Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    dui learning

    1

    Turn project experiments and tool experiences into durable, evidence-backed judgment records.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    dui learning

    dui learning

    Example session with this skill installed

    I've been trying to optimize the Postgres container startup for our integration tests. I tried Alpine-based images, but the health checks kept failing. Switching back to the standard Debian image with a custom shm_size fix finally worked. Document this learning.

    • Read your context and instructions
    • Compiled the dui learning

    I have analyzed the experiment results regarding the Postgres container optimization and created a new judgment record in docs/judgment-records/postgres-startup-optimization.md.

    Judgment Record: Postgres Container Image Selection

    FieldDetails
    StatusSupported
    ObjectiveReduce CI pipeline latency by optimizing Postgres container startup time.
    ConstraintMust pass reliability health checks within 30 seconds.
    Attempt 1Switched to postgres:15-alpine to reduce image pull size.
    Outcome 1Intermittent health check failures. Logs indicated shmmax exhaustion during heavy concurrent migrations.
    Attempt 2Reverted to postgres:15 (Debian) and added shm_size: 256mb to docker-compose.yml.
    Outcome 2100% pass rate over 20 runs. Startup time increased by 4s vs Alpine, but stability was maintained.
    JudgmentUnder CI environments with high-concurrency migrations, consider using Debian-based Postgres images with explicit shm_size config because Alpine images show unstable memory allocation for Postgres WAL processes.
    EvidenceLocal logs from 2024-05-20; PR #402 commit 8f2d3a1.

    Next steps

    1. Review the docker-compose.test.yml to ensure the shm_size fix is applied to the staging environment.
    2. Monitor if the 4s startup overhead impacts the total build budget significantly.
    3. Archive the Alpine experiment branch experiment/alpine-db-test.

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

    About this skill

    Capture Doing–Using–Interacting (DUI) learning to turn fleeting project experiences into durable, evidence-backed judgment records. Most engineering decisions are lost in Slack threads, PR comments, or unrecorded experiments, forcing teams to solve the same problems twice. This skill identifies meaningful milestones and reconstructs the rationale behind tradeoffs, failed attempts, and tool discoveries.

    What it does

    • Identify milestones by scanning experiment notes, diffs, and chat logs for consequential changes in approach.
    • Reconstruct rationale to capture the "why" behind decisions, citing specific test results, stable links, or message dates.
    • Formulate conditional judgments that define when to consider an action based on specific observed evidence.
    • Maintain versioned records that preserve prior reasoning while updating judgments as new data emerges.
    • Distinguish evidence types by labeling agent interpretations, participant explanations, and raw observations separately.

    How it works

    1. Context Analysis: The skill scans your current task, diffs, or conversation history for surprising outcomes or revised decisions.
    2. Knowledge Retrieval: It searches existing judgment-records/ to see if the current situation aligns with or contradicts prior findings.
    3. Record Drafting: It generates a Markdown record documenting objective, constraints, attempts, outcomes, and a conditional judgment.
    4. Validation: It labels the record as "provisional" or "supported" based on the completeness and source of the evidence.

    Frameworks & tools

    This skill produces standard Markdown files. It is designed to work within any git-based repository, documentation folder, or local judgment-records/ directory without requiring external databases or proprietary connectors.

    Why this beats prompting it yourself

    Generic prompts often result in vague "lessons learned" that lack the specific evidence needed for reuse. This skill enforces a strict separation between raw observation and inferred rationale, ensuring records are grounded in verifiable artifacts like commit hashes and test logs rather than LLM hallucinations.

    Use cases

    • Documenting why a specific library was rejected after a 2-day spike.
    • Recording the specific conditions that cause a flakey integration test to fail.
    • Capturing architectural tradeoffs made during a high-pressure refactor.
    • Preserving coordination feedback from senior reviewers to prevent future regressions.

    Known limitations

    Does not support background monitoring or automatic chat retrieval outside the provided context. Requires a project structure that allows Markdown file storage for persistence.

    Requires a local or repository-based Markdown storage path. Cannot access external links or private logs unless explicitly provided in the session context.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill automates the capture of "tribal knowledge" by scanning your dev logs and chat history to create Markdown-based judgment records, preventing your team from repeating the same failed experiments or architectural mistakes.

    The skill is designed to work with any AI agent that can read and write to a file system; it outputs standard Markdown files directly into your project's `judgment-records/` directory.

    No, this skill is designed to be zero-config for your infrastructure, operating entirely within your existing git-based repository or documentation folders without needing external databases or API connectors.

    The skill handles updates by creating versioned records that preserve your initial reasoning while appending new data, allowing your team's "judgment" to evolve as project conditions change.

    You receive the skill definition and a set of standardized Markdown templates that enforce the separation of raw observations from inferred rationale, ensuring your records remain evidence-backed.

    The skill only processes the context you explicitly provide, such as specific diffs, chat logs, or experiment notes; it does not perform background monitoring of your workspace.

    New in Agents & Orchestration