roborev-fix

Use when the user asks to fix open 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

Quality

74%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./internal/skills/claude/roborev-fix/SKILL.md

Quality

Discovery

72%

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 excels at defining when to use (and not use) the skill, with distinctive trigger terms and clear boundaries. However, it is weak on explaining what the skill actually does—the concrete actions and capabilities are not enumerated. Adding a brief 'what it does' clause would significantly improve it.

Suggestions

Add a clear 'what' clause listing specific actions, e.g., 'Discovers open code reviews from job IDs, applies fixes, and closes review items.'

Expand the capability description to clarify what 'fix' means in practice—does it modify code, post comments, update statuses, etc.?

Dimension	Reasoning	Score
Specificity	The description mentions 'fix open reviews' and 'discover or close reviews' which hint at concrete actions, but it doesn't list specific capabilities comprehensively—what does 'fix' entail? What steps are performed? The actions remain somewhat vague.	2 / 3
Completeness	The 'when' clause is explicit and well-defined, including both positive and negative triggers. However, the 'what does this do' part is weak—it never clearly states what the skill actually does beyond vague references to fixing/closing reviews.	2 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'fix open reviews', '/roborev-fix', 'job IDs', and the negative trigger exclusion ('only pastes review findings') helps disambiguate. These are terms a user would naturally use.	3 / 3
Distinctiveness Conflict Risk	The description is highly distinctive with specific triggers like '/roborev-fix' and 'job IDs', plus an explicit negative boundary ('do not use when the user only pastes review findings'). This makes it very unlikely to conflict with other skills.	3 / 3
	Total	10 / 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 strong, actionable skill with a well-sequenced multi-step workflow, explicit validation checkpoints, and concrete executable commands throughout. Its main weakness is moderate verbosity — the 'When NOT to invoke' section, JSON structure documentation, and three full examples add length that could be trimmed or split into supporting files. Overall it provides excellent guidance for the task.

Suggestions

Trim the 'When NOT to invoke this skill' section to 2-3 sentences — the examples section already demonstrates the distinction clearly.

Consider moving the detailed JSON output structure description (job_id, output, job.verdict, etc.) to a separate reference file to reduce inline length.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining concepts Claude already knows, but some sections are verbose — particularly the lengthy 'When NOT to invoke this skill' section and the detailed JSON structure explanation in step 2. The examples section, while useful, adds significant length and could be more compact.	2 / 3
Actionability	The skill provides fully executable bash commands for every step (roborev show, roborev fix --open --list, roborev comment, roborev close), clear JSON field names to parse, specific sorting/grouping logic, and concrete examples showing exact command sequences. Everything is copy-paste ready.	3 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced with explicit validation checkpoints: step 4 runs tests and requires fixing regressions before proceeding, step 5 only closes after confirming the comment succeeded, and there are clear skip/error-handling conditions at each step. The feedback loop (test → fix regressions → proceed) is well-defined.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and references to CLAUDE.md and /roborev-respond, but the skill is quite long (~150 lines of substantive content) and could benefit from splitting the detailed JSON structure or examples into separate reference files. Without bundle files, everything is inline.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: about 7 hours ago

Table of Contents

Discovery Implementation Validation

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.