ClawHub

Interviewer-Claw

v1.0.0

Conducts rigorous, structured interviews to stress-test a plan, design, or idea by walking every branch of the decision tree until reaching shared understand...

⭐ 0· 72·0 current·0 all-time
byChris Graffagnino@chris-graffagnino
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
The name/description (stress-test plans, generate spec-kit artifacts) matches the instructions and README. There are no unrelated binaries, environment variables, or external credentials requested.
ℹ
Instruction Scope
The runtime instructions allow the agent to read project artifacts (codebases, specs, spreadsheets) if the user points to them and to produce spec-kit artifacts via the `speckit` function. This is expected for a review/speccing tool, but it means the skill will access files you provide. There are no instructions to read system-wide config or secrets or to transmit data to third-party endpoints.
✓
Install Mechanism
No install spec or code is included; the skill is instruction-only (SKILL.md + references). Nothing is downloaded or written by an installer step by default.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. References to spec-kit and GitHub are informational; no credentialed access is requested.
✓
Persistence & Privilege
always is false and the skill does not request persistent platform privileges. It may write spec-kit artifacts when the user invokes `speckit` (expected behavior) but does not request to modify other skills or agent-wide settings.
Assessment
This skill appears coherent and focused: it will ask one question at a time, probe your plan, and (if you request) read project files you point it at and generate spec-kit artifacts. Before enabling file-reading or uploading project folders, confirm you want the assistant to access those files (do not upload secrets or unrelated private documents). The skill does not request credentials or contact external endpoints by default, but review any generated artifacts or file writes before accepting them. If you need stricter limits, avoid using the `review`/`speckit` functions or disable file-reading on your platform.

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

latestvk979456fn5zfx8qmvcmrnxnk7183e3hv

License

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

Comments