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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

85%Weight 40%Scale 1-3

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 clearly sequenced seven-step workflow including validation checkpoints and feedback loops, and clean progressive disclosure with a single-level cross-reference. Its only weakness is moderate verbosity from repeating the operative-only invocation guard across several sections.

Suggestions

Consolidate the repeated operative-only invocation guard (currently restated in 'Explicit invocation only', 'When NOT to invoke this skill', 'IMPORTANT', and the frontmatter) into a single, clearly marked section to reduce token overhead.

Trim restated phrasing in the overlap between step 1 and step 2 where discovery and fetching guidance is duplicated.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and a tight Examples section, but it repeats the operative-only invocation guard multiple times (frontmatter, 'Explicit invocation only', 'When NOT to invoke', 'IMPORTANT') and includes redundant restatements, which could be tightened.	2 / 3
Actionability	It provides fully executable bash commands (roborev show --job, roborev fix --list, roborev comment with heredoc, roborev close) and concrete, copy-paste-ready examples for pasted findings, auto-discovery, and explicit job IDs.	3 / 3
Workflow Clarity	The seven-step workflow is clearly sequenced with explicit validation checkpoints (run tests before closing, confirm comment succeeded before close, final audit verifying closed=true), matching the anchor for clear sequence with feedback loops and checklists.	3 / 3
Progressive Disclosure	The SKILL.md is a well-organized single-file overview with clearly labeled sections and a single-level 'See also' pointer to /roborev-respond; with no bundle files present and no nested references, this matches the simple-skill guidance for scoring 3 on well-organized single-file content.	3 / 3
	Total	11 / 12 Passed

Description

72%Weight 40%Scale 1-3

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 trigger specificity and distinctiveness by gating invocation to an explicit operative /roborev-fix or Agent Hook, but it never describes the skill's actual capability (fixing failing review findings), leaving the 'what' implicit and capping specificity and completeness at 2.

Suggestions

Add an explicit capability statement up front, e.g. 'Fix all open failing roborev review findings in one pass.' so the description answers 'what does this do' rather than only 'when to use it'.

Keep the operative-only trigger guard but lead with the action so the skill reads as a capability description rather than a usage restriction.

Dimension	Reasoning	Score
Specificity	The description names the invocation mechanism ('/roborev-fix', 'direct Agent Hook instruction') but never states the concrete action the skill performs (e.g. fixing failing review findings); it is more of a trigger guard than a capability list, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It explicitly answers 'when' (operative request invoking /roborev-fix, or Agent Hook) but does not state 'what' the skill does; the 'what' is only implied by the skill name, capping completeness at 2 per the missing-action guidance.	2 / 3
Trigger Term Quality	It surfaces natural trigger terms users would say — '/roborev-fix', 'Agent Hook instruction', 'quoted, pasted, or historical text' — with good coverage of the operative-vs-literal distinction a user would reference.	3 / 3
Distinctiveness Conflict Risk	The trigger is a precise, named slash-command with an explicit operative-only constraint, making it clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 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: d121b1a

Reviewed: 2 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.