Skill Review Pro

    1

    Modular skill QA system: static analysis, behavioral testing, and scoring across 6 review modes including direct fix, opinion validation, stability benchmark, and publish check.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    skill-review-pro

    Example session with this skill installed

    Review this skill / check my SKILL.md for issues.

    • Read your context and instructions
    • Compiled the -review-pro

    A scored review report across engineering, UX and workflow policies, with concrete fix instructions or an executed fix.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A modular QA system for AI agent skills. Evaluates skills through static analysis, behavioral testing, and scoring. Supports 6 modes: full review, direct fix (lightweight review then fix report), opinion validation (verify proposed fixes), fix execution, stability benchmark, and publish check (verify marketplace publishes against version, content, and sha). Uses a policy inheritance architecture with composable review policies for engineering, UX, cognition and workflow dimensions. Works with Claude Code, Cursor, OpenClaw, Codex and any agent that reads SKILL.md.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Does not review raw code quality, only skill logic. Requires ClawHub CLI for release verification. Context window limits apply for skills exceeding 8000 characters.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 14 days ago

    • Free with an Agensi account

    Software
    clawhubNode.js

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    skill-review-pro is designed to audit and harden AI agent skills by identifying architectural flaws, instruction ambiguities, and reliability gaps that manual prompting often misses. It uses a 100-point scoring engine and adversarial testing to ensure your skills are production-ready and resilient to edge cases.

    This tool is built specifically for the OpenClaw skill ecosystem and integrates with the ClawHub CLI. It is ideal for developers building complex, multi-file agentic skills who need to verify cross-file dependencies and workflow logic.

    The package includes the core scoring engine, a suite of domain-specific review policies (Engineering, Cognition, Workflow), the automated fix executor, and a benchmarking utility for stability testing. All necessary scripts for local repository audits are included.

    While it provides a 100-point quality score and identifies architectural weaknesses, it focuses on the logic, instructions, and prompt density of the skill. It does not perform deep static analysis on raw programming code (like C++ or Python syntax) outside of the skill's operational instructions.

    After the audit, you can use the 'fix' command to review proposed modifications. The tool provides a side-by-side diff of the improvements, and once you confirm, it automatically executes the file-level changes to your skill.

    For the most comprehensive experience, including release verification and repository audits, the ClawHub CLI is required. However, the core static analysis and 100-point scoring can be initiated by providing local file paths or pasting content directly.

    New in Prompt & Skill Engineering

    Free