ClawHub

Verifier Skill Generator

v1.0.0

Use when a project needs one or more verifier skills for web, CLI, or API runtime checks that the Verify agent can discover automatically.

⭐ 0· 35·0 current·0 all-time
by@wimi321
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
The name/description match the SKILL.md: the skill's purpose is to inspect a project and generate verifier skill folders for web/CLI/API surfaces. There are no unexpected dependencies, binaries, or credentials declared.
ℹ
Instruction Scope
The runtime instructions direct the agent to 'inspect the project' and detect stacks, layouts, and tooling availability — which reasonably implies reading repository files and configs. The instructions do not tell the agent to read unrelated system files or exfiltrate data, but reviewing repo files is inherent to the stated purpose and should be expected.
✓
Install Mechanism
No install spec or code is included; this is instruction-only, so nothing will be written to disk by an installer as part of skill installation.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does ask generated verifiers to include 'setup, authentication, cleanup, and self-update behavior' — but that applies to generated artifacts, not this skill's own runtime requirements.
✓
Persistence & Privilege
always is false and there are no indications the skill modifies other skills or system-wide agent settings. The skill is user-invocable and can be invoked autonomously by the agent (platform default), which is expected for a generator.
Assessment
This skill is an instruction-only template for generating repository-specific verifier skills and appears internally consistent. Before installing or running it: (1) be prepared that the agent will scan your repository files and configs to detect stacks and tooling; (2) carefully review any verifier folders or code the skill generates (especially 'authentication' or 'self-update' code) before executing them or supplying secrets; and (3) if provenance matters to you, note the skill's source/homepage are unspecified—ask for author or repository details if you need stronger trust guarantees.

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

claude-codevk970yy8ngy2hvh9g908m747s4n842zhmextractedvk970yy8ngy2hvh9g908m747s4n842zhmlatestvk970yy8ngy2hvh9g908m747s4n842zhm

License

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

Comments