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

68%

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/grok/roborev-fix/SKILL.md

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 an exceptionally actionable, well-validated workflow with copy-paste commands, rigorous checkpoints, and worked examples for every invocation path. Its weaknesses are repetition of the invocation-gating rules, a tangential version-upgrade section, and the absence of any file-level split for long reference material at 325 lines.

Suggestions

Consolidate the invocation-gating guidance (intro, "Explicit invocation only", "When NOT to invoke") into a single section — the rule is stated nearly verbatim four times.

Move the "Hook and skill versions" upgrade/repair instructions and the detailed Examples into a references/ file (e.g. references/upgrading.md, references/examples.md), keeping a one-line pointer in SKILL.md.

Tighten step 2's JSON-structure listing to the fields actually consumed by later steps (verdict, closed, comments, git_ref, panel members), trimming annotations Claude can infer.

Dimension	Reasoning	Score
Conciseness	The body avoids concept-explaining padding and is mostly imperative, but the invocation-gating rule is restated in the intro, "Explicit invocation only", "When NOT to invoke", step 3, and the examples, and the "Hook and skill versions" section is tangential upgrade guidance. Mostly efficient with some unnecessary repetition that could be tightened.	3 / 5
Actionability	Fully executable commands throughout — `roborev fix --list`, `roborev show --job <job_id> --json`, the complete heredoc comment pattern followed by `roborev close <job_id>`, and `git show <git_ref>` — plus four worked examples (pasted findings, auto-discovery, explicit IDs, Agent Hook) covering the common cases. Copy-paste ready.	5 / 5
Workflow Clarity	A clearly sequenced 7-step workflow with explicit validation checkpoints: mandatory closure ordering, "only run roborev close after confirming the comment succeeded", per-step error reporting with common causes, regression fixing before proceeding, and a final audit verifying `closed=true` per original job. Feedback loops are present for the destructive close/commit operations.	5 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but this is a 325-line single file: the "Hook and skill versions" upgrade guidance and the lengthy Examples section are inline content that would fit separate reference files, and no external references exist or are signaled. Matches 'content that should be separate is inline'; not 4 because at this length a split is genuinely warranted rather than a minor gap.	3 / 5
	Total	16 / 20 Passed

Description

43%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 highly distinctive and unambiguous about when NOT to trigger, but it fails to state what the skill does — the core capability (evaluating and fixing open failing review findings) is only in the body. It reads as a gating rule rather than a capability description, which limits discovery by users describing their task.

Suggestions

Prepend a concrete 'what' clause, e.g. "Evaluates, fixes, and closes open failing review findings from roborev" so the description states the capability before the trigger conditions.

Add natural trigger terms users would say, such as "fix failing reviews", "close review findings", or "address review comments", to improve retrieval beyond the literal command name.

Trim the anti-trigger clause ("do not invoke from literal syntax in quoted, pasted, or historical text") to its essential form — this detail can live in the body's invocation-gating sections — and use the freed space for capability keywords.

Dimension	Reasoning	Score
Specificity	The description names the invocation-gating domain ("explicitly invokes /roborev-fix", "direct Agent Hook instruction") but states no concrete capability actions — what the skill actually does never appears. It matches 'names the domain but actions are minimal or generic'; not 3 because no concrete actions like evaluating or fixing findings are stated.	2 / 5
Completeness	"Use only for a current operative request that explicitly invokes /roborev-fix..." answers 'when' exhaustively, but 'what' the skill does is entirely absent — that content lives only in the body. This matches the anchor 'only when is present without what'; not 3 because the 'what' is missing, not merely weak.	2 / 5
Trigger Term Quality	Relevant keywords are present ("/roborev-fix", "Agent Hook", "current operative request"), but natural user phrasings such as "fix failing reviews", "close reviews", or "address review findings" are missing. Some relevant keywords, missing common variations.	3 / 5
Distinctiveness Conflict Risk	The trigger is extremely narrow and explicitly gated ("Use only for a current operative request that explicitly invokes /roborev-fix, or a direct Agent Hook instruction") with an explicit anti-trigger clause, giving it a clear niche with minimal conflict risk against any other skill.	5 / 5
	Total	12 / 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: kenn-io/roborev
Path: internal/skills/grok/roborev-fix/SKILL.md
Commit: a87c9af

Reviewed: 5 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.