he-technical-review

Review diffs, PRs, specs, plans, or review-feedback items and return severity-ranked engineering findings with exact locations. Use when technical risks or feedback correctness must be verified before implementation.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

77%Weight 40%Scale 1-5

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

The body is a well-structured, validation-aware review doctrine with clear sequencing and minimal verbosity. Its main weakness is progressive disclosure: the reference graph points predominantly to missing files, so the promised detail is not actually reachable.

Suggestions

Restore or vendor the missing referenced files (contract.yaml, evals.yaml, task-profile.json, finding.md.tmpl, assets icons, domain-model-routing.md, qa-intake-routing.md, subagent-routing.md, routing-map.json, codex-agent-creator SKILL.md) so progressive-disclosure links resolve.

De-duplicate the References and 'Read when' lines against the When To Use and Subagent Routing sections to tighten conciseness.

Add one concrete worked example (sample finding with location/impact/minimal-fix/confidence) to lift actionability toward fully executable guidance.

Dimension	Reasoning	Score
Conciseness	Mostly lean bullet-driven prose that avoids re-explaining known concepts, but the References section, 'Read when' lines, and 'Route elsewhere' list partially restate material already covered in When To Use and Subagent Routing.	4 / 5
Actionability	Instruction-only skill with concrete, specific guidance (P0-P3 severities, feedback_response_plan enum values, validation checklist), which the rubric does not penalize for lacking code; minor gaps keep it from fully copy-paste-ready specificity.	4 / 5
Workflow Clarity	A clearly numbered Procedure is paired with an explicit Validation section and a 'Fail fast: stop at first blocking prerequisite or failed validation gate' checkpoint, giving a well-sequenced flow with validation feedback.	5 / 5
Progressive Disclosure	Sections are well-organized and references are signaled one level deep, but almost every referenced bundle path (Infrastructure/references/.yaml\|json, finding.md.tmpl, assets/.png, ../../../references/*.md, routing-map.json, codex-agent-creator SKILL.md) is absent from the actual bundle — only references/context-preservation.md exists — so the navigation structure is largely broken.	3 / 5
	Total	16 / 20 Passed

Description

88%Weight 40%Scale 1-5

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

The description is specific, complete, and distinct: it names concrete review targets, an explicit 'Use when' trigger, and a clear output shape. Trigger term coverage is strong but could add a few more natural synonyms.

Suggestions

Consider adding a couple of natural user phrasings (e.g. 'review this PR', 'check the diff', 'validate this fix') to broaden trigger-term coverage.

Sharpen the distinction from he-code-review in the description itself, since overlap risk is the weakest dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — reviewing 'diffs, PRs, specs, plans, or review-feedback items' and returning 'severity-ranked engineering findings with exact locations' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (review targets, return severity-ranked findings with locations) and 'when' ('Use when technical risks or feedback correctness must be verified before implementation') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger terms (diffs, PRs, specs, plans, review-feedback, technical risks) that users would plausibly say, though a few common synonyms or extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Clear findings-first review niche distinct from implementation, with minor overlap risk against the related he-code-review skill.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 6 missing, 3 deeper-than-1-level, 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/code_quality_review/he-technical-review/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.