roborev-review
Request a code review for a commit and present the results
53
58%
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 provides a basic sense of what the skill does but lacks the detail and explicit trigger guidance needed for reliable skill selection. It names the core domain (code review for commits) but omits a 'Use when...' clause, specific trigger terms, and detailed capability descriptions that would help Claude distinguish this skill from similar ones.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'code review', 'review my commit', 'PR feedback', 'pull request review', 'review changes'.
Expand the capability description to specify concrete actions, e.g., 'Submits a commit for automated code review, retrieves reviewer feedback, and presents issues, suggestions, and approval status'.
Clarify the scope to improve distinctiveness—mention the specific review tool or service used, and whether this covers PRs, individual commits, or diffs.
| 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 it does (request a code review for a commit and present results) but has no 'Use when...' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also fairly thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes natural terms like 'code review' and 'commit' which users would say, but misses common variations like 'PR review', 'pull request', 'review feedback', 'diff review', or tool-specific terms. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'code review' and 'commit' provides some specificity, but it could overlap with general code review skills, PR management skills, or git-related skills without clearer scoping. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%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 that clearly guides Claude through a multi-step review workflow with proper validation and error handling. The workflow is well-sequenced with explicit checkpoints and conditional logic for different outcomes. Minor verbosity in the panels explanation and some redundancy between instructions and examples prevent a perfect conciseness score.
Suggestions
Trim the 'IMPORTANT' paragraph — the fact that bash commands must be executed is already evident from the instructions containing bash blocks.
Consider condensing the examples section since they largely restate the instructions; a single example showing the less obvious panel case would be more token-efficient.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy. The 'IMPORTANT' section restates what's implied by the instructions. The panels explanation is somewhat verbose, and the 'When NOT to invoke' section, while useful, adds tokens for an edge case. The examples section partially repeats the instructions. | 2 / 3 |
Actionability | Provides fully concrete, executable bash commands at each step (git rev-parse, roborev review with specific flags). The flag combinations are clearly specified, and the examples show exact command construction. Claude knows exactly what to run and when. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence (validate → build/run → present → offer next steps) with explicit validation at step 1 (git rev-parse check with failure handling), error handling in step 3 (suggesting roborev status/init), and conditional branching for pass/fail verdicts. The feedback loop for errors is well-defined. | 3 / 3 |
Progressive Disclosure | For a skill of this scope, the content is well-organized with clear sections. References to related skills ($roborev-fix, $roborev-design-review, $roborev-review-branch) are cleanly listed in 'See also'. No bundle files are needed, and the content doesn't warrant splitting into multiple files. | 3 / 3 |
Total | 11 / 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.