roborev-snooze

Use only when the user explicitly invokes /roborev-snooze

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/droid/roborev-snooze/SKILL.md

Quality

Content

100%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 exemplary short skill: lean, fully executable, and unambiguous, with explicit error-handling branches for sandbox and non-git-repository failures. All guidance is non-obvious operational detail rather than filler.

Dimension	Reasoning	Score
Conciseness	The body is lean — every section carries non-obvious information (invocation rules, sandbox escalation, scope limits, error handling) with no padding and no explanation of concepts Claude already knows, matching the anchor for every token earning its place.	5 / 5
Actionability	Fully executable, copy-paste-ready commands ('roborev snooze on', 'roborev snooze on --duration 2h', 'roborev snooze off') cover all common cases including the default action and duration syntax.	5 / 5
Workflow Clarity	This simple single-purpose skill has an unambiguous action mapping (no action/on → snooze on with optional --duration; off → snooze off) plus explicit validation and error-recovery paths: permission-denied sandbox handling, 'do not restart the daemon', and reporting an untracked-git error without initializing. Per the rubric's simple-skill exception this warrants a 5.	5 / 5
Progressive Disclosure	At ~45 lines with no external content needed, the body is organized into well-labeled sections (Usage, Explicit invocation only, Sandbox access, Instructions, Examples), meeting the rubric's exception for short self-contained skills, which can score 5 with just well-organized sections.	5 / 5
	Total	20 / 20 Passed

Description

23%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 works as an invocation gate but fails as a skill description: it states when the skill may run without ever saying what it does. A user or model scanning descriptions would learn nothing about the snooze/silence capability.

Suggestions

Add a 'what' clause stating the capability, e.g., 'Temporarily silences or resumes roborev Agent Hook reminders for the current worktree and branch. Reviews continue to run while snoozed.'

Include natural trigger terms such as 'snooze', 'silence', 'pause', or 'mute reminders' so the capability is discoverable even though invocation is explicit-only.

Mention the duration parameter and default (e.g., 'supports Go duration syntax like 30m or 2h, defaulting to 8 hours') to round out capability coverage.

Dimension	Reasoning	Score
Specificity	The description 'Use only when the user explicitly invokes /roborev-snooze' names no concrete actions or even a domain — it is pure invocation gating with zero capability statements, matching the anchor for entirely vague descriptions.	1 / 5
Completeness	The 'when' is explicit ('Use only when the user explicitly invokes /roborev-snooze') but the 'what' is entirely absent — the description never says the skill silences or resumes reminders. This matches the anchor for only 'when' present without 'what'; a 3 would require a clear 'what'.	2 / 5
Trigger Term Quality	The only term present is the literal slash-command name; there are no natural keywords or phrases a user would say (e.g., 'snooze', 'silence', 'pause reminders'), matching the anchor for only technical jargon with no natural keywords.	1 / 5
Distinctiveness Conflict Risk	The single unique command-name trigger gives it a clear niche with effectively zero overlap risk with other skills, matching the top anchor for distinct triggers and minimal conflict risk.	5 / 5
	Total	9 / 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/droid/roborev-snooze/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.