ClawHub

拆书素材提炼

v0.1.0

Book-to-writing-material skill for Chinese content creation. Use when Codex needs to break down a book, chapter, excerpt, reading note, or book link into reu...

⭐ 0· 12·0 current·0 all-time
by@cellinlab
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
Name/description match the actual content: the skill is an instruction-only workflow for extracting viewpoints, stories, golden-line rewrites, and a draft for a downstream `deep-writer`. It requires no binaries, env vars, or external services, which is proportional to the stated goal.
✓
Instruction Scope
SKILL.md and supporting references define a confined three-round workflow that operates on user-supplied book names, excerpts, notes, or links. Instructions reference only local resource files bundled with the skill (references/*.md, assets/*.md) and do not instruct the agent to read unrelated system files, access secrets, or send data to external endpoints.
✓
Install Mechanism
No install spec and no code files — the skill is instruction-only. This is the lowest-risk install profile and consistent with the skill's purpose.
✓
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. There are no surprise credential requests in the instructions.
✓
Persistence & Privilege
Metadata flags show always:false (not force-included) and model invocation allowed (the platform default). The skill does not request persistent system privileges or modify other skills' configs.
Assessment
This skill appears coherent and low-risk as an instruction-only tool. Before installing, consider: (1) Do not paste full copyrighted books unless you have the right to do so — prefer excerpts or your own notes. (2) The skill hands output to a placeholder `deep-writer` workflow; verify any downstream skill or system that receives the output (where data is sent/stored). (3) Avoid submitting sensitive personal data in the materials you provide. (4) If you plan to integrate this into a multi-skill agent, confirm the other skills (e.g., `deep-writer`) are trustworthy since this skill's output may be forwarded to them.

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

latestvk970p83e25h3nq4446rh62pvwx84hnth

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments