CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-refine

Use only when the user explicitly invokes /roborev-refine

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/claude/roborev-refine/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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, highly actionable operational spec: exact commands, validation checkpoints, and a well-sequenced fix-review loop with edge cases handled. Its weaknesses are density and monolithic structure — the stall-detection rules and examples read as reference material inlined into the main flow of an already-long single file.

Suggestions

Move the stall/streak signaling rules (the two long paragraphs on file-set and severity streaks) into a references/ file (e.g. references/stall-signals.md) and keep a two-line summary plus the advisory text in SKILL.md.

Tighten the duplicated --since snippet by defining it once and referring back to it for the re-review step, and condense the repeated edge-case clauses in the streak rules into a short bullet list.

Consider moving the two worked examples to a references/examples.md, keeping only one compact example inline to illustrate the loop shape.

DimensionReasoningScore

Conciseness

The body is mostly operational specifics with no explanation of concepts Claude already knows, but it could be tightened: the stall/streak-tracking rules (lines ~226–263) are convoluted and restate edge cases redundantly, and the full --since heredoc snippet is duplicated verbatim. This lands between 'efficient with minor trimmable spots' (4) and clearly 'could be tightened' (3), and the density of the streak section pushes it to 3.

3 / 5

Actionability

Guidance is fully executable: copy-paste-ready bash with safe heredoc patterns, exact roborev CLI invocations with flags, exit-code semantics for --wait, job-ID extraction instructions ('Enqueued job <id> for ...' line), and concrete worked examples covering the common branch and --since flows. Only inherent placeholders (<commit>, <job_id>) remain, which is appropriate.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (sections 1–4 with 3a–3d) with explicit validation checkpoints: branch match check, --since resolution and ancestor verification, test runs after fixes, pass/fail gating on the full-scope re-review, and iteration-limit handling. The skill is itself a feedback loop with error-recovery guidance (daemon errors, hook-review cleanup), matching the top anchor.

5 / 5

Progressive Disclosure

There are no bundle files at all (no references/, scripts/, or assets/), so everything — including the ~38-line self-contained stall-signaling rule spec and the ~35-line examples section — is inlined in a 313-line SKILL.md. Sections are well-organized with clear headers, but reference-grade material is inline in the main flow with no external split, matching 'some structure but content that should be separate is inline'.

3 / 5

Total

16

/

20

Passed

Description

35%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 a pure invocation guard: it states precisely when the skill may run but says nothing about what the skill does. For an explicitly-invoked command this limits auto-trigger harm, but it fails the core job of a description — a user or model reading it learns nothing about the review-fix loop capability.

Suggestions

State the core capability in the description, e.g. 'Iteratively review the current branch or commit range, fix findings, commit, and re-review until all reviews pass. Use only when the user explicitly invokes /roborev-refine.'

Include natural trigger language (review-fix loop, iterate on review findings, re-review after fixing) so the skill is discoverable and distinguishable when users browse the skill list.

Differentiate from sibling skills in one clause, e.g. 'closes the loop by re-reviewing after each fix, unlike /roborev-fix' — the current text is indistinguishable from /roborev-fix's would-be description.

DimensionReasoningScore

Specificity

The description ("Use only when the user explicitly invokes /roborev-refine") names no concrete actions whatsoever — nothing about reviewing, fixing, committing, or iterating. It does not even name a domain, so it sits at the bottom anchor rather than anchor 2.

1 / 5

Completeness

The 'when' is explicit ("only when the user explicitly invokes /roborev-refine") but the 'what' is entirely missing — the description never says the skill runs an iterative review-fix loop. This is exactly anchor 2 ('only when is present without what'); it cannot be 3 because that anchor requires a clear 'what'.

2 / 5

Trigger Term Quality

The only keyword is the literal slash command "/roborev-refine", which is exactly what a user would type to invoke it, but there are no natural task-language variations (review, fix, iterate, re-review). This matches 'some relevant keywords but missing common variations or synonyms' rather than anchor 2, since the one term present is specific and natural, not generic.

3 / 5

Distinctiveness Conflict Risk

The explicit-invocation-only gate gives minimal conflict risk with unrelated skills, but the description does nothing to distinguish this skill from its close siblings (/roborev-fix, /roborev-review-branch), leaving minor overlap risk with closely related skills — anchor 4 rather than 5.

4 / 5

Total

10

/

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-refine/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.