ClawHub

Context Driven Development

v1.0.0

Treat project context as a managed artifact alongside code. Use structured context documents (product.md, tech-stack.md, workflow.md) to enable consistent AI interactions and team alignment. Essential for projects using AI-assisted development.

⭐ 0· 1.6k·15 current·17 all-time
by@wpank
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 match the actual contents: templates and prose to create product.md, tech-stack.md, workflow.md, and tracks.md. There are no unrelated binaries, credentials, or config paths requested.
✓
Instruction Scope
SKILL.md instructs the agent to read repository metadata (package.json, requirements.txt, go.mod, README, git history) and to create/maintain context files — these actions fit the stated purpose of extracting and managing project context. No instructions reference external endpoints or ask the agent to collect unrelated secrets or system-wide data.
✓
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute. README suggests manual copy and an npx-based install command, but there is no automated download/extract step in the skill metadata itself.
✓
Credentials
No environment variables, credentials, or config paths are declared or required. The documents' guidance to inspect project files is proportional to the stated goal of building project context.
✓
Persistence & Privilege
always:false and model invocation is default; the skill does not request persistent system-wide privileges or modification of other skills' configurations.
Assessment
This skill is a documentation/workflow template and appears internally consistent. Before installing: (1) preview the SKILL.md and template files (they're included) to confirm you like the formats; (2) be aware the agent will read repository files (package manifests, README, git history) to infer context — grant it only to repos you trust; (3) if you plan to run any installation commands from the README (e.g., npx copy commands), inspect those commands first — the skill metadata itself does not auto-download or run external code. If you need stronger guarantees, install locally and inspect templates before enabling autonomous invocation.

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

latestvk972f9ajestc9ga04vzmjw89mh80x7rf

License

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

Comments