profile-voice

Use when deriving a reusable messaging voice profile from user-approved writing samples or explicit approved voice guidance.

Quality

77%

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 ./skills/profile-voice/SKILL.md

Quality

Content

78%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 well-structured, concise, and actionable with a clear sequenced workflow, an explicit labeling taxonomy, and a ready output template. The only gaps are a minor Quality-check/Guardrails restatement and the absence of a fully worked transformation example and an explicit validation feedback loop.

Suggestions

Add a fully worked before/after sample transformation (real illustrative sentences) so the Sample transformation section is copy-paste ready rather than placeholder-driven.

Add an explicit validation feedback loop in the Workflow or Quality check (e.g., 'if a review check fails, revise the labeled items and re-run the check') to lift workflow clarity.

Tighten the Quality check section so it does not restate the Guardrails, or cross-reference it to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no padding or basics explanations, but the Quality check section slightly restates the Guardrails and workflow, keeping it just below a clean 5.	4 / 5
Actionability	Concrete guidance includes an explicit Observed/Inference/Missing taxonomy, a structural-recipe definition step, and a copy-paste-ready output template with a worked example invocation, but the transformation example uses placeholders rather than fully worked before/after content.	4 / 5
Workflow Clarity	Six steps are clearly numbered and sequenced with an input-gating rule and an explicit Quality check checklist, but there is no explicit error-recovery feedback loop (check fails -> fix -> redo).	4 / 5
Progressive Disclosure	The content is organized into clearly headed, logically separated sections with no external references needed and nothing that should be in a separate file inlined, matching the anchor for a well-organized self-contained overview.	5 / 5
	Total	17 / 20 Passed

Description

76%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 concise, third-person, and explicitly answers both what the skill does and when to use it, with concrete input types. It is held back only by limited coverage of the natural trigger vocabulary users would actually invoke.

Suggestions

Add natural user phrasings as trigger keywords (e.g., 'tone of voice', 'brand voice', 'writing style') so users' everyday wording surfaces the skill.

Consider naming a couple of distinct concrete actions (e.g., 'extract', 'label', 'transform') to lift specificity from a single composite action to a fuller action list.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete source types ('user-approved writing samples or explicit approved voice guidance') for the composite action of deriving a voice profile, sitting above a 3 but not listing multiple distinct actions like a 5.	4 / 5
Completeness	It explicitly states the 'what' (derive a reusable voice profile) and a concrete 'Use when...' trigger clause naming the approved inputs, matching the anchor that requires both with concrete trigger phrases.	5 / 5
Trigger Term Quality	It offers several relevant keywords ('voice profile', 'writing samples', 'voice guidance', 'messaging') but omits common natural phrasings users would actually say ('tone of voice', 'brand voice', 'writing style'), so it falls short of a 4.	3 / 5
Distinctiveness Conflict Risk	Voice-profile derivation from approved samples is a clear niche with a specific trigger and only minor overlap with adjacent brand/copywriting skills, but it lacks the ultra-precise disambiguators of a 5.	4 / 5
	Total	16 / 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: llaskin/AI-SDR-Skill-Pack
Path: skills/profile-voice/SKILL.md
Commit: 56ebfd3

Reviewed: ~23 hours 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.