CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-design-review-branch

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

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/codex/roborev-design-review-branch/SKILL.md
SKILL.md
Quality
Evals
Security

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, lean operational instruction set: exact executable commands, an explicit input-validation gate, error-handling and result-presentation guidance, and concrete examples. Its only weakness is minor redundancy where the bullets under step 2 re-explain flags already shown in the command snippets.

DimensionReasoningScore

Conciseness

The body is efficient with no explanations of concepts Claude already knows, but the bullets after the two command variants ("If `--base` is specified, include it (otherwise auto-detects the base branch)") restate what the code blocks already show, and the "These instructions are guidelines, not a rigid script" paragraph is mild meta-padding — minor instances that could be trimmed, matching the level-4 anchor rather than 5.

4 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: `roborev review --from-skill --branch --wait --type design [--panel <name>|none]`, the heredoc + `git rev-parse --verify --end-of-options` snippet for base validation, plus remediation commands (`roborev daemon status`, `roborev init`, `$roborev-fix <job_id>`), with concrete worked examples in the Examples section.

5 / 5

Workflow Clarity

The four-step sequence has an explicit validation checkpoint ("If validation fails, inform the user the ref is invalid. Do not proceed.") and an error-recovery path in step 3 (suggest `roborev daemon status`, `roborev init`, or re-running), and the review operation is read-only so the destructive/batch cap does not apply — matching the level-5 anchor with explicit validation and error feedback loops.

5 / 5

Progressive Disclosure

The skill is self-contained with no bundle files; all content (usage, sandbox access, invocation guardrails, instructions, panels, examples) is appropriately inline for a command-invocation skill, sections are well-organized and easy to navigate, and the "See also" pointers to sibling skills are clearly signaled one-level navigation with no nested references.

5 / 5

Total

19

/

20

Passed

Description

43%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 excellent as a trigger guardrail — unambiguous, distinct, zero conflict risk — but it completely omits the capability statement: a reader cannot learn what the skill actually does (request a design review for branch commits and present results) without opening the body. This caps completeness and specificity at the low end.

Suggestions

Add a 'what' clause stating the capability, e.g., 'Requests a design review for all commits on the current branch via the roborev daemon and presents the verdict and findings grouped by severity.'

State the trigger alongside the capability in one sentence ('Use only when the user explicitly invokes $roborev-design-review-branch') so both 'what' and 'when' are answered explicitly in the description.

Optionally name the key sub-capabilities (base-branch targeting via --base, panel multi-reviewer reviews via --panel, offering $roborev-fix for findings) to raise specificity without adding fluff.

DimensionReasoningScore

Specificity

The description names the domain only through the invocation token ("$roborev-design-review-branch") and states no concrete actions or capabilities whatsoever — nothing like 'requests a design review and presents findings'. This is above anchor 1 (not pure abstract language) but below anchor 3, which requires 1-2 concrete actions, so it sits at anchor 2 ('names the domain but actions are minimal or generic' — and here, absent).

2 / 5

Completeness

Only the 'when' is present and it is maximally explicit ("Use only when the user explicitly invokes..."), but the 'what' is entirely absent — the description never states what the skill does. This matches anchor 2 verbatim ('only when is present without what', example: 'Use when working with documents'); it cannot be 3 because that anchor requires a clear 'what', and cannot be 1 because the 'when' is neither missing nor vague.

2 / 5

Trigger Term Quality

Some relevant natural keywords are present ("design review", "branch", "invokes"), but common variations users would say are missing (e.g., 'review the branch's design', 'design issues') — matching anchor 3 ('some relevant keywords but missing common variations or synonyms'), and clearly below anchor 4's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

By restricting triggering to a single literal command token ("Use only when the user explicitly invokes $roborev-design-review-branch") the description carves out a clear niche with a distinct trigger and minimal conflict risk with any other skill — matching anchor 5.

5 / 5

Total

12

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

kenn-io/roborev

Path

internal/skills/codex/roborev-design-review-branch/SKILL.md

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.