Delivery Brief

    1

    Create concise, decision-ready handoffs that compare the requested change with implementation evidence, review rework, and verification gaps.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Delivery Brief

    Example session with this skill installed

    Review the current branch against the original task and available review history. Prepare a concise delivery brief showing acceptance status, any scope or architecture drift, review findings that led to rework, checks that ran, and remaining unknowns. Do not invent evidence or infer that an unrun check passed.

    • Read your context and instructions
    • Compiled the delivery brief

    Illustrative delivery brief

    This fictional example demonstrates the structure of a decision-ready handoff. The paths, review notes, and verification status below are illustrative; they are not findings from a real repository.

    Decision summary

    Status: Needs follow-up before acceptance. The change appears to implement the requested session-token flow, but the supplied evidence does not establish that revocation works after logout.

    AreaEvidence in this exampleImpact
    ScopeThe task requested a token-based session flow. The diff also changes password hashing behavior.Confirm that the additional change is intended and covered by tests.
    ContractThe implementation adds an exp claim; the requested lifetime is not present in the supplied acceptance notes.The required token lifetime remains unresolved.
    Review reworkA prior review requested an explicit expiry claim. The updated diff now includes one.Recheck the final value against the agreed requirement.
    VerificationUnit tests are listed as passing; the revocation integration check is not shown.Revocation behavior remains unverified.

    What would change the decision

    1. Confirm the required token lifetime from the original request or owner.
    2. Verify logout and revocation behavior with the project’s integration test or staging environment.
    3. Review the password-hashing change separately if it was outside the approved scope.

    Evidence limits

    This brief only reflects the supplied request, diff, review notes, and test results. It does not establish production behavior, and it does not treat a missing test receipt as a passing test.

    Huan Dev skill group

    Delivery Brief is part of the six-skill Huan Dev collection: https://github.com/HuanHuanHuanFFF/huan-dev

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

    About this skill

    Delivery Brief

    Delivery Brief turns repository work into a decision-ready handoff. It compares the request and acceptance criteria with the implementation, review history, and verification evidence, then brings material deviations and unresolved questions to the front.

    What it covers

    • Scope and requirement drift
    • Changes to architecture, state, concurrency, or public contracts
    • Review findings, resulting rework, and recheck evidence
    • Tests and checks that ran, failed, or remain unverified
    • Open questions that still need a user or owner decision

    The output focuses on facts that could change acceptance or release decisions instead of repeating routine implementation details. It requires a discoverable baseline, such as the original request, repository history, or acceptance criteria. It cannot verify runtime behavior in a live environment.

    Part of the Huan Dev skill group

    Delivery Brief is one of six related, free skills for a grounded development workflow. Browse the complete collection and source code: Huan Dev on GitHub.

    Requires access to repository history and original requirements. Cannot execute live environment tests or verify runtime state beyond static analysis of implemented changes.

    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

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike standard PR summaries that describe every line of code, this skill focuses exclusively on 'drift'—identifying where the final code diverged from the original requirements and highlighting potential architectural risks.

    The skill is framework-agnostic and designed to work with any git-based workflow; it is currently optimized for integration with IDE-based agents like Claude Code, Cursor, and GitHub Copilot.

    No complex installation is required; once purchased, you can import the skill's logic directly into your preferred AI agent's configuration to begin analyzing your local repository context.

    You will receive the core skill definition, a set of specialized analysis instructions for your agent, and a guide on how to provide the necessary repository context for the most accurate briefs.

    The skill can only analyze information present in your repository history and documentation; it cannot predict runtime behavior or detect drift against requirements that were never documented in the codebase.

    Buyers receive lifetime access to the current version of the skill, including any minor updates or optimizations released to maintain compatibility with evolving AI agent frameworks.

    New in Business & Operations