CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-design-review

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

Quality

73%

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/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 operational skill: exact commands, explicit validation and error-recovery paths, and clear presentation instructions make it immediately executable. Its only weaknesses are mild redundancy between Instructions and Examples and inline detail (Panels, Examples) that could be slimmed or split if the skill grows.

DimensionReasoningScore

Conciseness

The body is command-first and free of conceptual padding, but the Examples section largely restates the Instructions steps, and meta-guidance like "These instructions are guidelines, not a rigid script" could be trimmed. This matches anchor 4 ("efficient; minor instances of over-explanation that could be trimmed") rather than 5 because of that duplication.

4 / 5

Actionability

Fully executable commands cover both cases (`roborev review --from-skill --wait --type design` and the heredoc + `git rev-parse --verify --end-of-options` snippet), with concrete error branches, panel variants, and next-step offers including job-ID extraction. Placeholders (`<commit>`, `[--panel <name>|none]`) are clearly marked, matching anchor 5 ("fully executable; copy-paste ready").

5 / 5

Workflow Clarity

Four clearly sequenced steps include an explicit validation checkpoint ("If validation fails, inform the user the ref is invalid. Do not proceed.") and a feedback loop for error recovery (diagnose with `roborev daemon status`, `roborev init`, or re-run). This matches anchor 5; the operation is not destructive or batch, so no cap applies.

5 / 5

Progressive Disclosure

The single-file body is well-sectioned with clear headers and a "See also" section, and no bundle files exist to reference. At ~130 lines with the Panels subsection and Examples inlined, minor organization gaps keep it at anchor 4 ("good structure; most content is appropriately placed") rather than 5.

4 / 5

Total

18

/

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 unambiguous about its trigger and effectively prevents misfires, but it says nothing about what the skill actually does. As a capability description it reads as half-complete: the explicit-invocation constraint is well chosen, yet a one-clause summary of the action (requesting a commit design review and presenting results) would make it self-contained.

Suggestions

Add a brief 'what' clause, e.g., "Requests a roborev design review for a commit and presents the verdict and findings. Use only when the user explicitly invokes $roborev-design-review" — this would raise completeness and specificity without weakening the explicit-invocation constraint.

Include the key natural terms "design review" and "commit" as standalone words in the description rather than only embedded inside the invocation token, so the capability is legible even when the command name is not visible.

Optionally note the closely related commands ($roborev-review --type design, $roborev-design-review-branch) to strengthen distinctiveness, though the exact-string trigger already keeps conflict risk minimal.

DimensionReasoningScore

Specificity

The description names the domain only implicitly through the invocation token "$roborev-design-review" ("design review") but lists no concrete actions or capabilities. It fits anchor 2 ("names the domain but actions are minimal or generic") rather than anchor 1 because the text is precise and concrete about the invocation mechanism, not pure abstract language.

2 / 5

Completeness

Only the 'when' is present ("Use only when the user explicitly invokes $roborev-design-review") with no statement of 'what' the skill does — exactly anchor 2 ("only 'when' is present without 'what'"). It cannot score 3 because the 'what' is entirely absent, not merely weakly implied.

2 / 5

Trigger Term Quality

"design review" is a specific, relevant natural phrase embedded in the invocation, but no synonyms or variations (e.g., "review this commit's design", "design critique", "commit review") appear. This matches anchor 3 ("some relevant keywords but missing common variations or synonyms") rather than anchor 2, since the one keyword present is specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

"Use only when the user explicitly invokes" restricts triggering to an exact, literal invocation string, which is a maximally distinct trigger with minimal conflict risk against any other skill. This clearly matches anchor 5 despite lacking a capability summary.

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/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.