roborev-review

Use only when the user explicitly invokes /roborev-review

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

73%Weight 40%Scale 1-5

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

The body is a well-sequenced, highly actionable instruction set with real validation checkpoints and error-recovery guidance, appropriate for a non-destructive review-launching skill. Its main weakness is token efficiency: the command-construction blocks are duplicated across sections 2 and 3, and the usage syntax is restated three times.

Suggestions

Define the commit and no-commit command snippets once (e.g. in 'Build the command') and have section 3 reference them instead of repeating them verbatim, saving ~20 lines.

Fix 'subagent_type: "Bash"' — Bash is a tool, not a subagent type; instruct running the command as a background Bash task instead.

State the usage syntax once and remove the duplicate in the Instructions header, since it already appears in the Usage section.

Dimension	Reasoning	Score
Conciseness	The full command-construction snippets (both the no-commit and commit-with-ref variants) are duplicated verbatim in sections 2 and 3, and the usage syntax line appears three times, so roughly 20 lines could be removed. Otherwise the body assumes Claude's competence and has no concept explanations, placing it at 'mostly efficient but could be tightened' rather than the noticeably padded level 2.	3 / 5
Actionability	Guidance is concrete and executable: exact bash heredoc snippets with 'git rev-parse --verify --end-of-options', full 'roborev review --wait' command forms, and specific presentation steps. The minor gap is 'subagent_type: "Bash"', which names a tool as a subagent type, keeping it below the fully copy-paste-ready level 5.	4 / 5
Workflow Clarity	The five steps are clearly sequenced with explicit validation (rev-parse gate with 'If validation fails... Do not proceed') and error-recovery feedback (daemon not running / repo not initialized → 'roborev status' / 'roborev init' / re-run), plus explicit handling of the panel-vs-single-agent case. This matches the anchor for clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist and all content is appropriately inline for a single workflow, with clean section headers (Usage, Instructions, Examples, See also) making navigation easy. It falls short of the anchor-5 ideal of a tight overview because the body is long for a command wrapper and the repeated command blocks and usage line create minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

31%Weight 40%Scale 1-5

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 highly distinctive and unambiguous about when to fire, but it says nothing about what the skill does. For a disable-model-invocation skill this is a deliberate design, yet the 'what' half ('Request a code review for a commit and present the results') could be stated in one clause at no cost.

Suggestions

Add a 'what' clause, e.g. 'Request a roborev code review for a commit and present the verdict and findings. Use only when the user explicitly invokes /roborev-review.'

Include the natural domain keywords users associate with the task ('code review', 'review findings', 'security review') so the skill is legible even in explicit-selection UIs.

Keep the explicit-invocation clause, but consider mentioning the security/design review variants so the description reflects the skill's actual capability surface.

Dimension	Reasoning	Score
Specificity	The description ('Use only when the user explicitly invokes /roborev-review') names zero concrete actions and does not even mention the domain (code review), matching the anchor for entirely vague with no concrete actions. It is not a 2 because that anchor requires naming the domain, which this omits.	1 / 5
Completeness	The 'when' is fully explicit ('Use only when the user explicitly invokes /roborev-review'), but the 'what' — requesting a code review and presenting results — is entirely absent from the description. This exactly matches the anchor for only 'when' present without 'what', and is not a 3 since that anchor requires a clear 'what'.	2 / 5
Trigger Term Quality	The only keyword is the literal command '/roborev-review' plus 'explicitly invokes'; natural phrases a user would say such as 'code review' or 'review this commit' are absent. It is above 1 because the trigger that exists is real and specific rather than generic jargon, but it is a single keyword, matching the one-or-two-generic-keywords anchor.	2 / 5
Distinctiveness Conflict Risk	The explicit-invocation-only trigger gives this skill a clear niche that no other skill shares and makes accidental triggering essentially impossible, matching the anchor for a clear niche with distinct triggers and minimal conflict risk. Not a 4, since there is no overlap with related review skills — the trigger is a single unique literal command.	5 / 5
	Total	10 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: kenn-io/roborev
Path: internal/skills/claude/roborev-review/SKILL.md
Commit: a87c9af

Reviewed: 5 days 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.