CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/claude/roborev-snooze/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 model of a simple, single-purpose skill: exact commands, copy-paste examples, explicit error handling, and useful guardrails against unintended side effects. Its only flaw is minor duplication between the intro, the invocation section, and the instruction bullets.

DimensionReasoningScore

Conciseness

The body is efficient — exact commands, a tight sandbox-troubleshooting note, and no explanation of concepts Claude already knows — but "current worktree and branch" is stated both in the intro and again in the Instructions bullet, and the "Explicit invocation only" section restates the frontmatter guard. These minor repetitions keep it at anchor 4 rather than 5, and it is well above 3 since nothing is padded.

4 / 5

Actionability

The guidance is fully executable: exact commands with flags ("roborev agent hook snooze --from-skill on", "--duration <duration>", "off"), three copy-paste-ready examples covering on, on-with-duration, and off, plus concrete error paths (sandbox retry, non-git-repository handling). This matches anchor 5 ("copy-paste ready commands; examples cover the common cases").

5 / 5

Workflow Clarity

This is a simple single-action skill whose branch logic is unambiguous: default/"on" maps to one command (plus duration flag), "off" to another, with explicit handling for sandbox denial and non-git directories. The destructive/batch validation cap does not apply since snoozing reminders is a reversible, non-destructive toggle, so the simple-skill exception yields a 5.

5 / 5

Progressive Disclosure

The ~53-line body needs no external references and none exist; it is organized into clear sections (Usage, Explicit invocation only, Sandbox access, Instructions, Examples). Per the rubric's simple-skill guideline, well-organized sections with no need for bundle files merit a 5.

5 / 5

Total

19

/

20

Passed

Description

31%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 a deliberate explicit-invocation guard (consistent with disable-model-invocation: true) that minimizes conflict risk, but it says nothing about what the skill actually does. Both the capability description and natural trigger vocabulary are missing.

Suggestions

State the capability in the description, e.g. "Temporarily silences roborev Agent Hook review reminders for the current worktree and branch; resumes them with off. Use only when the user explicitly invokes /roborev-snooze."

Include natural capability keywords (snooze, silence, mute reminders, resume reminders) so the skill is identifiable even though auto-triggering is disabled.

Mention the duration argument (e.g. "accepts a Go duration such as 2h") so the description reflects the skill's full behavior.

DimensionReasoningScore

Specificity

The description "Use only when the user explicitly invokes /roborev-snooze" names no concrete actions and no domain — it is purely an invocation guard. It matches the anchor "Entirely vague; no concrete actions" and does not reach 2 because, unlike "Processes PDF files", even the domain of the skill is unstated.

1 / 5

Completeness

"Use only when the user explicitly invokes" answers "when" explicitly but "what the skill does" (silence/resume roborev review reminders) is entirely absent. This matches anchor 2 ("only 'when' is present without 'what'") and cannot be 3, which requires a clear "what".

2 / 5

Trigger Term Quality

The only trigger is the literal slash command "/roborev-snooze"; no natural phrases a user might say ("snooze", "silence", "mute review reminders") or synonyms appear. It scores 2 rather than 3 because there are no domain keywords or variations at all, and not 1 because the exact command is a genuine trigger a user would say rather than jargon.

2 / 5

Distinctiveness Conflict Risk

By restricting invocation to the explicit literal command, the description cannot trigger for the wrong skill and carves out a clear niche. This matches anchor 5 ("Clear niche with distinct triggers; minimal conflict risk") rather than 4, since overlap risk is essentially eliminated by the explicit-invocation-only constraint.

5 / 5

Total

10

/

20

Passed

Validation

100%

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-snooze/SKILL.md

Reviewed

Table of Contents

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.