agentsclimarketplace

Review

Skill Tiao553/sdd-harness-copilot/.github/skills/review

AI-powered assistant for Harness-based software delivery, helping automate CI/CD, testing, deployments, and pipeline optimization with faster, safer, and more reliable workflows.

Install
npx -y skills add Tiao553/sdd-harness-copilot --skill review

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

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 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

AgentSpec review commands. Use /review-commands + command. Commands: /review, /judge

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, as published. Nobody here has run it

Review Commands

Invoke as:

/review-commands /review <file-or-directory>
/review-commands /judge <file> [--context "..."] [--model <openrouter-model>]
/review-commands /judge --ledger

Grounding

  1. Read .github/config/grounding.md.
  2. Treat this skill as the primary routing source.
  3. For /review, use .github/agents/python.code-reviewer.agent.md.
  4. For /judge, use .github/agents/dev.judge-agent.agent.md.
  5. Load only the KB files required by the selected agent or by the reviewed domain.

/review

Use for code review, config review, migration review, and documentation review.

Execution:

  1. Read the target file or directory.
  2. Use the code-review stance: findings first, ordered by severity.
  3. Cite concrete file paths and line numbers.
  4. Include missing tests or residual risks.

/judge

Use for a second opinion on high-risk or ambiguous output.

Execution:

  1. Read .github/agents/dev.judge-agent.agent.md.
  2. If the request targets a file, read the file before judging.
  3. If an external judge runtime is configured and OPENROUTER_API_KEY is available, run that runtime.
  4. If the runtime or key is missing, stop and report the missing prerequisite instead of inventing an external verdict.
  5. Write ledger entries only to .github/storage/judge-ledger.jsonl.

Comandos Disponíveis

ComandoDescriçãoArquivoAgente
/reviewCode review com findings por severidadecommands/review.mdcode-reviewer
/judgeSegunda opinião via judge runtime externocommands/judge.mdjudge-agent

Constraints

  • Do not use #skill: or skill: syntax.
  • Do not use .claude/** paths.
  • Do not initiate SDD workflow phases from this skill.

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.