ClawHub

Team Role Launchkit

v1.0.0

Launch clone-like multi-agent workflows using explicit role prompts (researcher, builder, editor), strict handoff contracts, and shared behavior files for co...

⭐ 0· 18·0 current·0 all-time
byChristopher Wheeler@cwheeler67
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, and included files (handoff contract and role prompts) align with a multi-agent orchestration helper. There are no unrelated environment variables, binaries, or external integrations requested.
ℹ
Instruction Scope
SKILL.md and the referenced prompt files confine behavior to role definitions, handoff contracts, and operator review. The only operational directive with potential persistence is the line 'Capture durable outcomes in memory' — otherwise instructions do not access files, credentials, or external endpoints. This is within scope but you should be aware it encourages storing outputs in agent memory.
✓
Install Mechanism
No install spec or code files — instruction-only. No downloads, package installs, or extracted archives are present.
✓
Credentials
The skill declares no required env vars, credentials, or config paths. Nothing is requesting secrets or access beyond what the platform already provides.
ℹ
Persistence & Privilege
always is false and the skill is not force-included. However the instructions explicitly recommend promoting outcomes to durable memory; if your agent platform persists memory, that could store user data long-term. Consider whether you want the agent to write to memory and whether autonomous invocation should be limited for this workflow.
Assessment
This is an instruction-only template for coordinating Researcher/Builder/Editor roles and appears internally consistent. It does not request credentials, install software, or call external endpoints. Things to consider before installing: (1) the skill suggests promoting results to durable memory — if that concerns you, disable memory writes or review what gets saved; (2) the skill allows autonomous invocation by default — if you prefer manual control, restrict autonomous runs; (3) ensure any external/public actions are explicitly approved by the operator as the SKILL.md recommends. If you want a deeper check, request the author reveal any runtime hooks or platform-specific memory calls the skill will use.

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

latestvk97bc4bs7w0vvqvfynj3z249gn850g93

License

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

Comments