AgentStack
SKILL verified MIT Self-run

Reporter Protocol

skill-gustavo-meilus-superpipelines-reporter-protocol · by gustavo-meilus

Loaded by the run-parity-test-h entry skill to supply operating protocol and invariants for markdown validation report formatting in the parity-test-h pipeline. Not user-invocable.

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-gustavo-meilus-superpipelines-reporter-protocol

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Reporter Protocol? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Reporter — Operational Protocol

The reporter step reads the reviewed findings produced by the reviewer step, formats a structured markdown validation report with separate sections for required-field violations, type mismatches, deprecated keys, and dismissed findings, and writes the report to {ROOT}/output/parity-test-h-validation-report.md. It is the final step of the parity-test-h Sequential pipeline (Pattern 1) on Tier 2 (Cursor/Windsurf/Cline), executing inline in the entry skill's session. The quality bar is: the output must be a readable markdown file whose confirmed findings are clearly separated by category and whose dismissed findings are documented with their dismissal rationale.

Protocol

1. DISCOVER

  1. Read inputs from the orchestrator execution context:
  • reviewed_findings_path: path to reviewed-findings.json written by the reviewer step.
  • output_path: path where the final validation report must be written (always {ROOT}/output/parity-test-h-validation-report.md).
  • state_path: path to pipeline-state.json for status updates.
  • run_id: current run identifier.
  • root: resolved scope root.
  1. Verify reviewed_findings_path exists and is a readable file. If not: update pipeline-state.json phases[2].status = "blocked"; emit BLOCKED with message: "Reviewed findings not found at {reviewed_findings_path}. The reviewer step may have failed."
  2. Parse the reviewed findings JSON. If JSON is malformed: update pipeline-state.json phases[2].status = "blocked"; emit BLOCKED with message: "Reviewed findings at {reviewed_findings_path} are not valid JSON. Re-run the reviewer step."

2. PROCESS

Step 2.1 — Partition findings by category and status:

From reviewed-findings.json, partition the findings into four groups:

  1. confirmed_required_fields: findings where category = "required_field" and review_status = "confirmed".
  2. confirmed_type_mismatches: findings where category = "type_mismatch" and review_status = "confirmed".
  3. confirmed_deprecated_keys: findings where category = "deprecated_key" and review_status = "confirmed".
  4. dismissed: all findings where review_status = "dismissed", regardless of category.

Step 2.2 — Render the markdown report:

Format the markdown report using the following template:

# YAML Validation Report — parity-test-h

**Source file**: {source_path}
**Reviewed at**: {reviewed_at}
**Run ID**: {run_id}
**Total findings**: {total_findings} ({confirmed} confirmed, {dismissed} dismissed)

---

## Summary

| Category | Confirmed | Dismissed |
|---|---|---|
| Required field violations | {n} | {n} |
| Type mismatches | {n} | {n} |
| Deprecated keys | {n} | {n} |
| **Total** | **{confirmed}** | **{dismissed}** |

---

## Required Field Violations

{If no confirmed required-field findings: "_No required field violations confirmed._"}

{For each confirmed required-field finding:}
### {id}: {key}

- **Severity**: Error
- **Message**: {message}

---

## Type Mismatches

{If no confirmed type-mismatch findings: "_No type mismatches confirmed._"}

{For each confirmed type-mismatch finding:}
### {id}: {key}

- **Severity**: Error
- **Expected type**: `{expected_type}`
- **Actual type**: `{actual_type}`
- **Actual value**: `{actual_value}`
- **Message**: {message}

---

## Deprecated Keys

{If no confirmed deprecated-key findings: "_No deprecated keys confirmed._"}

{For each confirmed deprecated-key finding:}
### {id}: {key}

- **Severity**: Warning
- **Message**: {message}

---

## Dismissed Findings (False Positives)

{If no dismissed findings: "_No findings were dismissed._"}

{For each dismissed finding:}
### {id}: {key} ({category})

- **Original severity**: {severity}
- **Original message**: {message}
- **Dismissal rationale**: {review_note}

---

_Report generated by parity-test-h pipeline on Tier 2 (Cursor/Windsurf/Cline). Reviewer isolation is convention-only; review was performed within the same agent session as validation._

Step 2.3 — Handle zero-confirmed-findings edge case:

If confirmed = 0 (all findings dismissed, or zero findings from validator): the report still renders with all sections showing the "no findings" placeholder text. Emit DONE_WITH_CONCERNS with message: "Report written with zero confirmed findings. Either the YAML is fully valid or all findings were dismissed as false positives."

3. DELIVER

  1. Create the {root}/output/ directory if it does not exist.
  2. Write the rendered markdown report to output_path using the Write tool.
  3. Update pipeline-state.json:
  • Set phases[2].status = "completed" (or "completed_with_concerns" if zero confirmed findings).
  • Set phases[2].outputs = [output_path].
  • Set phases[2].outputs_summary = { "confirmed_findings": N, "dismissed_findings": N }.
  • Set top-level status = "completed" (or "completed_with_concerns" as appropriate).
  • Set completed_at = current ISO-8601 timestamp.
  1. Emit terminal status:
  • DONE — report written successfully with at least one confirmed finding.
  • DONE_WITH_CONCERNS — report written but contained zero confirmed findings (note reason).
  • BLOCKED — reviewed-findings file missing or malformed; output not written.
  • ALWAYS write the output to exactly {ROOT}/output/parity-test-h-validation-report.md — never a different path.
  • ALWAYS include all four report sections (required fields, type mismatches, deprecated keys, dismissed) even when a section has zero entries.
  • ALWAYS include the footer note about convention-only reviewer isolation in the report.
  • NEVER write partial output — if rendering fails mid-way, do not write the file; emit BLOCKED.
  • NEVER hardcode platform paths — use only the root value supplied in the execution context.
  • ALWAYS update pipeline-state.json phases[2] and top-level status after writing.
  • NEVER suppress dismissed findings from the report — they must appear in the Dismissed Findings section with their rationale.
  • Emit exactly one terminal status: DONE / DONEWITHCONCERNS / NEEDS_CONTEXT / BLOCKED.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.