Issue Triage Brief — Structured Intake for Maintainer Agents

    1

    Free AgentOps Lab skill: turn a raw issue, bug report, or feature request into a triage brief with type, severity, repro gaps, and next action. Not a star or income guarantee.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Issue Triage Brief — Structured Intake for Maintainer Agents

    Example session with this skill installed

    Please write an Issue Triage Brief for this sanitized issue from a repository I already have rights to. Do not comment or close anything. Write a one-screen brief.

    • Read your context and instructions
    • Compiled the issue triage brief

    A maintainer pastes a sanitized issue from a repo they already have rights to. The skill does not comment or close anything. It writes a one-screen brief:

    Restated report (1 sentence). Type (bug, feature, docs, question, support, security-sensitive, or other) taken from the text. Severity only from what the reporter actually said, or UNKNOWN — no invented production impact. Affected surface. Repro steps and environment that were mentioned, plus explicit gaps. Reported facts vs labeled assumptions. Related issues only if the user cited them. One next action (ask-clarifying, needs-repro, accept-and-label, pack-as-good-first only if the work is real and scoped, park, close-with-reason as a proposal, or escalate-privately). Up to five clarifying questions the reporter could actually answer. A public-safe check: secrets, tokens, private emails, and undisclosed security reports stay out of public notes.

    If the paste looks like an undisclosed security issue, the skill stops public drafting and flags private handling. The maintainer still owns labels, comments, and closes. This is a ritual for structured intake, not a growth or earnings product and not a mass-comment bot.

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

    About this skill

    You already use agents on maintainer work. What still breaks: incoming issues that never become a reusable triage brief, and next actions that start before severity or repro is clear.

    Issue Triage Brief by AgentOps Lab turns a raw issue, bug report, or feature request into a one-screen brief: type, severity (from the text or UNKNOWN), affected surface, reproducibility gaps, reported facts vs assumptions, next action, and clear clarifying questions.

    Compliance: Structure triage only. Authorized repositories and communities only. No invented impact or issue numbers. No mass-comment or spam-issue bots. Never publish undisclosed security issues. Sanitize secrets, tokens, and private emails. Not a Code of Conduct tribunal. No star, fame, or earnings guarantees.

    Install as markdown SKILL.md for Cursor / Claude Code / Grok Bot-style agents.

    Authorized repos only. Not a star or income guarantee. Never publish undisclosed security issues. No mass-comment bots. No invented issue numbers or impact. Not a Code of Conduct tribunal.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed6 days ago

    What's inside

    Frequently Asked Questions

    Authorized repositories and communities only. Confirm you maintain the repo or are authorized to help before triaging.

    No. This is not a star or income guarantee. It is a ritual for structured intake, not a growth or earnings product.

    Never publish undisclosed security issues. If the paste looks like an undisclosed security issue, the skill stops public drafting and flags private handling.

    No mass-comment or spam-issue bots. The skill does not comment or close anything. The maintainer still owns labels, comments, and closes.

    No invented issue numbers or impact. Severity is taken only from what the reporter actually said, or UNKNOWN.

    Not a Code of Conduct tribunal. Sanitize secrets, tokens, and private emails. Structure triage only.

    New in Prompt & Skill Engineering