CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-lookahead-review

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

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/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 highly actionable, well-sequenced instruction body with executable commands, explicit validation, and error-recovery guidance. Its main weakness is redundancy: the command blocks appear twice verbatim and the Examples section repeats the workflow, costing token efficiency and slightly muddying organization.

DimensionReasoningScore

Conciseness

The body is mostly lean with no beginner-concept padding, but the two multi-line command blocks are duplicated verbatim between 'Build the command' and 'Run the review in the background', and the Examples section restates the numbered workflow. Tightening these would remove noticeable redundancy.

3 / 5

Actionability

Fully executable commands cover both the no-commit and commit cases, including a copy-paste heredoc plus `git rev-parse --verify --end-of-options` validation snippet, concrete error recovery (`roborev daemon status`, `roborev init`), and specific job-ID extraction guidance from the `Enqueued job <id>` line. Minor placeholders like `<commit>` are clearly signaled templates.

5 / 5

Workflow Clarity

Five clearly sequenced steps (validate, build, launch background, present, offer next steps) with an explicit validation checkpoint ('If validation fails, inform the user the ref is invalid. Do not proceed.') and an error-recovery feedback loop in step 4. The review is read-only, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and the single file is well-organized with clear headers (Usage, Instructions 1-5, Examples, See also) and a 'See also' cross-reference section. At roughly 165 lines with internally duplicated command blocks that could be factored out, it falls short of the fully clean split envisioned by the top anchor.

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 maximally distinctive but content-free about capabilities: it says when to fire (explicit command invocation only) while omitting entirely what the skill does and the natural vocabulary of its domain. While this is a deliberate design for an explicit-only skill, the rubric scores what is written, and the written text fails the what/when completeness standard.

Suggestions

State the capability explicitly, e.g. 'Requests a time-series look-ahead review of a commit and presents the verdict and findings' — this would raise completeness and specificity from trigger-only to the what+when standard.

Include the domain's natural vocabulary (look-ahead bias, peekahead, future/temporal leakage) so the description documents what users mean when they invoke the command, improving trigger-term coverage.

Keep the 'Use only when the user explicitly invokes /roborev-lookahead-review' clause, but append the what-clause to it rather than letting the invocation guard be the entire description.

DimensionReasoningScore

Specificity

The description states only 'Use only when the user explicitly invokes /roborev-lookahead-review', naming the domain solely via the embedded command name while listing zero concrete actions (no mention of requesting a review, validating a commit, or presenting findings). It exceeds pure abstraction ('Helps with documents') but never reaches the 1-2 named actions of anchor 3.

2 / 5

Completeness

Only the 'when' is present (explicit invocation of the command) with no 'what' whatsoever — matching anchor 2's 'only when is present without what'. It cannot score 3 because the anchor-3 shape requires a clear statement of what the skill does.

2 / 5

Trigger Term Quality

The only keyword is the literal slash command; natural phrases a user would say when needing this skill — 'look-ahead bias', 'peekahead', 'future leakage', 'temporal leakage', 'time-series review' — are all absent. 'lookahead review' inside the command is a recognizable domain term, keeping this above the pure-jargon anchor 1.

2 / 5

Distinctiveness Conflict Risk

The explicit-invocation-only gating (reinforced by 'disable-model-invocation: true' in the frontmatter) creates a clear niche with a distinct, unambiguous trigger and minimal conflict risk with any other skill.

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/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.