HA

harness-artifact-reviewer

Validates specific harness artifacts against acceptance criteria before they move forward.

Install

mkdir -p .claude/skills/harness-artifact-reviewer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17299" && unzip -o skill.zip -d .claude/skills/harness-artifact-reviewer && rm skill.zip

Installs to .claude/skills/harness-artifact-reviewer

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Review a single critical harness workflow artifact, such as plan.md or technical-decisions.md, before a downstream agent consumes it. Writes one review report and uses an explicit Review Status gate.
199 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Review a single critical workflow artifact
  • Assess acceptance criteria against cited evidence
  • Reject plans missing required headings or checklist shape
  • Report approval or rejection with findings and blockers
  • Integrate sub-agent results without editing the artifact

How it works

The skill spawns a sub-agent to review a specified artifact against its acceptance criteria, assessing each criterion using cited evidence. It reports approval or rejection based on this assessment.

Inputs & outputs

You give it
A single workflow artifact (e.g., plan.md) and its acceptance criteria
You get back
A review report indicating approval or rejection, along with findings, evidence, and blockers

When to use harness-artifact-reviewer

  • Validating project plans
  • Reviewing technical decision documents
  • Artifact quality gating

About harness-artifact-reviewer

Uses a sub-agent to review single workflow artifacts (like plan.md) against defined criteria. Reports approval or rejection based on evidence, preventing broken plans from moving to execution.

Review a single critical harness workflow artifact, such as plan.md or technical-decisions.md, before a downstream agent consumes it. Writes one review report and uses an explicit Review Status gate.

When not to use it

  • When reviewing multiple artifacts simultaneously
  • When the goal is to edit the reviewed artifact or choose remediation
  • When the artifact is not a critical workflow document like plan.md or technical-decisions.md

Limitations

  • Reviews only one selected artifact at a time
  • Does not edit the reviewed artifact
  • Does not choose remediation actions

How it compares

This skill automates the critical review of single workflow artifacts using a dedicated sub-agent and predefined criteria, providing a structured gatekeeping mechanism that is more consistent than manual review.

Compared to similar skills

harness-artifact-reviewer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
harness-artifact-reviewer (this skill)017dNo flagsIntermediate
deepwiki-rs259moReviewIntermediate
python-code-style95moReviewIntermediate
code-review-excellence194moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

deepwiki-rs

sopaco

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.

25170

python-code-style

wshobson

Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.

971

code-review-excellence

wshobson

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

1958

code-walk-thru

pchalasani

Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.

670

cookbook-audit

anthropics

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

568

schema-markup

davila7

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.

1042

Search skills

Search the agent skills registry