roborev-review-branch
Request a code review for all commits on the current branch and present the results
51
55%
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 ./internal/skills/claude/roborev-review-branch/SKILL.mdQuality
Discovery
32%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 conveys a clear action—requesting code reviews for branch commits—but lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. It also misses common trigger term variations and doesn't elaborate on the specific aspects of the code review process.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'review my code', 'code review', 'review commits', 'check my branch', or 'review changes'.
Include additional natural keywords and variations users might say, such as 'PR review', 'pull request', 'diff', 'review my changes', or 'branch feedback'.
Expand the 'what' portion to list more specific actions, e.g., 'Requests a code review for all commits on the current branch, summarizes feedback, highlights issues, and presents actionable results'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (code review) and a concrete action (request a code review for commits on the current branch, present results), but it doesn't list multiple specific actions or elaborate on what the review covers (e.g., style checks, bug detection, security analysis). | 2 / 3 |
Completeness | The description answers 'what' (request a code review for commits and present results) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'code review', 'commits', and 'current branch' which users might naturally say, but misses common variations like 'PR review', 'pull request', 'diff review', 'review my changes', or 'branch review'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'code review' and 'commits on the current branch' provides some specificity, but it could overlap with general code review skills, git-related skills, or CI/CD pipeline skills without clearer scoping. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with a clear multi-step workflow and good error handling guidance. Its main weakness is moderate verbosity — the examples section largely duplicates the instructions, and some explanatory sections could be tightened. The panels documentation is valuable domain knowledge but could benefit from being extracted to a reference file.
Suggestions
Condense the Examples section — it mostly restates the instructions; consider replacing with a single compact example or removing it entirely since the instructions are already clear.
Consider extracting the Panels explanation into a shared reference file since it likely applies across multiple roborev skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the examples section largely restates the instructions, and the 'When NOT to invoke this skill' and 'IMPORTANT' sections add moderate overhead. The panels explanation is somewhat verbose but contains genuinely useful domain-specific information. | 2 / 3 |
Actionability | Provides concrete, executable bash commands (git rev-parse, roborev review with specific flags), specific tool usage instructions (Task tool with run_in_background and subagent_type), and clear examples of how to construct commands with different flag combinations. The error handling guidance is specific and actionable. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation (step 1: verify ref), a clear decision point for error handling (step 4: check for errors vs success), and appropriate next-step branching (step 5: offer fix only on failure). The feedback loop for errors in step 4 suggests specific recovery commands. | 3 / 3 |
Progressive Disclosure | The skill has reasonable structure with clear sections and a 'See also' section linking to related skills. However, the panels explanation is inlined rather than referenced externally, and the examples section could be more concise or separated. No bundle files are provided, so there's no external reference structure to leverage. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- roborev-dev/roborev
- Commit
a407fdb
- 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.