More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Task Backlog Triage System

    1

    Turn an overgrown task backlog into Now, Next, Parked, and Closed lists that fit real weekly throughput, with a closure log.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Task Backlog Triage System

    Task Backlog Triage System

    Example session with this skill installed

    Worked example: score a 5-item backlog including a high-value export fix, an aging dashboard rebuild, a stale ownerless template, a vendor renewal, and an archive task.

    • Read your context and instructions
    • Compiled the task backlog triage

    Worked example produced by running scripts/backlog_score.py --demo: the export fix scores 10 and lands in Now, the vendor renewal scores 6 and lands in Now on the deadline rule (20 days out), the onboarding guide scores 7 and lands in Next, the dashboard rebuild parks, the archive task parks, and the ownerless 210-day-old item closes as stale with no claimant; 2 priority disagreements are flagged (the dashboard rebuild and archive task are labelled high but score 5 and 4). The SKILL.md example then shows a 186-item backlog cut to 6 weeks of Now plus Next work.

    archive task are labelled high but score 5 and 4). The SKILL.md

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

    About this skill

    Backlogs fail when they become wish lists with no cost. This skill measures backlog size in weeks of throughput, applies an aging rule before any scoring debate, scores surviving items on value, urgency, effort, and delay risk, and enforces capacity limits on the Now list. It includes a scoring script, triage record template, item cards with verb-first next actions, a monthly re-score cadence, and a 10-point health score.

    Does not estimate individual tasks in detail or resolve strategy disagreements. Throughput must come from real completions; guessed throughput makes the system unreliable.

    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 23 days ago

    Permissions

    Terminal / Shell
    Listed23 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    No. Items close only with a reason from an approved list, and requesters get a reopen path with new information or a named owner.

    The skill defines urgency as a cost within 30 days and uses scores plus hard deadlines, so urgency labels alone cannot fill the Now list.

    Weekly for 30 minutes on Now items, monthly for 60 minutes on full re-scoring and the aging rule.

    New in Business & Operations