roborev-respond

Use only when the user explicitly invokes /roborev-respond

Quality

73%

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-respond/SKILL.md

Quality

Content

88%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 example of an action-oriented, executable skill: concrete bash commands, a validated workflow with error-recovery guidance, and clear examples for both invocation variants. Its only weaknesses are mild padding (duplicated example commands, a meta-instructions paragraph) and everything living in one slightly long file rather than being split or trimmed.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence (no concept explanations), but the "These instructions are guidelines, not a rigid script" meta-paragraph and an Examples section that repeats the identical `comment && close` command twice are trimmable padding — 'minor instances of over-explanation that could be trimmed', not the every-token-earns-its-place of anchor 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands (`roborev show --job <job_id> --json`, `roborev comment --job <id> "<message>" && roborev close <id>`) with quoting-escape guidance, and the Examples cover both the with-message and no-message cases — an exact anchor 5 match.	5 / 5
Workflow Clarity	A clear three-step sequence with explicit pre-close validation (inspect the job, check `panel_role`, resolve the synthesis parent) and a verification step enumerating failure causes with remedies (`roborev init`, daemon not running). The destructive close operation is validated, so the missing-validation cap does not apply; error-recovery guidance matches anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist, and the single SKILL.md is well-sectioned (Usage, Sandbox access, Instructions, Examples, See also) with a clear one-level pointer to `/roborev-fix`. However, the ~104-line body inlines everything — including a 26-line Examples section — so it exceeds the under-50-line simple-skill case that would allow a 5, landing on 'good structure; minor organization gaps'.	4 / 5
	Total	18 / 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 maximally restrictive and conflict-free but describes no capabilities whatsoever: a user reading it learns only when the skill fires, not what it does. This is partly mitigated by the skill being explicitly invocation-only (disable-model-invocation: true), so the description need not win a model-trigger competition, but it still fails to inform a user browsing the skill list what the skill does.

Suggestions

Add a 'what' clause naming the concrete actions, e.g. "Records a comment on a roborev code review job and closes it. Use only when the user explicitly invokes /roborev-respond."

Include the natural phrases users would say in this context (respond to a review, comment on a review, close a review) so the skill is discoverable when browsing or searching the skill list.

Anchor the description in the roborev domain (code review response/close) rather than relying solely on the command name as the domain identifier.

Dimension	Reasoning	Score
Specificity	The description names the domain ("/roborev-respond") but states no concrete actions — nothing about recording a comment, closing a review, or what roborev is. It matches 'Names the domain but actions are minimal or generic' rather than anchor 3, which requires 1-2 concrete actions.	2 / 5
Completeness	Only a 'when' is present ("Use only when the user explicitly invokes") with no 'what' at all — an exact match for anchor 2 ('only when is present without what'). It cannot score 3 because no capability is described anywhere.	2 / 5
Trigger Term Quality	The exact command name "/roborev-respond" is the one natural term a user would type, but common variations and synonyms ("respond to a review", "close a review", "comment on a review") are absent, matching 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The trigger is tied to one literal, highly specific command invocation, creating a clear niche with minimal conflict risk with any other skill — an exact anchor 5 match.	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/claude/roborev-respond/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.