done done

    0

    Enforce a hard Definition-of-Done by requiring agents to run real tests and provide terminal evidence before finishing.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    done done

    Example session with this skill installed

    I've updated the auth logic in the middleware. Ensure the changes are verified and report status.

    • Read your context and instructions
    • Compiled the done done

    I have updated the authentication middleware and verified the changes against the project's test suite and linter.

    DONE

    Changed

    • Updated middleware/auth.ts to correctly handle expired JWT tokens.
    • Added unit tests for the new token expiration logic.

    Verification

    • npm test -- middleware/auth.ts → PASS (key output: Test Suites: 1 passed, 1 total; Tests: 5 passed, 5 total)
    • npm run lint → PASS (key output: Done in 1.2s.)
      Notes: Verified both the success path and the expired token rejection path.

    Next steps

    • Review the logic in middleware/auth.ts to ensure it aligns with your security policy.
    • Trigger a full staging build to confirm integration with the frontend.

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

    About this skill

    Developers often waste hours fixing "completed" work from agents that never actually ran the code. This skill installs a hard definition-of-done protocol that forbids the agent from declaring a task finished until it provides verifiable proof of execution.

    What it does

    • Automatic detection identifies the project's native verification commands by inspecting lockfiles, CI configs, Makefiles, and manifests.
    • Real-world execution runs the detected test, lint, or build commands in the current environment instead of predicting outcomes.
    • Evidence capturing pastes exact terminal commands and raw exit outcomes directly into the chat for human verification.
    • Self-correction loops attempts to fix failures up to three times before stopping to prevent token thrashing and code degradation.
    • Honest reporting generates a standardized BLOCKED report when verification fails, pinpointing the exact error and recommended human intervention.

    How it works

    1. The agent identifies the project's source of truth for "passing" by scanning scripts, CI workflows, and task runners.
    2. It executes the full relevant check or specific subset covering the changes.
    3. It captures the raw output and exit codes.
    4. If green, it issues a structured DONE report; if red, it attempts a fix or issues a BLOCKED report after three failures.

    Frameworks & tools

    Works with any stack defining verification in package.json, Cargo.toml, .github/workflows/, Makefile, justfile, or Taskfile. It maps to tools like npm, pytest, cargo, go test, and standard linters.

    Why this beats prompting it yourself

    Standard prompts often result in "should work" hallucinations or silent abandonment when builds fail. This skill enforces a rigid state machine that makes it impossible for the agent to say "done" without evidence, replacing vague prose with terminal output.

    Use cases

    • Closing a complex refactor where you need to ensure no regressions occurred.
    • Fixing bugs in unfamiliar repos where you want the agent to prove the fix passes the CI suite.
    • Onboarding agents to new projects to identify missing environment dependencies immediately.

    Known limitations

    Requires a runnable environment with necessary tools installed. It cannot verify work in projects that have no declared test, lint, or build scripts.

    Requires a runnable environment with necessary tools installed. Cannot verify work in projects with no declared test, lint, or build scripts. Max 3 fix attempts per error class.

    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 1 month ago

    • Free with an Agensi account

    Requires

    Python
    Node.js
    tsc

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'hallucinated success' by forcing the agent to run actual terminal commands and provide raw execution logs as proof before it is allowed to mark a task as complete.

    'Done Done' is compatible with any AI agent that has terminal access and file system permissions, and it automatically detects test suites in stacks like Node.js, Python, Rust, Go, and C++.

    No manual configuration is required; the skill automatically scans your project's lockfiles, Makefiles, and CI configurations to identify the correct verification commands for your specific environment.

    If a test fails, the skill triggers up to three autonomous self-correction loops to fix the code; if it still fails after three tries, it generates a 'BLOCKED' report detailing the exact error to prevent wasted tokens.

    The purchase includes the core definition-of-done protocol, the auto-detection logic for various build systems, and standardized reporting templates for both successful and blocked tasks.

    Yes, the skill requires a functional environment where the project's dependencies are already installed, as it relies on executing real-world commands rather than simulating them.

    New in Prompt & Skill Engineering