CtrlK
BlogDocsLog inGet started
Tessl Logo

roborev-fix

Use when the user asks to fix open failing reviews, invokes /roborev-fix, or provides job IDs; do not use when the user only pastes review findings with no request to discover or close reviews

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable workflow skill with clear sequencing and validation checkpoints. It loses points on conciseness (some redundancy) and progressive disclosure (a long monolithic file with everything inline).

Suggestions

Collapse the three 'Skip any reviews where...' bullets into a single consolidated skip rule to remove redundancy.

Move the lengthy worked Examples and the panel-member edge-case detail into a separate reference file referenced from the body, leaving the core workflow leaner.

State the commit-ordering policy once in the main step rather than re-explaining it inside each example.

DimensionReasoningScore

Conciseness

Mostly efficient and earned for genuine complexity (closure ordering, panel parents, heredoc safety), but redundancy remains — three separate 'Skip any reviews where...' bullets and repeated commit-ordering notes across the examples.

2 / 3

Actionability

Provides fully executable commands (roborev show/fix/comment/close, go test, git show) and a complete, copy-paste heredoc comment template with an explicit safety warning about shell metacharacters.

3 / 3

Workflow Clarity

A clear 7-step sequence with explicit validation checkpoints (run tests, 'Only if the comment above succeeded', audit closed=true) and feedback loops for the batch/destructive close-and-commit operations.

3 / 3

Progressive Disclosure

Well-organized into labeled sections, but it is a monolithic ~180-line single file with no reference structure; detailed examples and panel edge-case guidance sit inline rather than in split-out reference files.

2 / 3

Total

10

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, well-constructed description that answers both what and when with natural trigger terms and an explicit negative-trigger boundary. The only weak spot is specificity, since it names a single core action rather than a comprehensive set.

DimensionReasoningScore

Specificity

Names the domain ('open failing reviews') and the concrete action ('fix') plus implicit discover/close, but offers only one core action rather than a comprehensive list of specific actions.

2 / 3

Completeness

An explicit 'Use when...' clause answers when, 'fix open failing reviews' answers what, and a 'do not use when...' negative trigger sharpens the boundary.

3 / 3

Trigger Term Quality

Includes natural terms users would actually say — 'fix open failing reviews', 'job IDs', and the '/roborev-fix' slash command — giving good coverage.

3 / 3

Distinctiveness Conflict Risk

The carve-out 'do not use when the user only pastes review findings' clearly distinguishes it from sibling review skills, giving it a distinct niche.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
roborev-dev/roborev
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.