roborev-review
Request a code review for a commit and present the results
58
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 ./internal/skills/codex/roborev-review/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 is brief and identifies the core action (requesting a code review for a commit) but lacks a 'Use when...' clause, detailed capability listing, and sufficient trigger term coverage. It would benefit significantly from explicit trigger guidance and more specific descriptions of what the review covers and how results are presented.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'review my commit', 'code review', 'check my changes', 'review this PR', 'feedback on code'.
Expand the capability description to specify what the review covers (e.g., 'Requests a code review for a given commit, analyzing code quality, potential bugs, and style issues, then presents a structured summary of findings').
Include common keyword variations such as 'PR', 'pull request', 'diff', 'review feedback' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code review) and two actions (request a review, present results), but lacks detail on what 'presenting results' entails or what kind of review is performed. | 2 / 3 |
Completeness | Describes what the skill does (request a code review for a commit and present results) but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also fairly thin, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes 'code review' and 'commit' which are natural terms users might say, but misses common variations like 'PR review', 'pull request', 'review my changes', 'diff', or 'feedback on code'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'code review' and 'commit' provides some specificity, but could overlap with general code review skills, linting tools, or git-related skills without clearer scoping. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%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-crafted skill that efficiently guides Claude through a code review workflow. It provides concrete, executable commands at each step, handles error cases explicitly, and maintains excellent structure with clear conditional logic for different outcomes. The 'When NOT to invoke' section is a thoughtful addition that prevents misuse.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what code reviews are, what git commits are, or how bash works. Every section serves a purpose—usage, when not to invoke, validation, execution, result presentation, and examples. The 'IMPORTANT' and 'When NOT to invoke' sections add genuine value for disambiguation. | 3 / 3 |
Actionability | Provides fully executable bash commands for both validation (`git rev-parse --verify`) and the review itself (`roborev review [commit] --wait`). Clear instructions on how to construct the command with optional flags, how to interpret output, and what to suggest to the user in each scenario. | 3 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced with explicit validation (step 1 validates the commit ref before proceeding), error handling (step 3 covers error cases with specific recovery suggestions), and conditional branching (step 4 differentiates pass vs fail outcomes). The feedback loop of checking errors and suggesting remediation commands is well-defined. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and appropriate length for a single skill file. The 'See also' section provides one-level-deep references to related skills. No bundle files are needed for this skill, and no content is unnecessarily inlined or deeply nested. | 3 / 3 |
Total | 12 / 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
3172d3b
- 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.