quality loops

    1

    Iterative quality enforcement for LLM outputs using structured critique-rewrite patterns and numeric scoring gates.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    quality loops

    Example session with this skill installed

    This incident report is for the CEO. Critique and improve it using a Generate-Critique-Rewrite loop. Ensure it scores at least an 8/10 for clarity and professional tone.

    • Read your context and instructions
    • Compiled the quality loops

    I have initiated a quality loop to refine the incident report. The process will iterate until the clarity and tone scores meet your requirement of 8/10, using a maximum of 4 passes to ensure efficiency.

    Quality Loop: Incident Report Refinement

    IterationClarity ScoreTone ScoreCritic FeedbackStatus
    15/106/10Technical jargon is too dense; opening paragraph lacks a clear impact summary.Iterating
    27/108/10Impact summary added. Paragraph 3 still contains circular reasoning regarding the database failover.Iterating
    39/109/10Technical explanations are now accessible. Professional tone is consistent. No issues found.Target Reached

    Refined Incident Report

    Summary: On October 14, at 14:02 UTC, a database connection pool exhaustion caused a 12-minute outage for 15% of users. The issue was resolved by manually scaling the connection limit and implementing an automated cleanup script.

    Root Cause: The recently deployed analytics module failed to release connections back to the pool under high load.

    Resolution:

    • Scaled RDS connection limits immediately.
    • Reverted the analytics module to v2.1.
    • Implemented connection.close() in the cleanup middleware.

    Next steps

    • Review the final report for any sensitive internal naming conventions.
    • Submit the report to the executive communications channel.
    • Archive the loop ledger logs for the compliance audit trail.

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

    About this skill

    This skill implements structured iteration loops for high-stakes outputs where a model's first draft is insufficient. It enforces a strict separation between the generator and the critic, ensuring work is not shipped until it clears a measurable, numeric quality bar. By using defined patterns like Multi-Critic and Adversarial Critique, it prevents circular arguments, hallmarked errors, and superficial "looks good to me" approvals.

    What it does

    • Enforced Scoring requires every iteration to have a numeric progress metric rather than vague prose feedback.
    • Generator-Critic Separation ensures the model that writes the content is not the same instance that approves it.
    • Multi-Dimension Auditing tracks independent scores for correctness, style, and safety without letting one high score mask a failure in another.
    • Adversarial Stress-Testing identifies edge cases and security exploits by actively attacking the draft until no unrebutted objections remain.
    • Stall Detection monitors for repeated failed rewrites, triggering escalation rather than infinite, unproductive loops.

    How it works

    1. Pattern Selection Choose between Generate-Critique-Rewrite, Score-and-Retry, Multi-Critic, Adversarial Critique, or Judge Ensemble based on the complexity of the task.
    2. Loop Initialization Define a specific numeric target value and a maximum iteration budget using the loop-ledger tool.
    3. Critic Pass Run independent critics or automated scorers to identify specific issues and generate a progress score.
    4. Targeted Rewriting The generator iterates on the draft, specifically addressing the issues list provided by the critic.
    5. Gate Exit The process terminates only when the numeric threshold is cleared, the budget is exhausted, or the critique-gate plugin halts the session.

    Frameworks & tools

    Built for use with loop-ledger and the critique-gate plugin. It utilizes standard GitHub-flavored Markdown for reporting and works across LLM providers supporting tool-calling and system prompt overrides.

    Why this beats prompting it yourself

    Generic "critique this" prompts often result in polite, superficial feedback that fails to improve the actual content. This skill forces numeric accountability and prevents the model from closing a task before the quality bar is demonstrably met.

    Use cases

    • Technical Postmortems refining incident reports until they meet clarity and completeness scores.
    • Security Audits running adversarial loops to find exploits in design documents or code.
    • PR Reviews scoring code changes independently for style, logic, and performance before merging.
    • Legal/Policy Drafting ensuring documents survive a judge ensemble where multiple critics must reach consensus.

    Known limitations

    Requires a numeric metric to function; it cannot iterate on purely subjective tasks that lack a scorable dimension. It is not intended for exploring multiple design variations.

    Requires a numeric metric for progress tracking. Not for exploring multiple designs. Exit conditions depend on tool-ledger logic for target reaching or manual completion.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 28 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed28 days ago

    What's inside

    Frequently Asked Questions

    Unlike simple prompting, this skill utilizes the `loop-ledger` tool to enforce a numeric quality gate, preventing the AI from approving its own work through superficial feedback or circular logic. It ensures the generator and critic remain independent, so the output must demonstrably improve to pass.

    Quality Loops is designed for any LLM provider that supports tool-calling and system prompt overrides, and it integrates directly with the `critique-gate` plugin for automated session management.

    You receive the complete logic for five iteration patterns (such as Multi-Critic and Adversarial), the `loop-ledger` configuration schema, and the `critique-gate` integration parameters ready for deployment.

    No, this skill requires at least one measurable, scorable dimension (like a logic score or style rubric) to function; it is not recommended for purely open-ended creative tasks where quality cannot be quantified.

    The skill includes a 'Stall Detection' feature that monitors for repeated failed attempts or flat progress scores, triggering an automatic escalation or halt rather than wasting tokens on infinite loops.

    New in Agents & Orchestration