rsi skill

    1

    Automated evaluation and optimization loop that evolves agent skills through recursive testing and blinded grading.

    $5

    /mo

    Subscription · cancel anytime

    Secure checkout via Stripe

    • Always the latest version
    • Delivered live to your agent via MCP
    • Cancel anytime, access ends at period end
    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    rsi skill

    Example session with this skill installed

    rsi-skill run against ./weather-agent until no major accuracy errors max 3 iterations $10 limit

    • Read your context and instructions
    • Compiled the rsi
    • Generated the document

    I have completed the recursive self-improvement loop for the weather-agent skill. The process ran for 3 iterations, evaluating the skill against 15 unique test cases.

    RSI Execution Summary

    MetricValue
    Final Championv2 (Promoted in Iteration 2)
    Goal StatusMet (No major accuracy errors found in last 5 cases)
    Total Iterations3
    Total Spend$6.42 / $10.00
    Findings Fixed4 (Incorrect unit conversion, missing city fallback, API timeout handling)
    Remaining Issues1 (External: API rate limiting on free tier)

    Performance Trajectory

    The baseline (v0) failed 40% of cases due to temperature unit confusion. v1 introduced a unit-normalization script but regressed on location parsing. v2 (the current champion) corrected the parsing logic and successfully handled all 5 fresh cases in the final evaluation iteration.

    Changes Applied

    The following improvements were written to weather-agent/SKILL.md and weather-agent/utils.py:

    • Added explicit instruction to check for Celsius/Fahrenheit markers in the user prompt.
    • Implemented a regex-based coordinate extractor to handle ambiguous city names.
    • Added a retry loop with exponential backoff for weather-api calls.

    Next steps

    1. Review the uncommitted changes in ./weather-agent using git diff.
    2. Run rsi-skill report to view the full HTML evaluation report with transcripts.
    3. Commit the changes if the benchmarks in REPORT.md meet your requirements.

    rsi-skill.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    $5/mo

    Subscription · always the latest version

    • Secure checkout via Stripe
    • Cancel anytime
    • Delivered live via MCP

    About this skill

    Recursive self-improvement is hard to manage manually. Testing an agent skill across diverse scenarios, grading its outputs objectively, and iterating on the prompt or logic often leads to overfit solutions or ballooning costs.

    What it does

    • Autonomous Iteration executes a continuous loop of profiling, case generation, headless execution, and evidence-based grading.
    • Champion-Challenger Gating ensures only changes that outperform the current best version on fresh, held-out test cases are promoted.
    • Dynamic Case Generation creates new evaluation scenarios for every iteration to prevent the agent from simply "teaching to the test."
    • Sandbox Execution runs skill candidates in isolated environments to safely benchmark performance and side effects.
    • Resource Management tracks token usage, time, and dollar spend against user-defined limits to prevent runaway loops.

    How it works

    1. Initialize the workspace and profile the target skill to establish a baseline and measurable success goal.
    2. Generate a batch of fresh, unseen test cases based on the skill's specific failure modes and objectives.
    3. Execute and Grade the current champion and the new challenger in parallel, using independent subagents to provide blinded, evidence-backed scores.
    4. Promote or Veto the challenger based on deterministic gates and aggregate performance improvements.
    5. Apply the final optimized version as uncommitted edits to the target project for developer review.

    Frameworks & tools

    The skill utilizes Python scripts for state management and budget tracking, along with general-purpose agents for profiling and grading. It interacts with the Claude CLI for headless execution and supports any agent skill structure including standalone scripts, plugins, or project-integrated skills.

    Why this beats prompting it yourself

    Manual iteration is prone to bias and ignores regression. This tool enforces a rigorous scientific method where every improvement must prove its worth against held-out data that the improver agent has never seen.

    Use cases

    • Hardening a production skill against edge cases before deployment.
    • Benchmarking a skill's performance across different LLM models.
    • Automating the fix-test-deploy loop for complex multi-step agent workflows.
    • Identifying and documenting external API limitations that hinder skill performance.

    Known limitations

    Requires a sandbox-capable environment and specific CLI access. Grading accuracy depends on the quality of the judge model configured. Pre-existing environment errors in the target may be skipped.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires Claude CLI for headless runs. Performance depends on judge model quality. Cannot fix external API or infrastructure failures. Environment setup must allow sandbox execution.

    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 11 days ago

    Software
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed11 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the tedious trial-and-error process of prompt engineering by using a recursive "Champion-Challenger" loop to test, grade, and refine your agent's logic against dynamic test cases.

    The skill is designed to work with any agent structure, including standalone Python scripts, plugins, and Claude CLI-integrated projects, provided they can be executed in a headless sandbox.

    To prevent "teaching to the test," the skill dynamically generates fresh, unseen evaluation scenarios for every iteration, ensuring your agent truly improves rather than just memorizing specific answers.

    The package includes the core optimization engine, state management scripts for budget tracking, and the sandbox configuration files required to run the autonomous iteration loop.

    Yes, you can set strict limits on token usage, execution time, and total dollar spend to ensure the self-improvement loop stays within your project's budget.

    Once the optimization loop completes, the skill provides the final refined version as uncommitted edits, allowing you to review the changes before they are integrated into your production code.

    New in Agents & Orchestration