tag and remove-tag for incremental changes.sync at the start of a session if the library may have changed from Calibre desktop or another device.sync --progress when pulling metadata.db may take time. Progress is
emitted as JSON lines on stderr so stdout remains the final JSON result.metadata.db as authoritative.calibredb/calibredb.exe backend for authoritative
library writes; direct SQLite is a guarded fallback only.metadata.db is pushed back to Drive and the local cache is refreshed.metadata.db from concurrent write conflicts.clean removes staged files older than 24 hours.