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.
57
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./Plugins/harness-engineering/fixtures/budget-archive/2026-04-21/deferred-store/skills/code_quality_review/he-code-review/SKILL.mdQuality
Discovery
75%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 has strong completeness and distinctiveness, explicitly stating both what it does and when to use it, and clearly differentiating from related skills. However, it relies on somewhat jargon-heavy language ('severity-ranked synthesis', 'workflow artifacts') rather than concrete user-facing actions, and misses common natural trigger terms like 'pull request', 'ready to merge', or 'code review'.
Suggestions
Replace jargon like 'severity-ranked synthesis' and 'workflow artifacts' with concrete actions users would recognize, e.g., 'summarize blockers, flag failing checks, assess merge readiness'.
Add natural trigger term variations such as 'pull request', 'ready to merge', 'code review', 'ship', 'merge check' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PR/branch review) and some actions ('Review PRs, branches, diffs, and workflow artifacts'), but the core action is described abstractly as 'package-level go/no-go readiness with severity-ranked synthesis' which is jargon-heavy rather than listing concrete specific actions like 'check test coverage, verify CI status, flag breaking changes'. | 2 / 3 |
Completeness | Clearly answers both 'what' (review PRs, branches, diffs, and workflow artifacts for go/no-go readiness with severity-ranked synthesis) and 'when' ('Use when users need readiness synthesis rather than detailed technical-risk critique'), with an explicit trigger clause that also differentiates from a related skill. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'PRs', 'branches', 'diffs', and 'readiness' that users might say, but misses common natural variations like 'pull request', 'code review', 'merge', 'ship it', 'ready to merge'. Terms like 'severity-ranked synthesis' and 'workflow artifacts' are not natural user language. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche by explicitly distinguishing itself from 'detailed technical-risk critique' and focusing on 'package-level go/no-go readiness with severity-ranked synthesis', which makes it unlikely to conflict with a more general code review or technical analysis skill. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves as a reasonable entry-point overview for code review readiness assessment, with good progressive disclosure to supporting references and clear verdict categories. Its main weaknesses are redundancy between sections (Anti-patterns/Gotchas/Constraints overlap), lack of concrete output templates or executable examples beyond one validation script, and an overly coarse three-step procedure that would benefit from explicit sub-steps and feedback loops.
Suggestions
Add a concrete output template showing the expected format for a readiness verdict (e.g., a sample finding with severity, location, evidence, impact, confidence, and remediation fields filled in).
Expand the three-step Procedure into more granular sub-steps with explicit validation checkpoints and feedback loops (e.g., what to do if evidence pack is incomplete, how to handle partial CI results).
Consolidate the overlapping Anti-patterns, Gotchas, and Constraints sections into a single 'Constraints & Anti-patterns' section to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some redundancy—'Gotchas' largely repeats 'Anti-patterns' and 'Constraints', and the 'Context disposition' line at the top is meta-instruction noise. The 'Philosophy' section is brief but adds little actionable value. Overall mostly lean but could be tightened. | 2 / 3 |
Actionability | The skill provides a concrete validation command (`python3 Infrastructure/scripts/validation-and-linting/he_linear_traceability_lint.py <artifact-path>`) and specific severity ranking (P0-P3), verdict categories, and traceability chain. However, most guidance is procedural description rather than executable examples—no sample output format, no template for findings, no concrete diff-review commands. It describes what to do more than showing how. | 2 / 3 |
Workflow Clarity | The procedure is listed as three high-level steps, and the Validation section adds gate-based blocking logic with a 'stop at first failed gate' instruction. However, the three procedure steps are too coarse—they lack explicit checkpoints, feedback loops for error recovery, and detailed sub-steps. The validation section partially compensates but is separated from the procedure, making the overall flow harder to follow as a single sequence. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to a full guide, review flow, review modes, subagent routing, and domain/QA routing. The main body stays concise as an entry point, appropriately deferring detailed content to referenced files. Navigation is straightforward. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
d00c351
- Reviewed
Table of Contents
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.