he-code-review

Review PRs, branches, diffs, and workflow artifacts for package-level go/no-go readiness with severity-ranked synthesis. Use when users need readiness synthesis rather than detailed technical-risk critique.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

A well-sequenced review workflow with clear validation gates and a feedback loop, but it is held back by repeated guidance across sections, mostly abstract rather than executable direction, and a References section whose paths do not resolve to actual bundle files.

Suggestions

Dedupe the recurring themes (CI-not-readiness, read-focused-unless-autofix, reviewer-thread routing) into a single Constraints/Anti-patterns block so Philosophy, Gotchas, and Constraints do not restate them.

Make the evidence-pack and ranking steps more concrete — e.g., a short checklist or template for a P0-P3 finding with exact fields — rather than "Build an evidence pack from...".

Resolve the References section: either ship the referenced files (SKILL.full.md, codex-review-flow.md, review-modes.md) in the bundle or point to the actual present file (references/context-preservation.md) so the disclosure is real rather than dangling.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes Claude's competence, but themes repeat across Philosophy, Anti-patterns, Gotchas, and Constraints (e.g., "Do not treat passing CI alone as merge readiness" appears twice; "read-focused unless an explicit mode" repeats), so it could be tightened.	2 / 3
Actionability	It provides one concrete executable command ("python3 Infrastructure/scripts/validation-and-linting/he_linear_traceability_lint.py <artifact-path>") and concrete verdict labels, but most guidance is abstract direction ("Build an evidence pack from diff/base, changed files, checks...") without copy-paste-ready steps.	2 / 3
Workflow Clarity	The Procedure sequences resolution, evidence-pack building, and verdict emission, with explicit validation checkpoints ("Block go for...", "Stop at the first failed gate") and a feedback loop via the traceability lint before a go verdict, matching the highest anchor.	3 / 3
Progressive Disclosure	A References section is present, but the cited paths (e.g., SKILL.full.md, codex-review-flow.md) do not exist in the bundle; the only real bundle file (references/context-preservation.md) is not referenced from the body, so navigation is signaled but not backed by an actual one-level-deep structure.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 concise, third-person description that clearly states concrete capabilities and an explicit use-trigger, with a distinct readiness-synthesis niche. Its only weakness is trigger-term naturalness, relying on some specialized jargon over the phrasings a user would naturally say.

Suggestions

Add plainer user-facing trigger phrasing (e.g., "Use when the user asks whether a PR is ready to merge or needs a go/no-go call") alongside the readiness-synthesis framing.

Include common natural variations such as "merge readiness", "release readiness", or "is this safe to merge" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Review PRs, branches, diffs, and workflow artifacts", "package-level go/no-go readiness", "severity-ranked synthesis" — matching the highest anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does and when to use it via "Use when users need readiness synthesis", satisfying the highest anchor for an explicit "Use when..." trigger alongside the capability statement.	3 / 3
Trigger Term Quality	Includes some natural user terms (PRs, branches, diffs, go/no-go) but leans on jargon like "readiness synthesis" and "technical-risk critique" and omits common variations users would naturally say; not the level above's broad coverage.	2 / 3
Distinctiveness Conflict Risk	The package-level readiness-synthesis niche with its distinct go/no-go framing is clearly distinguishable from general code review and unlikely to trigger the wrong skill.	3 / 3
	Total	11 / 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
Commit: 5a6027f

Reviewed: 5 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.