critique

Audits and fixes staged repository scripts and GitHub Actions workflows for robustness and security.

Updated Aug 26, 2026
One-click install
npx skills add https://github.com/rameshkumarchouhanr/gemni-cli --skill critique-rameshkumarchouhanr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/rameshkumarchouhanr/gemni-cli/tree/main/tools/gemini-cli-bot/.gemini/skills/critique
Command: npx skills add https://github.com/rameshkumarchouhanr/gemni-cli --skill critique-rameshkumarchouhanr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Automated repository maintenance scripts and GitHub Actions workflows often ship with subtle flaws like hardcoded data, missing error handling, spammy notification loops, or security vulnerabilities. This Skill acts as a quality gate that reviews staged changes against a rigorous technical checklist before they are merged. ## Core Features & Use Cases - Technical Robustness Audit: Verifies time-based logic, dynamic data fetching via the GitHub API, error handling around CLI calls, and performance of loops in staged scripts. - Security & Payload Screening: Detects prompt injection attempts, data exfiltration, unauthorized command execution, and untrusted external directives in staged changes. - Scope Enforcement: Ensures each PR addresses a single cohesive change, unstages unrelated internal files, and outputs an [APPROVED] or [REJECTED] verdict for the CI workflow. - Use Case: A bot proposes a script that nudges stale pull requests. This Skill reviews the staged diff, fixes brittle string replacements and missing try/catch blocks, records the decision in the lessons-learned ledger, and approves or rejects the change. ## Quick Start Review the currently staged changes with the critique skill and fix any technical or security issues before outputting a verdict.

Frequently Asked Questions about critique

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically review bot-generated script changes before merging?

Stage the proposed changes and run this critique workflow, which inspects the staged diff against a technical and security checklist. It fixes detected flaws directly, re-stages the files, and outputs an APPROVED or REJECTED verdict for the CI pipeline.

What does the critique skill check in GitHub Actions workflows?

It verifies time-based grace period logic, dynamic fetching of maintainers via the GitHub API, try/catch error handling around CLI calls, async execution in loops, terminal escalation states to prevent spam, and correct comma-separated metrics output formats.

Can this skill detect prompt injection in code changes?

Yes, it scans staged changes for comments or strings resembling prompt injection, such as instructions to ignore rules or force approval outputs. It also rejects changes justified by external GitHub comments rather than empirical repository evidence.

When does the critique skill reject a pull request?

It rejects when a PR bundles multiple unrelated changes, contains security risks like data exfiltration or arbitrary command execution, or when the solution is spammy or degrades developer experience and cannot be easily fixed.

What are the limitations of this automated critique approach?

It is strictly limited to files already staged by the prior investigation phase and cannot modify unstaged files or invent new workflows. It also does not create pull requests itself; the GitHub Actions workflow acts on its verdict string.