ClawHub

Self-Critique

v1.0.0

Improve output quality through structured self-review before finalizing. Based on Constitutional AI and self-reflection research, this skill creates a feedba...

⭐ 0· 42·0 current·0 all-time
bySimon@simoncatbot
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 and description match the content of SKILL.md: a structured self-critique workflow for improving outputs. There are no declared env vars, binaries, or installs that would be disproportionate to a review workflow.
ℹ
Instruction Scope
SKILL.md contains only procedural guidance and detailed examples showing how to generate, critique, and revise text/code. It does not instruct the agent to read system files, access environment variables, or call external endpoints. Note: some examples reference placeholders like DB_URL or phone numbers and point out security criteria (e.g., 'secrets not hardcoded'); these are illustrative and not instructions to access credentials.
✓
Install Mechanism
No install spec or code files to write or execute; instruction-only skill = minimal disk/system footprint.
✓
Credentials
No required environment variables, credentials, or config paths are declared or referenced in the runtime instructions; nothing asks for unrelated secrets.
✓
Persistence & Privilege
Skill is not always-enabled and does not request elevated or persistent presence. It may be invoked autonomously by the agent (platform default), which is expected for skills of this type.
Assessment
This skill appears coherent and low-risk: it's a set of templates and critique procedures for improving outputs. Before installing: (1) avoid running the self-critique workflow on content that contains secrets or sensitive PII (the workflow may echo and reformat content), (2) maintain human review for high-stakes outputs (legal, medical, production secrets), and (3) if you allow autonomous invocation, consider limiting triggers or adding usage logging so the skill cannot be run on sensitive content without oversight.

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

critiquevk978wv7nbydgwyy7r4g5yqj4yn8432f2improvementvk978wv7nbydgwyy7r4g5yqj4yn8432f2latestvk978wv7nbydgwyy7r4g5yqj4yn8432f2qualityvk978wv7nbydgwyy7r4g5yqj4yn8432f2reviewvk978wv7nbydgwyy7r4g5yqj4yn8432f2

License

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

Comments