CtrlK
BlogDocsLog inGet started
Tessl Logo

roborev-review

Request a code review for a commit and present the results

59

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands, a clear validated workflow, and clean single-file organization. Its only weakness is minor redundancy between the Usage and Instructions sections that slightly undercuts token efficiency.

Suggestions

Remove the duplicated command-syntax line from the Instructions header since it already appears in the Usage block, linking instead with "as shown above".

Tighten the Panels subsection by moving the deeper detail (synthesis parent semantics, reviewers-summary line) into a referenced file if the skill grows, keeping the inline explanation to the essential rule.

Consider a one-line "Use when..." trigger in the body to complement the When-NOT-to-invoke section and aid routing.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no concept over-explanation, but the command syntax appears redundantly in both the Usage block ("$roborev-review [commit] [--type security|design] [--panel <name>|none]") and the Instructions header, and the Panels subsection is dense. Not a 3 due to this repeat; not a 1 because it assumes Claude's competence and avoids padding.

2 / 3

Actionability

Provides fully executable commands such as "git rev-parse --verify -- \"$commit^{commit}\"" and "roborev review \"$commit\" --wait [--type <type>]", with concrete examples showing validation, execution, and result presentation. Placeholders are obvious substitutions, making guidance copy-paste ready. Not a 2 because the code is real and complete, not pseudocode.

3 / 3

Workflow Clarity

A clear four-step sequence (Validate inputs → Build and run → Present results → Offer next steps) with an explicit validation checkpoint ("git rev-parse --verify ... || exit 1") and error-recovery guidance for daemon/repo failures. Not a 2 because validation and feedback paths are explicit; not a 1 because the sequence is unambiguous.

3 / 3

Progressive Disclosure

The skill is a single self-contained file with well-organized sections (Usage, When NOT to invoke, Instructions with numbered subsections, Examples, See also) and no nested external references — appropriate for its scope, with no bundle files present to verify. Not a 2 because content is appropriately sectioned rather than a monolithic wall; not a 1 because there are no deep reference chains.

3 / 3

Total

11

/

12

Passed

Description

50%

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 concrete and on-domain but lacks an explicit "Use when..." trigger clause and broader natural-language variations, capping both completeness and trigger quality at 2. It is adequately distinct from generic skills but overlaps with sibling roborev review skills.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when the user asks to review a commit, run a code review, or check changes before merging."

Broaden trigger terms to cover common phrasings like "review my changes", "review this diff", or "check this commit".

Distinguish from sibling skills by noting the single-commit focus, e.g. "for one commit; use $roborev-review-branch for whole-branch reviews."

DimensionReasoningScore

Specificity

Quotes "Request a code review for a commit and present the results" name the domain and two actions (request review, present results), but the action set is not comprehensive — it omits validation, panel fan-out, and fix-offering covered in the body. Not a 3 because it does not list multiple specific concrete actions; not a 1 because the actions are concrete rather than abstract.

2 / 3

Completeness

It states what the skill does ("Request a code review for a commit and present the results") but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2. Not a 1 because the what is clearly stated; not a 3 because when is entirely missing rather than explicit.

2 / 3

Trigger Term Quality

"code review" and "commit" are relevant natural terms a user might say, but coverage is thin with no common variations (e.g. "review my changes", "review this diff", "check this commit"). Not a 3 due to missing common variations; not a 1 because the terms present are natural rather than jargon.

2 / 3

Distinctiveness Conflict Risk

"code review for a commit" carves a recognizable niche but could overlap with sibling review skills referenced in the body ($roborev-design-review, $roborev-review-branch). Not a 3 because overlap with similar review skills remains; not a 1 because it is not generic.

2 / 3

Total

8

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
roborev-dev/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.