CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-lookahead-review-branch

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

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-lookahead-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.

A well-structured, highly actionable operational skill with explicit validation and error-handling checkpoints. Its main flaw is redundancy: both bash command variants are repeated in full across sections 2 and 3.

Suggestions

In section 3 ('Run the review in the background'), reference the commands from section 2 ('Build the command') instead of repeating both full bash blocks verbatim, saving ~40 lines.

Consider trimming the Panels subsection to the essentials and moving extended panel semantics (synthesis parent, default_panel, post-commit behavior) next to where the --panel flag is introduced.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes competence (no explaining what a review or git branch is), but both full command blocks are duplicated verbatim in 'Build the command' and 'Run the review in the background', wasting roughly 40 lines. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than anchor 2, since the padding is confined to one clear duplication.

3 / 5

Actionability

Commands are copy-paste ready and complete, e.g. 'roborev review --from-skill --branch --wait --type lookahead [--panel <name>|none]' and the heredoc-based 'read -r branch <<"ROBOREV_REF" ... git rev-parse --verify --end-of-options "$branch" || exit 1' snippet. Worked examples cover the default and --base cases with expected user-facing messages, matching the fully-executable anchor.

5 / 5

Workflow Clarity

A clear five-step sequence (validate inputs, build command, run in background, present results, offer next steps) with explicit validation ('git rev-parse --verify --end-of-options "$branch" || exit 1') and error-recovery guidance ('Suggest roborev daemon status to check the daemon, roborev init if the repo is not initialized, or re-running the review'). This is a read-only review skill, so the destructive/batch validation cap does not apply, and the feedback-loop anchor is satisfied.

5 / 5

Progressive Disclosure

No bundle files exist and the skill is self-contained with clear, navigable sections ('Validate inputs', 'Run the review in the background', 'Panels', 'See also'). It falls short of anchor 5 only because the inline Panels subsection and the duplicated command blocks could be organized more tightly; nothing here needs external file splitting.

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 functions purely as an explicit-invocation guard and is maximally distinctive, but it states no capabilities and no natural trigger language. A user scanning descriptions learns nothing about what the skill does.

Suggestions

Add a 'what' clause, e.g. 'Requests a time-series look-ahead review of all commits on the current branch and presents the verdict and findings. Use only when the user explicitly invokes /roborev-lookahead-review-branch.'

Include natural synonyms users would say — 'future leakage', 'peekahead', 'temporal leakage' — so the skill's purpose is discoverable from the description even though invocation is explicit-only.

State the outcome the user gets (verdict Pass/Fail plus findings grouped by severity) to round out the capability coverage.

DimensionReasoningScore

Specificity

The description 'Use only when the user explicitly invokes /roborev-lookahead-review-branch' names the domain only via the command name and describes no concrete actions the skill performs. It scores above anchor 1 because it is not abstract or vague — it precisely names the skill — but below anchor 3 because no capability (request a look-ahead review, present results) is stated.

2 / 5

Completeness

Only the 'when' is present (explicit invocation of the command); the 'what' — what the skill actually does — is entirely missing. This matches anchor 2 exactly ('only when is present without what') and cannot score 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

The only terms present are 'lookahead', 'review', and 'branch' embedded in the technical command name; natural phrases a user would say — 'future leakage', 'peekahead', 'temporal leakage' — are absent. This sits between 'no natural keywords; only technical jargon' (1) and 'some relevant keywords but missing common variations' (3).

2 / 5

Distinctiveness Conflict Risk

Triggering is gated on the exact literal command '/roborev-lookahead-review-branch', giving it a clear niche with minimal conflict risk even against sibling roborev skills. No generic language exists that could collide with unrelated skills.

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

Path

internal/skills/claude/roborev-lookahead-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.