he-code-review

Review Harness Engineering diffs, PRs, commits, and readiness claims for introduced risk. Use when correctness, validation proof, security posture, traceability, closure safety, or review-thread resolution must be assessed before merge or handoff.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-structured instruction skill with a clear sequenced workflow and strong fail-fast validation, plus specific actionable guidance and worked examples. Its main weaknesses are verbosity in enumerated lens/field lists and a mismatch between the body's cited reference paths and the files actually present in the bundle.

Suggestions

Tighten the long enumerated lists (e.g., the eight review lenses in step 6 and the repeated mode enumerations across When to Use, Procedure, and Execution Boundaries) into a single canonical list referenced once.

Reconcile the References section with the actual bundle: either add the cited review-mode-contract.md / review-policy-index.md / stage-arc-boundary-contract.md files to references/, or point the "Read when" map at the bundle files that exist (contract.yaml, evals.yaml, task-profile.json).

Surface the existing bundle files in the body — for example, link evals.yaml and task-profile.json from the Validation or Outputs sections so the present assets are discoverable and navigable.

Dimension	Reasoning	Score
Conciseness	It avoids over-explaining concepts Claude already knows, but lengthy enumerations such as "policy-index, specialist, simplify, coding-harness, gate-selection, first-principles, plugin-hook, and agent-native lenses" and the repeated mode lists across sections could be tightened.	2 / 3
Actionability	For an instruction-only review skill the guidance is concrete and specific: a 13-step numbered procedure, exact mode names, required output fields, decision categories (linear_required/reinforce_required/both_required), and concrete invocation examples.	3 / 3
Workflow Clarity	A clear 13-step sequence with explicit validation checkpoints ("Fail fast: stop at the first failed gate"), mutation-authority gates ("ask when mutation authority is ambiguous"), and a recovery loop ("return the blocker with the smallest recovery step").	3 / 3
Progressive Disclosure	The References section is well-signaled with a condition-to-file "Read when" map, but the cited paths (../../references/skills/he-code-review/.md, Plugins/harness-engineering/references/.md) do not exist in the actual bundle, while the present bundle files (contract.yaml, evals.yaml, task-profile.json) are never referenced in the body.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and pairs them with an explicit "Use when" trigger clause covering the right domain signals. It is concise, complete, and clearly distinguishes this skill from generic review tools.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete review actions on specific objects — "Review Harness Engineering diffs, PRs, commits, and readiness claims for introduced risk" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (review diffs/PRs/commits/readiness for introduced risk) and when ("Use when correctness, validation proof, security posture, traceability, closure safety, or review-thread resolution must be assessed before merge or handoff").	3 / 3
Trigger Term Quality	Covers natural terms the target audience would say — "diffs, PRs, commits, readiness," "merge or handoff," "review-thread resolution" — alongside domain triggers; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear Harness Engineering niche with distinctive triggers (readiness claims, traceability, closure safety, review-thread resolution) unlikely to fire for generic code-review skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/skills/he-code-review/SKILL.md
Commit: 46e4be2

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.