ClawHub

Vibe Coding Blueprint

v1.0.0

A document-driven AI programming methodology. Use when: (1) starting a new code project, (2) adding a new feature module, (3) debugging a bug, (4) code becom...

⭐ 0· 23·0 current·0 all-time
by@xiaoxiangxie
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 shipped documents all describe a document-driven development methodology. The skill does not declare unrelated binaries, env vars, or installs — everything requested (reading/writing project docs, producing architecture and header files, running verifications) is consistent with a coding workflow.
ℹ
Instruction Scope
SKILL.md instructs the agent to read and update repository documentation (docs/*), create architecture and folder/file headers, and run verification steps (unit tests, demos, manual tests). That behavior is appropriate for a coding methodology but does mean the agent will read and modify workspace files and run project tests — users should expect and approve that level of access.
✓
Install Mechanism
No install specification or external downloads are present (instruction-only). Nothing is written to disk by an installer; the skill relies on editing the existing project workspace, which is expected.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. There are no requests for secrets or unrelated service tokens in the files or instructions.
✓
Persistence & Privilege
always:false and no special privileges are requested. The skill does not attempt to modify other skills or global agent settings; its scope is limited to guiding workspace/document edits.
Assessment
This skill is an instruction-only methodology for AI-assisted development and appears internally consistent. Before installing or using it, ensure the agent is limited to the intended project workspace (use a branch or sandbox), review and approve the AI-generated technical plans before code changes, and run CI/tests yourself or in a controlled environment. Because the agent will read and modify repository files and run verifications, avoid granting it access to secrets or production credentials, and keep human-in-the-loop control for any changes that affect security or architecture.

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

latestvk976z0g5ehxrxf7knphv8273ch84hxar

License

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

Comments