agentsclimarketplace

Reporter protocol

Skill gustavo-meilus/superpipelines/.agents/antigravity/skills/superpipelines/parity-test-d/reporter-protocol

Loop Engineering for AI coding agents, with real review boundaries. Your AI reviewer cannot edit code. Structurally.

Install
npx -y skills add gustavo-meilus/superpipelines --skill reporter-protocol

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Loaded by the reporter agent to supply operating protocol and invariants for markdown health document generation in the parity-test-d pipeline. Not user-invocable.

SKILL.md

4.1 KB, as published. Nobody here has run it

Reporter — Operational Protocol

<overview> The reporter agent reads the structured metrics produced by the scanner, renders a formatted markdown document with sections for high-complexity files, missing docstrings, and long functions, and writes the final output to `{ROOT}/output/parity-test-d-health-report.md`. It is the final step of the parity-test-d Sequential pipeline (Pattern 1) on Tier 1c (Antigravity CLI). The quality bar is: the output markdown must be human-readable and contain all three required sections without truncation. </overview>

Protocol

<protocol>

1. DISCOVER

  1. Read inputs from the orchestrator dispatch context:
    • metrics_path: path to scanner-metrics.json written by the scanner.
    • output_path: path where the final markdown health document must be written (always {ROOT}/output/parity-test-d-health-report.md).
    • state_path: path to pipeline-state.json for status updates.
    • run_id: current run identifier.
    • root: resolved scope root.
  2. Verify metrics_path exists and is valid JSON. If the file does not exist: emit BLOCKED with message: "Scanner metrics not found at {metrics_path}. The scanner step may have failed."
  3. Parse the metrics JSON. If JSON is malformed: emit BLOCKED with message: "Scanner metrics at {metrics_path} are not valid JSON. Re-run the scanner step."

2. PROCESS

Render the markdown health document using the following template (populated from the parsed metrics):

# Code Health Report — parity-test-d

> Generated by the parity-test-d pipeline (Tier 1c — Antigravity CLI)

## Source

**Directory scanned:** `{metrics.scanned_directory}`
**Files scanned:** {metrics.file_count}

## High-Complexity Files

{If metrics.high_complexity is non-empty, for each entry render:}
- **`{entry.file}`** — complexity score {entry.complexity_score}: {entry.reason}

{If metrics.high_complexity is empty, render:}
- No high-complexity files detected.

## Missing Docstrings

{If metrics.missing_docstrings is non-empty, for each entry render:}
- **`{entry.file}`** — missing docstrings at: {entry.locations joined by ", "}

{If metrics.missing_docstrings is empty, render:}
- No missing docstrings detected.

## Long Functions

{If metrics.long_functions is non-empty, for each entry render:}
- **`{entry.file}`** — `{entry.function}`: {entry.line_count} lines

{If metrics.long_functions is empty, render:}
- No long functions detected.

Ensure:

  • ## High-Complexity Files section is present (even if empty with "No ... detected." sentinel).
  • ## Missing Docstrings section is present (same rule).
  • ## Long Functions section is present (same rule).
  • No section is left entirely blank or contains placeholder text.

3. DELIVER

  1. Create the {ROOT}/output/ directory if it does not exist.
  2. Write the rendered markdown to output_path using the Write tool.
  3. Update pipeline-state.json:
    • Set phases[1].status = "completed".
    • Set phases[1].outputs = [output_path].
    • Set top-level status = "completed".
    • Set completed_at = current ISO-8601 timestamp.
  4. Emit terminal status:
    • DONE — health document written successfully; all three required sections present.
    • DONE_WITH_CONCERNS — document written but one or more sections had no data from metrics (note which and why).
    • BLOCKED — metrics file missing or malformed; output not written.
</protocol> <invariants> - ALWAYS write the output to exactly `{ROOT}/output/parity-test-d-health-report.md` — never a different path. - ALWAYS include `## High-Complexity Files`, `## Missing Docstrings`, and `## Long Functions` sections in the output. - NEVER write partial output — if rendering fails mid-way, do not write the file; emit BLOCKED. - ALWAYS update `pipeline-state.json` phases[1] and top-level status after writing. - Emit exactly one terminal status: DONE / DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED. </invariants>

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.