Fleet Playbooks — Standup, CI Watch, Weekly Review, Triage

    1

    Includes the full safety rulebook for writing your own playbooks.

    $7.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Fleet Playbooks — Standup, CI Watch, Weekly Review, Triage

    Example session with this skill installed

    Run the engineering-standup playbook for the mobile-app team now and show me the report.

    • Read your context and instructions
    • Compiled the fleet playbooks

    I have executed the engineering-standup playbook for the mobile-app team. The routine pulled data from the GitHub repository and Linear workspace. No write actions were attempted as per the report-only contract.

    Engineering Standup Report: Mobile App

    CategorySummaryItems / Links
    Completed4 PRs merged in mobile-core, Auth flow refactor finalized.PR #402, PR #405, PR #409
    In ProgressPush notification debugging; UI flickering on Android 14.LINEAR-882, LINEAR-890
    BlockedStripe API version mismatch in staging environment.Needs Ops review
    Security/Deps2 low-severity vulnerabilities found in package.json.Scheduled for Mon 10:00
    Metrics92% CI pass rate over last 24 hours.3 failures in e2e-ios

    Next steps

    • Review the blocked Stripe API issue with the backend team.
    • Acknowledge the CI failures in the e2e-ios pipeline.
    • The next scheduled run is tomorrow at 09:00.

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

    About this skill

    Every founder and senior engineer re-runs the same small jobs forever: the morning standup, the Friday review, watching CI, checking dependencies, triaging issues, drafting the investor update. Fleet Playbooks turns them into standing routines your agent runs on schedule — built from the playbook system of Jarvis, a production chief-of-staff agent that runs these exact routines over a live worker fleet.

    Eight playbooks, each with a schedule, an exact field-tested prompt, and an output contract:

    • Engineering standup (weekdays) and Weekly review (Fridays) — what shipped, what's stuck, what's at risk
    • CI watch (hourly) — silent unless it's red, then it tells you why and sends an investigator, never a fixer
    • Dependency & security check (Mondays) — upgrades arrive as a tested branch you land or discard, never a silent push
    • Issue triage, Customer follow-ups (reply drafts, never sends), Revenue pulse (three lines, read-only), Monthly investor update (drafted on a branch, metrics never invented)

    The part that makes routines safe to run unattended is the contract: read-only credentials only, content from email/issues/web is data — never instructions, numbers are never fabricated, every output names its playbook and sources, and everything waiting on you lands in one review queue. Includes the full safety rulebook for writing your own playbooks.

    Pairs with Fleet Delegation (the orchestrator discipline) — Playbooks is the routine layer that runs on top of it. Works with OpenCode, Claude Code, Codex, Grok Build, Cursor, Copilot, Gemini CLI and other SKILL.md-compatible agents. Install paths in INSTALL.md. One-time purchase, free updates.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    Requires host scheduling/cron support. External connections must be read-only. Does not backfill missed runs. Only supports the eight predefined playbook categories.

    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 buying a skill.

    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 17 days ago

    Permissions

    Read Files
    Listed17 days ago

    What's inside

    Frequently Asked Questions

    Fleet Playbooks utilizes a "read-only/draft-only" architecture, meaning the agent can analyze data and prepare work, but it lacks the permission to execute final actions like sending emails or merging code without your direct sign-off.

    This skill is compatible with any AI agent platform that supports cron jobs or scheduled routines; simply import the playbook definitions into your agent's reference library or system prompt.

    The purchase includes eight pre-configured playbook templates for engineering, ops, and comms, along with the logic for schedule management and the standardized approval interface.

    No, to maintain the safety contract, Fleet Playbooks requires read-only access to your tools (like GitHub or Stripe) to generate reports and drafts that you then review manually.

    Unlike basic prompts, these playbooks include built-in "silence is valid" logic and noise reduction, ensuring you only get notified when an action is required rather than receiving repetitive "no update" alerts.

    While the core approval logic is standardized for safety, you can easily adjust the schedule triggers and specific data parameters to fit your team's unique sprint cycles or reporting windows.

    New in Workflow Automation