roborev-design-review-branch
Request a design review for all commits on the current branch 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/claude/roborev-design-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 communicates a basic action but lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. It has moderate specificity and trigger term coverage but would benefit from listing more concrete capabilities and explicit trigger conditions. The term 'design review' is somewhat ambiguous and could conflict with other review-oriented skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a design review, code review of branch commits, or feedback on recent changes.'
Include natural trigger term variations such as 'code review', 'review my changes', 'branch diff', 'PR feedback' to improve matching.
Expand the capability description to list specific actions, e.g., 'Analyzes commits on the current branch, requests a design review, and presents structured feedback on code quality, architecture, and style.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific action ('request a design review') and a specific context ('all commits on the current branch'), but it only describes one action rather than listing multiple concrete capabilities. It's more specific than vague but not comprehensive. | 2 / 3 |
Completeness | The description answers 'what' (request a design 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 some relevant terms like 'design review', 'commits', and 'current branch' that users might naturally say. However, it misses common variations like 'code review', 'PR review', 'diff review', 'feedback on changes', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'design review' and 'commits on the current branch' provides some specificity, but 'design review' could overlap with other review-related skills (code review, PR review tools). It's somewhat distinctive but not clearly carved out. | 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 skill with clear, actionable steps and good workflow sequencing including validation and error handling. The main weakness is moderate verbosity—the examples section largely duplicates the instructions, and some preamble sections could be tightened. Overall it effectively teaches Claude how to execute this specific task.
Suggestions
Condense or remove the Examples section, as it mostly restates the instructions without adding new information—or reduce it to a single compact example showing only the non-obvious aspects.
Tighten the IMPORTANT preamble by removing the sentence about guidelines vs rigid script, which Claude can infer from context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content. The 'When NOT to invoke this skill' section and the 'IMPORTANT' preamble add tokens that could be trimmed. The examples section largely restates the instructions in a different format, which is somewhat redundant. | 2 / 3 |
Actionability | Provides concrete, executable bash commands at each step (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 presenting results and handling errors. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation (step 1: verify ref), error handling (step 4: report errors with specific recovery suggestions), and conditional branching (pass vs fail in steps 4-5). The feedback loop for invalid inputs and failed reviews is well-defined. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Usage, Instructions with numbered steps, Examples, See also). The 'See also' section provides one-level-deep references to related skills. For a skill of this complexity with no bundle files, the structure is appropriate and easy to navigate. | 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
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.