roborev-design-review-branch

Use only when the user explicitly invokes /roborev-design-review-branch

Quality

77%

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-design-review-branch/SKILL.md

Quality

Content

92%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 strong, executable workflow: commands are copy-paste ready, input validation and error-recovery paths are explicit, and examples cover the common invocation cases. The only real defect is the verbatim duplication of the base-branch command snippet between steps 2 and 3, plus a little meta-commentary.

Dimension	Reasoning	Score
Conciseness	The body is efficient with concrete command blocks and tight sections, but the full base-branch heredoc snippet is repeated verbatim in both step 2 and step 3, and the "These instructions are guidelines, not a rigid script" paragraph is meta-commentary that could be trimmed. Not 5 because of that duplication; not 3 because the padding is minor rather than pervasive.	4 / 5
Actionability	Fully executable guidance throughout: the direct command `roborev review --branch --wait --type design`, the heredoc plus `git rev-parse --verify --end-of-options` validation snippet, error-recovery suggestions ("Suggest `roborev status` to check the daemon, `roborev init`"), and job-ID extraction instructions ("Look for it in the `Enqueued job <id> for ...` line"). Concrete commands cover the common cases with and without a base branch.	5 / 5
Workflow Clarity	A clear five-step sequence with an explicit validation checkpoint ("If validation fails, inform the user the ref is invalid. Do not proceed.") and feedback loops for error recovery in the presentation step (daemon not running, repo not initialized, review errored). The operation is a read-only review, so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed: the body is a well-organized single-workflow overview (Usage, Instructions, Examples, See also) with every section at the depth the workflow requires and nothing that belongs in a separate reference file. The See-also section cleanly signals sibling skills one level deep.	5 / 5
	Total	19 / 20 Passed

Description

51%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 a deliberate explicit-invocation-only trigger, and it is excellent at that job — unambiguous, impossible to mis-trigger. But as a description it omits what the skill actually does, so a reader learns the invocation condition without the capability. Adding a one-line 'what' would make it complete without sacrificing precision.

Suggestions

Lead with a one-clause 'what', e.g. "Requests a roborev design review for all commits on the current branch and presents the verdict and findings. Use only when the user explicitly invokes /roborev-design-review-branch."

Briefly name the concrete capabilities in the what-clause (runs the review in the background, reports findings grouped by severity, supports --base and --panel options) so the description covers actions, not just the trigger.

Keep the explicit-invocation restriction, but pair it with a natural-language summary of the skill so it is self-describing when read in a skill list.

Dimension	Reasoning	Score
Specificity	The description states only "Use only when the user explicitly invokes /roborev-design-review-branch"; the domain is merely implied by the command name and no concrete actions or capabilities are described. It is not vague (ruling out 1), but lacks the 1-2 concrete actions required for 3.	2 / 5
Completeness	The 'when' is explicit ("Use only when the user explicitly invokes..."), but the 'what' — that the skill requests a design review of all commits on the current branch and presents the results — is entirely absent, matching the anchor for 'only when present without what'. Not 3 because the 'what' is unstated rather than weakly implied; not 1 because the 'when' clause is precise.	2 / 5
Trigger Term Quality	The single trigger term "/roborev-design-review-branch" is exact and unambiguous, which is the complete and correct trigger set for a disable-model-invocation skill. Not 5 because no natural phrasings or synonyms are covered; not 3 because the one term present is precisely the right trigger for this invocation mode.	4 / 5
Distinctiveness Conflict Risk	The literal-command trigger makes accidental invocation for any other skill essentially impossible; it carves out a clear niche with a distinct trigger and minimal conflict risk.	5 / 5
	Total	13 / 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-design-review-branch/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.