More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Report Gate — Validate Worker Report YAML

    1

    Validate worker agents' report YAML before anyone trusts it: required fields, placeholders, real timestamps, 1-3 line summaries, partial-result reasons, block scalars. 13 checks, JSON output, 14 tests.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Report Gate — Validate Worker Report YAML

    Agent Report Gate — Validate Worker Report YAML

    Example session with this skill installed

    A worker agent just wrote report_bad.yaml and says the task is done. Check the report before the reviewer or dashboard reads it.

    • Read your context and instructions
    • Compiled the agent report gate

    Summary

    The good example passes. The bad example is blocked with 4 errors and 3 warnings, each with a stable reason code, so the pipeline never trusts it.

    Commands and real output

    $ python3 scripts/report_gate.py examples/report_good.yaml
    PASS: 0 error(s), 0 warning(s)
    
    $ python3 scripts/report_gate.py examples/report_bad.yaml --strict
    ERROR placeholder:next_action: 'next_action' is empty or a placeholder
    ERROR completed_at_invalid: completed_at must be ISO-8601 with a timezone, e.g. 2026-01-01T09:30:00+00:00
    ERROR did_line_count: 'did' must be 1..3 non-empty lines (got 5); move details to notes
    ERROR shortfall_reason_not_text: shortfall_reason must explain why, not repeat a number
    WARN  bare_free_text:notes: write 'notes' as a block scalar ('notes: |') so pasted text cannot break the YAML
    WARN  bare_free_text:next_action: write 'next_action' as a block scalar ('next_action: |') so pasted text cannot break the YAML
    WARN  bare_free_text:shortfall_reason: write 'shortfall_reason' as a block scalar ('shortfall_reason: |') so pasted text cannot break the YAML
    FAIL: 4 error(s), 3 warning(s)
    

    What each finding means

    CodeWhy it matters
    placeholderAn empty or TBD field looks filled but tells the next step nothing
    completed_at_invalidA finish time without a timezone cannot be compared or ordered
    did_line_countA 5-line "did" hides the result; details belong in notes
    shortfall_reason_not_textA partial result needs a reason, not a number
    bare_free_textUnquoted free text is the usual cause of broken report YAML

    Next steps

    Add --json to feed the result to a script, or --expect task_id=... to check the report belongs to the assigned task. Tune required fields in examples/contract.yaml.

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

    About this skill

    Your worker agents say "done". Their report says otherwise.

    In multi-agent setups, each worker writes a small YAML report and the next step trusts it. When that report is broken, vague, or carries a made-up finish time, the error spreads to your reviewer, your dashboard, and your scheduler.

    Agent Report Gate is one Python file that checks a report before anyone reads it:

    • Parses safely and flags free text that is not in a block scalar (the usual cause of broken YAML)
    • Required fields present and not placeholders like TBD, n/a, -
    • completed_at is ISO-8601 with a timezone, not in the future, not before assignment
    • "did" is 1-3 lines, so the summary stays readable
    • Partial reports must state target, actual, and a real reason
    • task_id / worker_id match the assignment

    What's inside:

    • SKILL.md: instructions for Claude Code and other coding agents
    • scripts/report_gate.py: CLI with human or JSON output and clear exit codes
    • Good and bad example reports, a contract file to tune the rules
    • 14 unittest cases

    Requirements: Python 3.9+, PyYAML.

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

    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 8 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed8 days ago
    Updated4 days ago

    What's inside

    Frequently Asked Questions

    Validate worker agents' report YAML before anyone trusts it: required fields, placeholders, real timestamps, 1-3 line summaries, partial-result reasons, block scalars. 13 checks, JSON output, 14 tests.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Agent Report Gate — Validate Worker Report YAML on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.