Yuanyuan Blueprint Workshop
v1.0.0Guide users through a 5-step workshop to convert tacit know-how into a testable Agent Blueprint with scenario, SOP, dependencies, and skill sourcing.
⭐ 0· 158·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name, description, and included templates/references match the stated goal of running a 5-step workshop to produce an agent blueprint. There are no unrelated requirements (no env vars, no binaries, no install steps) that would be inconsistent with a discovery/workshop skill.
Instruction Scope
SKILL.md stays within the workshop scope (scenario discovery → SOP extraction → dependency mapping → blueprint → sourcing). It explicitly tells the agent to prefer local reuse, search ClawHub, vet/scan, then install or author missing skills. This is appropriate for a sourcing plan, but it does grant the agent procedural permission to search and potentially install other skills — the skill also allows saving files internally (but requires delivering the blueprint in chat). No instructions reference reading unrelated system files, environment variables, or external endpoints outside the platform.
Install Mechanism
There is no install spec and no code files that would be downloaded or executed; this is instruction-only, which minimizes written-to-disk risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. It does not attempt to access or request secrets; this is proportionate to its discovery/workshop purpose.
Persistence & Privilege
always:false (default) and no actions that modify other skills or system-wide configs are present. The only persistence-related action is an allowance to 'save files internally if useful' — this is reasonable for archiving session artifacts but users should confirm what internal storage is used and how long artifacts are retained.
Scan Findings in Context
[no-findings] expected: The registry scan found no code patterns because this is an instruction-only skill (no install, no binaries, no code files). Absence of findings here is expected but does not replace runtime vigilance.
Assessment
This skill is internally consistent and low-risk: it only contains workshop instructions and templates, asks for no credentials, and doesn't install or download code. Before installing or enabling it, confirm platform controls: (1) that the agent will not auto-install other skills without your explicit consent when following the 'search/vet/install' step, (2) how and where any 'saved internal files' are stored and who can access them, and (3) that the delivered blueprint will appear fully in chat as promised (do not rely solely on hidden files). If you plan to let the agent act on its own to install skills from ClawHub, require manual approval or review of any candidate skills first.Like a lobster shell, security has layers — review code before you run it.
latestvk97a911cydzq6drqv5cwe77zz9835zy0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.