ClawHub

Help Center

v1.0.0

Build and run help centers with provider selection, migration playbooks, workflow mapping, content taxonomy, and support deflection metrics.

⭐ 0· 273·1 current·1 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 (help center planning, provider selection, migration playbooks, taxonomy, metrics) match the content of the SKILL.md and supporting docs. There are no unexpected required binaries, environment variables, or external services declared.
✓
Instruction Scope
Runtime instructions are limited to guiding conversations, creating/maintaining files under ~/help-center/, and providing checklists and templates. The SKILL.md explicitly states files are created only after user confirmation and that it does not send local files to third-party APIs or modify files outside ~/help-center/.
✓
Install Mechanism
There is no install spec and no code files — the skill is instruction-only. That minimizes disk-write and executable risk.
✓
Credentials
The skill declares no required environment variables, no credentials, and no config paths beyond the local ~/help-center/ workspace, which is proportionate for a planning/consulting skill.
✓
Persistence & Privilege
The skill is not marked always:true and does not request system-level persistence. It records a small local memory in ~/help-center/memory.md per its instructions, which is reasonable for its stated purpose.
Assessment
This skill appears to be a local planning and playbook helper and is internally consistent. Before installing, review and confirm the following: (1) the skill will create files only under ~/help-center/ — back up anything in that path you care about; (2) it claims to create files only after asking for confirmation — when first run, verify the prompt and deny file creation if you don't want it; (3) the skill is instruction-only (no code to inspect), but the source is listed as unknown — if you require provenance, verify the publisher or homepage; (4) the agent platform allows autonomous invocation by default—if you prefer to limit automatic runs, disable autonomous invocation for this skill in your agent settings. If you want extra caution, run the skill in a throwaway account or VM first to confirm behavior.

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

latestvk97396nvsm8acm7q38r2qv4pyd8255td

License

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

Runtime requirements

🛟 Clawdis
OSLinux · macOS · Windows

Comments