Book Writing

v1.0.0

Plan, draft, and revise complete books with chapter architecture, voice consistency, and finish-ready revision workflows.

1· 1.8k·21 current·22 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name and description (planning, drafting, revising books) match the actual content and requirements. The skill requests no binaries, no environment variables, and no external services — all of which are proportionate for a local drafting/revision workflow.
Instruction Scope
SKILL.md and the supporting docs explicitly limit file reads/writes to the ~/book-writing/ directory, instruct the agent to run a local setup flow, and do not direct data to external endpoints or ask the agent to read unrelated system files. The setup prompts are limited to book metadata and activation preferences.
Install Mechanism
There is no install spec and no code files — this is instruction-only. That produces a minimal footprint: nothing is downloaded or installed by the skill itself.
Credentials
The skill requests no environment variables, no credentials, and explicitly states it will not store secrets or send manuscript data externally. The local-memory approach (~/book-writing/) is appropriate for the stated goals.
Persistence & Privilege
The skill persists state locally by creating and updating ~/book-writing/memory.md and related files when the user opts into setup. always:false (default) and normal autonomous invocation apply. This local persistence is expected for a long-form writing workflow, but users should be aware files are created in their home directory.
Assessment
This skill appears coherent and low-risk, but check a few things before enabling it: confirm you are okay with the skill creating and updating ~/book-writing/ files (memory.md, chapters/, revisions/); do not put passwords or secrets into the memory files; if you prefer no persistence, decline the setup prompt (the skill will continue to help without creating memory); back up or version-control manuscripts yourself if needed; verify the skill source/homepage if you want an update/trust provenance; and be cautious if you later install related skills — review their requested permissions and env vars before enabling them.

Like a lobster shell, security has layers — review code before you run it.

latestvk97668wwmky8vhmj7xbmkjnw9n81zc3f

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📚 Clawdis
OSLinux · macOS · Windows

Comments