roborev-fix

Use only for a current operative request that explicitly invokes /roborev-fix, or a direct Agent Hook instruction; do not invoke from literal syntax in quoted, pasted, or historical text

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/claude/roborev-fix/SKILL.md

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 body is a highly actionable, well-sequenced workflow with strong validation checkpoints and copy-paste examples. Its main weakness is redundancy in the invocation-gating sections and a long monolithic structure that could be split into reference files.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and free of basic-concept padding, but the invocation-gating message recurs across "Explicit invocation only", "When NOT to invoke this skill", and "Scope authority", which could be consolidated; this matches the anchor for mostly efficient content with some unnecessary explanation that could be tightened.	3 / 5
Actionability	It provides copy-paste-ready commands (roborev show/fix --list/comment/close), a concrete heredoc comment template, and a documented JSON output structure with worked examples covering pasted-findings, auto-discovery, explicit IDs, and Agent Hook cases, matching fully executable guidance.	5 / 5
Workflow Clarity	A clear 7-step sequence includes explicit validation checkpoints (prove each finding before editing, run focused then required tests, mandatory comment-then-close ordering, final audit verifying closed=true), with feedback loops for error recovery on a destructive/batch operation.	5 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained with well-organized section headers and clear navigation; it is a long monolithic document where the JSON-structure detail and examples could plausibly live in separate references, matching good structure with minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

52%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 excels at distinctiveness and explicit invocation gating but is weakened by omitting what the skill actually does, leaving the capability implied only by its name. Trigger terms are concrete but narrow.

Suggestions

Lead with a concrete capability clause, e.g. "Evaluates and addresses open failing review findings in one pass.", before the invocation-gating guidance so the "what" is explicit.

Add natural trigger synonyms users might say (e.g. "fix open findings", "close failing reviews") alongside the literal /roborev-fix token.

Tighten the gating language; the same anti-misfire rule is repeated across the description, "Explicit invocation only", and "When NOT to invoke this skill", which dilutes the core capability statement.

Dimension	Reasoning	Score
Specificity	The description names the skill's trigger domain ("explicitly invokes /roborev-fix, or a direct Agent Hook instruction") but states no concrete actions describing what the skill does; the actual capability (evaluate and fix failing review findings) is absent, matching the anchor where the domain is named but actions are minimal.	2 / 5
Completeness	The "when" is exceptionally explicit (current operative request invoking /roborev-fix or a direct Agent Hook, with an explicit anti-misfire clause), but the "what" is only weakly implied by the skill name rather than stated; one half is clear while the other is weakly implied.	3 / 5
Trigger Term Quality	It includes concrete trigger terms a user would say ("/roborev-fix", "Agent Hook instruction") but the vocabulary is narrow and specialized with no synonyms or common variations, fitting the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche with distinct triggers and actively suppresses mis-invocation ("do not invoke from literal syntax in quoted, pasted, or historical text"), giving minimal conflict risk with other skills.	5 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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: roborev-dev/roborev
Path: internal/skills/claude/roborev-fix/SKILL.md
Commit: 1a1900d

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.