ClawHub

Chapter Skeleton

v1.0.0

Build a retrieval-informed chapter skeleton (`outline/chapter_skeleton.yml`) from taxonomy/core scope before stable H3 decomposition. **Trigger**: chapter sk...

⭐ 0· 114·1 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 (chapter skeleton from taxonomy) match the actual behavior: scripts/run.py reads outline/taxonomy.yml and optional GOAL.md and emits outline/chapter_skeleton.yml. Declared required binaries (python/python3) are appropriate and no unrelated credentials or system paths are requested.
✓
Instruction Scope
SKILL.md restricts actions to reading local inputs (references/overview.md, outline/taxonomy.yml, GOAL.md) and writing the specified output. The included run.py and tooling are consistent with those instructions and do not perform network calls or access unrelated files. It documents guardrails (no prose, chapter-level only).
✓
Install Mechanism
No install spec is provided (instruction-only). Code files are bundled and run locally via python; there are no downloads or external installers. This is low-risk for install mechanism.
✓
Credentials
The skill declares no required environment variables, no credentials, and the code does not read environment secrets or external config beyond workspace files. File reads/writes are limited to workspace inputs/outputs.
✓
Persistence & Privilege
Flags: always=false and default autonomous invocation allowed (normal). The skill does not request permanent platform presence, modify other skills, or access other skills' configs.
Assessment
This skill appears coherent and limited to generating outline/chapter_skeleton.yml from a local taxonomy and optional GOAL.md. Before running, inspect scripts/run.py and the tooling files (already included) if you want to verify behavior; run it in a workspace you control. Note it will read and write files under the provided workspace path (it also backs up/atomically writes files). No network access or credentials are required. If you need stronger assurance, run the script in a sandboxed test workspace first.

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

latestvk9722eyshq2be4nh2mrs2ga7m9836v07

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