Skip to content
Automation
Skill

/evaluator-review-contract-parallel

Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

From plugin
auto-harness
1420 skills26 agents8 commands5 hooks
+1
Install
$ npx -y skills add redker56/auto-harness --skill evaluator-review-contract-parallel --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/evaluator-review-contract-parallel

Context preview

The summary Claude sees to decide when to auto-load this skill.

Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

SKILL.md

evaluator-review-contract-parallel.SKILL.md
name: evaluator-review-contract-parallel
description: Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
user-invocable: false

Evaluator Review Contract Parallel

This skill governs Evaluator **review mode**.

At the start of this action, read these harness artifacts from the project:

  • `.harness-parallel/status.md`
  • `.harness-parallel/intake.md`
  • `.harness-parallel/spec.md`
  • `.harness-parallel/design-direction.md`
  • `.harness-parallel/contracts/sprint-XX-contract.md`
  • `.harness-parallel/contracts/sprint-XX-review.md` when revising an existing review.

Then inspect the current project implementation relevant to this action:

  • Read the current source files, routes, components, services, tests, and config that determine whether the proposed sprint contract is feasible and respects locked decisions.
  • Use the codebase to judge feasibility, integration points, and constraint compliance before implementation begins.

Then read these skill references:

  • `references/templates/sprint-contract.md`
  • `references/protocols/file-ownership.md`

Follow these rules:

  • Review the sprint contract before implementation begins.
  • Fail the review when scope, testability, verification readiness, or locked decisions are violated.
  • Judge the contract against the written artifacts and the current implementation, not Generator intent.
  • If feasibility or verification cannot be established from the current contract plus the existing codebase, fail conservatively and say why.
  • Review both `Parallel Workstreams` and `Dependency Graph JSON`.
  • Fail the review if two nodes overlap on owned files, if dependency edges are missing for coupled modules, or if behavior coverage is incomplete.
  • Fail the review if the graph is missing, malformed, cyclic, or references unknown behavior rows.
  • Cite exact files, boundaries, runtime assumptions, or locked decisions when a hard blocker or revision request is raised.
  • Write only the sprint review artifact.
  • Do not modify application source code or generator-owned artifacts.
Read more
Ships withauto-harness

Auto-Harness is a Claude Code plugin for longer software tasks that need planning, implementation, QA, fixes, retests, and a final report. Give it a product brief.

Get the whole plugin

Other skills on auto-harness.