CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

voice

Write messages in the user's authentic voice and communication style. Use whenever generating text that will be sent on behalf of the user — Google Chat messages, emails, Slack messages, DMs, announcements, or any written communication. Also use when another skill (e.g. dm-followup) needs to draft messages.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 content is a well-structured, highly actionable voice template with concrete patterns and examples throughout. Its weaknesses are the absence of a validation checkpoint for the batch-messaging workflow (capping workflow clarity) and a flat single-file organization with no progressive layering.

Suggestions

Add an explicit validation/verification step to the 'Jitter for Batch Messages' section — e.g., 'Before sending, review the batch and confirm no two messages are identical in greeting, phrasing, sign-off, or structure.'

Tighten the opening blockquote: the 50-150+ message collection guidance for building a voice profile is contextual padding that could be trimmed or moved to a separate reference file to improve conciseness.

Consider splitting the example message library (greetings, sign-offs, structure patterns) into a references file, keeping SKILL.md as a concise overview — this would add progressive layering and reduce the flat single-file bulk.

DimensionReasoningScore

Conciseness

The body is lean and well-organized with tables and compact example blocks, avoiding over-explanation of concepts Claude already knows. Minor padding remains in the opening template-building instructions ('collect 50-150+ real messages...') that could be trimmed, keeping it just short of fully lean (5).

4 / 5

Actionability

Provides concrete, copy-paste-ready guidance: specific greeting/sign-off patterns, exact example messages across request/announcement/feedback/recognition/escalation contexts, a Prefer/Avoid word-choice table, and explicit jitter variations. Specific examples cover the common cases comprehensively.

5 / 5

Workflow Clarity

The single-task action ('write all outbound messages to match the user's style') is unambiguous, but the 'Jitter for Batch Messages' batch operation gives the rule 'No two messages in a batch should be identical' without any validation/verification checkpoint. Per the rubric, a batch operation missing validation caps workflow clarity at 3, taking precedence over the simple-skill exception.

3 / 5

Progressive Disclosure

No bundle files exist and none are referenced; the skill is a self-contained, well-organized single file with clear section headers and tables. Structure is good, but it is a flat reference document over 50 lines with no overview/detail layering or reference splitting, so it does not reach the clear-overview-with-signaled-references anchor (5).

4 / 5

Total

16

/

20

Passed

Description

78%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 clearly communicates a distinctive purpose (authentic-voice message drafting) with explicit, natural trigger contexts spanning multiple communication channels. It fully answers what and when; its main limitation is that the capability is essentially a single action rather than multiple concrete operations.

DimensionReasoningScore

Specificity

Names the domain ('authentic voice and communication style') and the concrete action of writing messages across listed channels, but offers only one core action rather than several distinct capabilities. It is more than minimal/generic (not a 2) yet lacks the several specific actions needed for a 4.

3 / 5

Completeness

Explicitly answers both 'what' (write messages in the user's authentic voice) and 'when' (concrete trigger contexts: on-behalf-of-user generation across named channels, plus when another skill needs drafts), matching the explicit-concrete-triggers anchor.

5 / 5

Trigger Term Quality

Includes natural, user-spoken channel terms — 'Google Chat messages, emails, Slack messages, DMs, announcements' — with good coverage and some synonyms, though common drafting phrasings like 'write/draft a message' are absent. Coverage exceeds 'some relevant keywords' (3) but is not fully comprehensive (5).

4 / 5

Distinctiveness Conflict Risk

The authentic-voice niche and channel-specific triggers are mostly distinct with only minor overlap risk against closely related drafting skills (e.g., dm-followup, which it explicitly complements). The broad 'write messages' framing prevents a 5.

4 / 5

Total

16

/

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

foogunlana/skills

Path

.claude/skills/voice/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.