CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-design-review-branch

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

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/droid/roborev-design-review-branch/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: executable commands, an explicit validate-then-run-then-report workflow with error recovery, and clear verdict-presentation and next-step guidance. Its only weaknesses are minor — some repeated syntax and bullets that restate the command templates, and a Panels section that carries detail not needed on the happy path.

DimensionReasoningScore

Conciseness

The body is mostly tight operational prose with no explanations of concepts Claude already knows, but there is minor repetition: the command syntax appears three times (Usage line 13, Instructions line 46) and the bullets at lines 74-77 restate what the two command templates already show. This matches anchor 4 (efficient, minor instances that could be trimmed); not 5 because of that redundancy, and not 3 because the padding is limited and incidental.

4 / 5

Actionability

Guidance is fully executable: the default command `roborev review --from-skill --branch --wait --type design`, the base-branch snippet with `git rev-parse --verify --end-of-options "$branch" || exit 1`, and concrete recovery commands (`roborev daemon status`, `roborev init`) are all copy-paste ready, and the Examples section covers both the default and base cases end-to-end with concrete job IDs. This matches anchor 5; it is not 4 because there are no meaningful gaps in the common cases.

5 / 5

Workflow Clarity

The four-step sequence (validate inputs → build and run → present results → offer next steps) has explicit checkpoints: "If validation fails, inform the user the ref is invalid. Do not proceed", error-output handling with recovery suggestions, and verdict-conditional next steps (Fail → offer /roborev-fix with the extracted job ID; Pass → confirm only). This matches anchor 5 (explicit validation, feedback loops for error recovery); not 4 because the checkpoints are explicit rather than implicit.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the ~135-line body is well-sectioned (Usage, Sandbox access, When NOT to invoke, numbered Instructions, Examples, See also) with everything needed to execute inlined. This matches anchor 4 (good structure, content appropriately placed, minor organization gaps); it is not 5 because the Panels subsection detail and the repeated command syntax could be consolidated or split out, and not 3 because nothing is buried and no content obviously belongs in a separate file.

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 functions well as a precise invocation gate but fails as a capability summary: it answers 'when' with a single exact trigger and nothing else. A user scanning skill descriptions would learn nothing about what the skill actually does. Adding a one-clause statement of the capability would lift both completeness and specificity substantially.

Suggestions

Lead with a 'what' clause, e.g. "Runs a design review over all commits on the current branch via roborev and presents the verdict and findings grouped by severity. Use only when the user explicitly invokes /roborev-design-review-branch."

Surface 2-3 natural keywords (design review, branch commits, review findings) in the description so the skill's purpose is discoverable when listing or searching skills, even though triggering stays explicit-only.

Briefly differentiate from sibling skills (e.g. mention it is the branch-wide counterpart to /roborev-design-review for a single commit) to aid users choosing between them.

DimensionReasoningScore

Specificity

The description is "Use only when the user explicitly invokes /roborev-design-review-branch" — the domain (branch design review) is conveyed only through the command name and no concrete capability actions are stated anywhere. It is not 1 because the named command is specific rather than pure abstract language, and not 3 because zero actions are described (the body's "Request a design review for all commits on the current branch and present the results" is not in the description).

2 / 5

Completeness

The 'when' is explicit and crisp ("Use only when the user explicitly invokes /roborev-design-review-branch") but the 'what' is entirely missing — the description never says it runs a design review over branch commits or presents results. This is exactly anchor 2 (only 'when' present without 'what'); not 3 because anchor 3 requires a clear 'what', and not 1 because the 'when' is unambiguous.

2 / 5

Trigger Term Quality

Natural keywords "design", "review", and "branch" appear, but only embedded inside the command name, with no standalone phrases or variations like "review the branch's design" or "design review the branch". This matches anchor 3 (relevant keywords but missing common variations); it falls short of 4 because users' natural phrasings are absent, though that is partly deliberate for an explicit-invocation-only skill.

3 / 5

Distinctiveness Conflict Risk

By restricting activation to the exact literal command "/roborev-design-review-branch", the description has minimal conflict risk — it will not fire on generic review requests, unlike sibling skills such as /roborev-review-branch or /roborev-design-review. This matches anchor 5 (clear niche with distinct triggers); it is not 4 because the explicit-invocation gate removes even minor overlap ambiguity.

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/droid/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.