Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    HuG

    1

    The Humane-Gated Flow is an issue-driven development lifecycle for building software with a coding agent.

    $8

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    HuG

    HuG

    Example session with this skill installed

    /intake The login button is flickering on Safari, and we really need a way to export user data to CSV for the marketing team. Also, the README still shows the old API endpoint from v1.

    • Read your context and instructions
    • Compiled the hug

    I have processed the feedback and created three distinct issues in the repository.

    GitHub Issues Created

    TitleTypeURL
    Fix login button flickering on Safaribughttps://github.com/org/repo/issues/42
    Add user data export to CSVenhancementhttps://github.com/org/repo/issues/43
    Improve README API documentation for v2documentationhttps://github.com/org/repo/issues/44

    Each issue includes the original verbatim feedback as a reference. I have assigned these to you and applied the relevant labels.

    Next steps

    1. Run check-doc-drift README.md to identify the specific lines in the documentation that need updating.
    2. Use plan-issues to determine if the CSV export should be prioritized for the current milestone.
    3. Start a review-loop to begin the Safari flickering fix.

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

    About this skill

    HuG is a collection of six specialized skills designed to bridge the gap between source code and repository management. It solves the friction of maintaining documentation accuracy, managing GitHub issue hygiene, and enforcing high-quality review workflows. The package automates the tedious parts of the development lifecycle, ensuring that documentation never drifts from the implementation and that every pull request is backed by a clean, traceable history.

    What it does

    • Detect documentation drift by mapping repository files to specific doc sections and identifying missing or outdated content.
    • Automate issue management by turning raw feedback into formatted GitHub issues with proper labels, milestones, and tracking relationships.
    • Orchestrate pull requests by syncing them with existing issues, verifying CI status, and handling the merge-and-cleanup flow.
    • Enforce reviewed commits through a specialized loop where the agent only commits what the human has manually staged.
    • Generate repository roadmaps by sequencing open issues into pinned tracking issues with dependency logic.

    How it works

    1. Sync check: Run check-doc-drift against a file or URL to receive a diff table of the repo vs. documentation.
    2. Intake feedback: Use /intake with pasted text to automatically generate categorized GitHub issues.
    3. Plan work: Invoke plan-issues to build a prioritized roadmap directly within the GitHub issue tracker.
    4. Iterative development: Use /review-loop to write code that the human must stage before the agent will commit and push.

    Frameworks & tools

    This skill requires the GitHub CLI (gh) and git. It integrates with repository-specific tools like package.json scripts, Makefiles, and standard GitHub issue/PR templates.

    Why this beats prompting it yourself

    Writing prompts to manage GitHub API calls and multi-file drift checks is prone to hallucination and context loss. HuG provides a deterministic workflow for repository maintenance, ensuring that system-level commands like gh api and git write-tree are executed with precise, verified logic.

    Use cases

    • Maintaining READMEs by ensuring code snippets match the actual source files.
    • Triage automation for turning messy email feedback into actionable dev tickets.
    • Review enforcement for teams that want a strict "human-stages, agent-commits" workflow.
    • Release planning to visualize issue dependencies without leaving the GitHub UI.

    Known limitations

    Requires the GitHub CLI to be authenticated. The review loop requires manual staging by the user. Planning skills are limited to approximately 200 open issues per run.

    What's included (6 skills)

    • check-doc-drift

      Check whether a document (a blog post, an article, a README, docs pages, a spec copy) is missing anything or out of date given the current repository, and report what it needs, without editing anything. Use when the user asks whether a doc is still accurate, up to date or in sync with the code, or before releasing or merging changes that a doc describes.

    • file-issue

      Turn a request into a well-formed GitHub issue - capitalized imperative title (Add, Fix, Improve, Remove), a body following the repository's issue templates or a template by kind (bug, feature, other), the matching label, the right milestone and tracking issue, assigned to the user. Use when the user asks to open, file, create or log an issue, or before starting work that has no issue yet.

    • intake

      Turn pasted feedback (a message, an email, a bug report, in any language) into one English GitHub issue per topic on the current repository, with a verb-first title, a short description and the original message quoted verbatim. Use when the user types /intake followed by feedback text, or asks to file pasted feedback as issues.

    • open-pr

      Open a GitHub pull request for the current branch that matches its issue - same title as the issue, body from the repository's pull request template or Summary / Changes / How to test / Notes, "Closes #n" so merging closes the issue, assigned to the user - then wait for checks and merge only on green. Use when the user asks to open, create or merge a pull request for the current branch.

    • plan-issues

      Order a repository's open GitHub issues into a plan that lives in the tracker, not in a file - a pinned tracking issue listing them in order, grouped by milestone, with every issue attached as a sub-issue and only real dependencies encoded as "blocked by" links. Use when the user asks to order, prioritize, plan or sequence open issues, or to build a roadmap from them.

    • review-loop

      Work in small reviewed chunks where the human approves each one by staging it in git and the agent commits exactly what was staged - the agent never stages its own work, runs the format check and linter on every chunk, and watches for the staged content to commit and push it. Use when the user asks to review changes chunk by chunk, to approve each commit, or types /review-loop.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed 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 scanned

    Verified clean 6 days ago

    • Passed all security checks, Safe to install

    Requires

    GitHub

    Listed6 days ago

    What's inside

    Frequently Asked Questions