ClawHub

Prompt Library Manager

v1.1.0

Curated prompt template library for OpenClaw agents. Store, search, version, tag, and reuse prompt templates across sessions and agents. Use when asked to "s...

⭐ 0· 103·0 current·0 all-time
by@stevojarvisai-star
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name/description (prompt template library) align with the provided CLI and code. The script manages prompts, searching, versioning, import/export and stores them under the user's workspace—capabilities requested are proportionate.
✓
Instruction Scope
SKILL.md instructs only local operations (add/search/list/use/import/export) and references the local storage path (~/.openclaw/workspace/memory/prompt-library.json). The only file reads occur when the user supplies --from-file or import files, which is expected. No instructions direct data to external endpoints.
✓
Install Mechanism
No install spec (instruction-only with an included script). No external packages or remote downloads are required by the manifest.
✓
Credentials
The skill does not require environment variables, credentials, or config paths beyond writing to a workspace directory. No secrets are requested or declared.
✓
Persistence & Privilege
always:false (not force-installed) and default model invocation allowed. The skill writes only to its own workspace path and does not request elevated system privileges.
Assessment
This skill appears to be a local prompt library that reads/writes a JSON file under ~/.openclaw/workspace/memory/prompt-library.json and can import templates from files you provide. Before installing or using it: 1) Inspect the full script for any network calls (none are apparent in the shown imports, but the file was truncated in the listing). 2) Avoid storing secrets or API keys inside prompt templates (templates may be exported or copied). 3) Be aware the tool can read files you point at with --from-file or --import, so only import trusted files. 4) If you want to prevent autonomous invocation, disable model invocation for the skill in your agent settings; by default the agent may call skills autonomously. If you want, I can scan the remainder of scripts/prompt-library.py (the truncated portion) to raise or lower my confidence.

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

latestvk97ay8990mwsb3dsw5ycj5nrnh83wa68

License

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

Comments