CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-review

Use only when the user explicitly invokes /roborev-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/claude/roborev-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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: fully executable commands, a validated multi-step workflow with error recovery, and clear organization. Its main inefficiency is the verbatim duplication of the command snippets between steps 2 and 3.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but the full heredoc + roborev review command blocks are duplicated verbatim in steps 2 and 3, plus a few filler sentences ('This lets the user continue working while the review runs') — anchor 2 overstates the issue since nearly all content is operational guidance, while anchor 4 understates the duplication, so anchor 3's 'could be tightened' fits best.

3 / 5

Actionability

Fully executable, copy-paste-ready commands including the commit-validation heredoc with 'git rev-parse --verify --end-of-options', exact --type/--panel flag semantics, error-recovery commands ('roborev daemon status', 'roborev init'), and worked examples covering both the default and security cases — matches anchor 5.

5 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit validation checkpoint ('git rev-parse ... || exit 1', 'If validation fails... Do not proceed') and error-recovery guidance in step 4 (report error, suggest daemon status/init, re-run) — anchor 5's explicit validation and feedback loops are present; the operation is read-only so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist or are needed; the skill is self-contained with well-organized, clearly headed sections and no buried references — good structure (anchor 4), but at ~160 monolithic lines with the panels subsection and extended examples being plausible split-out candidates, it falls short of anchor 5's 'clear overview with well-signaled one-level-deep references'.

4 / 5

Total

17

/

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 highly effective as an explicit-invocation guard — unambiguous, distinctive, and impossible to mis-trigger — but it omits any statement of what the skill actually does. A user scanning the skill list learns the trigger condition and nothing about the capability.

Suggestions

State the capability in the description, 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.'

Mention the supported variations (security/design review types, panel reviews) so the 'what' is concrete rather than implicit in the command name.

Keep the 'Use only when...' restriction as the trailing trigger clause so the explicit-invocation guard is preserved while adding the missing 'what'.

DimensionReasoningScore

Specificity

"Use only when the user explicitly invokes /roborev-review" states an invocation condition but names zero concrete actions — not abstract fluff (anchor 1) yet entirely action-free, matching anchor 2's 'actions are minimal or generic' better than anchor 1's 'pure abstract language'.

2 / 5

Completeness

Only 'when' is present without 'what': the 'when' is explicit and unambiguous, but the description never states what the skill does (request a roborev code review and present results) — this is the literal anchor 2 case, not anchor 3 which requires a clear 'what'.

2 / 5

Trigger Term Quality

The single trigger term "/roborev-review" is exactly what a user types to invoke the skill, but no natural synonyms or related phrases (e.g. 'code review') appear — anchor 4 ('good keyword coverage; a few natural terms missing') fits better than anchor 3 because the one term present is precisely the natural invocation phrase.

4 / 5

Distinctiveness Conflict Risk

Triggering only on the literal command "/roborev-review" creates a clear niche with minimal conflict risk even against the sibling /roborev-design-review skill — matches anchor 5, and anchor 4's 'minor overlap risk' does not apply since no plausible overlap scenario exists.

5 / 5

Total

13

/

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/claude/roborev-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.