roborev-design-review
Request a design review for a commit 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-design-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 too brief and lacks explicit trigger guidance ('Use when...'), making it difficult for Claude to reliably select this skill from a large pool. While it names a specific domain (design review + commit), it doesn't explain what a design review entails or provide enough natural language trigger terms for robust matching.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a design review, architecture feedback, or wants to evaluate the design quality of a commit or changeset.'
List more specific actions the skill performs, such as 'Submits a commit to a design review service, retrieves reviewer feedback, and formats the results as a summary with actionable suggestions.'
Include natural trigger term variations like 'architecture review', 'code design feedback', 'review my changes', or 'design critique' to improve matching coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (design review) and two actions (request a review, present results), but lacks detail on what the review entails, what kind of commit, or what 'present the results' means concretely. | 2 / 3 |
Completeness | Describes what it does at a high level 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 the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'design review' and 'commit' which are relevant trigger terms, but misses common variations like 'code review', 'PR review', 'review feedback', or tool-specific terms that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | 'Design review for a commit' is somewhat specific and distinguishes it from general code review or linting skills, but could overlap with other review-related skills since 'design review' is not precisely defined. | 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 skill with strong actionability and workflow clarity. The 5-step process is clearly sequenced with proper validation, error handling, and conditional logic. The main weakness is moderate verbosity — the examples section largely duplicates the instructions, and some explanatory text could be trimmed without losing clarity.
Suggestions
Trim or remove the Examples section, as it mostly restates the instructions already covered in steps 1-5 without adding new information.
Tighten the 'IMPORTANT' and 'When NOT to invoke' preamble sections — consider merging them into a single brief note.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy. The 'When NOT to invoke this skill' and 'IMPORTANT' sections add useful context, but the examples section largely restates the instructions already given. The panels explanation could be tighter. Some phrases like 'These instructions are guidelines, not a rigid script' are filler. | 2 / 3 |
Actionability | The skill provides concrete, executable bash commands (git rev-parse, roborev review with specific flags), specifies exact tool usage (Task tool with run_in_background and subagent_type), and gives clear instructions for constructing commands with different argument combinations. The error handling guidance is specific with concrete suggestions (roborev status, roborev init). | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation (step 1 validates the commit ref before proceeding), error handling at multiple points (invalid ref in step 1, command errors in step 4), and conditional branching (pass vs fail in steps 4-5). The feedback loop for errors includes specific recovery suggestions. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections and a 'See also' section pointing to related skills. However, the content is somewhat long for a single file with no bundle files to offload detail to. The panels explanation and examples sections could potentially be separated. For a skill of this complexity, the inline approach is acceptable but not optimal. | 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.