CtrlK
BlogDocsLog inGet started
Tessl Logo

roborev-review-branch

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

53

Quality

67%

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-branch/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 content is a strong operational skill: fully executable commands, an explicit five-step workflow with validation and error recovery, and thoughtful guardrails (sandbox retry, when-not-to-invoke, panel synthesis). Its main weakness is token efficiency — the base-branch bash snippet is repeated in full — and it could shed length by factoring that snippet or panel details into a reference file.

Suggestions

Define the base-branch validation/fetch snippet once and reference it from section 3 instead of duplicating all ~30 lines verbatim.

Move the Panels subsection and ref-recovery explanation into a reference file (e.g. references/panels.md) to keep SKILL.md as a lean overview.

Trim the redundant plain-language re-statements of the command construction rules that immediately follow the code block in section 2.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, but the ~30-line base-branch bash snippet is duplicated verbatim in sections 2 and 3, which is more than 'minor instances of over-explanation' and a real tightening opportunity.

3 / 5

Actionability

Fully executable, copy-paste-ready commands including the complete ref-validation/fetch-recovery shell snippet, concrete error remedies ('roborev status', 'roborev init'), and worked examples covering default and base-branch cases.

5 / 5

Workflow Clarity

Five clearly numbered steps with explicit validation ('If validation fails... Do not proceed'), error-recovery guidance for daemon and repo failures, background-task completion handling, and a Panels subsection disambiguating synthesis vs reviewer jobs.

5 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized with clear section headers (Usage, Sandbox access, When NOT to invoke, Instructions 1-5, Examples, See also), but at ~210 lines the duplicated snippet and panel details could be split into a reference file.

4 / 5

Total

17

/

20

Passed

Description

36%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 distinctive and appropriately strict about explicit-only invocation, but it says nothing about what the skill actually does (request a code review of all commits on the current branch via roborev). It is a deliberate guard for a disable-model-invocation skill rather than a capability description, which costs it on specificity, triggers, and completeness.

Suggestions

Add a concise 'what' clause, e.g. 'Requests a code review of all commits on the current branch via the roborev CLI and presents the verdict and findings.'

Include the domain keywords ('code review', 'branch', 'findings') so the skill's purpose is legible in listings even though invocation remains explicit-only.

Optionally note the variant flags (--base, --type security|design, --panel) in one short phrase to round out coverage without inviting auto-invocation.

DimensionReasoningScore

Specificity

The description states no concrete actions at all — the domain (branch code review) is only inferable from the command name 'roborev-review-branch', matching 'Names the domain but actions are minimal or generic' rather than anchor 1, since it is not pure abstract filler like 'Helps with documents'.

2 / 5

Completeness

Only 'when' is present ('Use only when the user explicitly invokes /roborev-review-branch') with no statement of what the skill does, matching the anchor example 'Use when working with documents'; it cannot reach 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

The only trigger signal is the literal slash-command token '/roborev-review-branch'; natural phrases users would say ('review this branch', 'code review my changes') are entirely absent, fitting 'One or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

The description gates invocation on the exact literal command, giving a clear niche with distinct triggers and minimal conflict risk with native review skills — it explicitly tells non-explicit requests to use native behavior in the body.

5 / 5

Total

11

/

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
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.