ClawHub

Chapter Lead Writer

v1.0.0

Write H2 chapter lead blocks (`sections/S<sec_id>_lead.md`) that preview the chapter's comparison lens and connect its H3 subsections, without adding new fac...

⭐ 0· 86·1 current·1 all-time
by@willoscar
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, required inputs (outline files, chapter briefs, citations), and the included Python scripts/tooling are consistent with a document-generation writer skill. The only declared runtime dependency is python/python3, which is appropriate for bundled .py scripts. There are no unrelated environment variables, credentials, or config paths requested.
ℹ
Instruction Scope
SKILL.md explicitly instructs the agent to read the listed repository reference files and to execute scripts/run.py in compatibility mode to produce lead files; it also specifies citation scoping rules and 'Network: none'. This is coherent for the skill's purpose. Caveat: runtime behavior depends on executing the bundled Python script/tooling, which can perform arbitrary filesystem and process actions. The SKILL.md lists the intended inputs/outputs, but you should review scripts/run.py/tooling before running to confirm there are no unexpected file reads/writes or network calls.
✓
Install Mechanism
No install spec is provided (instruction-only install), so nothing is downloaded or installed automatically. The package includes Python scripts and modules that are executed directly; that is proportionate and expected for this kind of skill.
✓
Credentials
The skill requests no environment variables or credentials and only requires a Python binary. This is proportionate for a local document-generation utility that operates on workspace files and local citation assets.
✓
Persistence & Privilege
Skill is not forced-always-on (always: false) and uses the normal autonomous-invocation default. It does not declare modifications to other skills or system-wide settings. It will write output files into the workspace (sections/S<sec_id>_lead.md) as intended.
Assessment
This package appears coherent with its stated purpose, but it executes bundled Python code, so: 1) Inspect scripts/run.py and the tooling/*.py files before running to confirm there are no unexpected network calls, telemetry, or access to unrelated system paths. 2) Run the skill in an isolated or disposable workspace (not on a machine holding secrets) so you can review all files it writes (expected outputs are sections/S<sec_id>_lead.md and logs/reports). 3) Ensure the required inputs (outline/outline.yml, outline/chapter_briefs.jsonl, citations/ref.bib) exist and that citation keys are correct. 4) If you do not want code execution, you can use the references and assets in the repo as a prompt-only guide and draft leads without running scripts. If you want extra assurance, share scripts/run.py for a targeted review of network and file I/O behavior.

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

latestvk97f7yb9mn95yzbw0jw59ejkp5837q87

License

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

Runtime requirements

Any binpython3, python

Comments