agentsclimarketplace

Review artifact

Skill dsifry/metareview/skills/review-artifact

Review a spec, plan, design, decomposition, architecture doc, pre-mortem, runbook, or acceptance report with metareview.From its SKILL.md

Install
npx -y skills add dsifry/metareview --skill review-artifact

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

  • 23 stars23 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.

SKILL.md

3.1 KB, as published. Nobody here has run it

metareview review artifact

Use when reviewing a Markdown artifact before implementation or before a gate is considered passed.

Workflow

  1. Run metareview review artifact <path> to create the review scaffold. The command exits nonzero while the review is still NOT_REVIEWED; this is expected and is blocking.
  2. Read the generated context pack and review log path.
  3. Use rubrics/artifact-review-rubric.md.
  4. Run the required lenses as parallel subagents by default: Feasibility, Completeness, Scope and alignment, Architecture, Intent preservation, Security, Testing-quality, Data-migration. Invoking this artifact-review workflow is explicit authorization to delegate those lenses. The Security lens uses rubrics/security-review-rubric.md (OWASP classes scoped to a diff review). The Testing-quality lens uses rubrics/testing-quality-rubric.md. The Data-migration lens uses rubrics/data-migration-rubric.md. Lenses take an adversarial stance: assume there may be a fundamental mistake hiding in this design; hunt for it, do not confirm the artifact is well-shaped.
  5. Only fall back to in-session-emulated when subagents are unavailable or the human explicitly requests no delegation. If falling back, state that the review is not independently adversarial and treat it as weaker evidence.
  6. Update the review log with reviewer rows, per-reviewer verdicts, findings, evidence, execution mode, and the aggregate verdict. Keep orchestrator context/synthesis (checkout notes, filtering rationale, consolidation narrative) in the ## Orchestrator Notes (not findings) section ONLY — it is audit trail, not a finding stream. Only the ## Findings section and its classified ## Blocking Findings, ## Advisory Findings, ## Follow-up Findings, and ## Warnings sections contain review findings. The deterministic gates (eval-injection, missing-test, etc.) remain blocking findings for the task-done verdict; downstream eval extractors should skip findings sourced from metareview-deterministic/* and metareview-session.
  7. Always return the actual artifact-review verdict from the reviewer set. Do not substitute a fixed example verdict; NEEDS_REVISION and ESCALATE are valid review results when supported by findings.
  8. Blocking findings must cite file lines, artifact sections, command output, or task IDs.
  9. For a re-review, run metareview review artifact <path> --previous-run <run-id> so the new run links to the prior attempt.

Use metareview review artifact <path> --scaffold-only only when explicitly creating a scaffold without claiming the review is complete.

Gate Rule

A review execution is incomplete while required reviewer rows are missing, any reviewer lacks a verdict, or the aggregate verdict is NOT_REVIEWED. Do not call an artifact implementation-ready while the verdict is ESCALATE or NEEDS_REVISION, required reviewer rows are missing, reviewer verdicts are missing, or blocking findings remain unresolved unless the human explicitly accepts the risk.

Keep looking

Skills are one crate of 613,297. 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.