write-in-voice

Use when transforming or auditing an existing or already-scoped one-off draft against approved or provisional voice rules after its message type is chosen.

Quality

56%

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/write-in-voice/SKILL.md

Quality

Content

67%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 tight, well-structured instruction skill with explicit gates and return tokens and a quality check, assuming Claude's competence throughout. Its main gap is actionability: it gives routing/control tokens but no concrete worked example of an actual voice-transformed draft or input-output pair.

Suggestions

Add one concrete worked example showing a short input draft and its voice-transformed/audited output with the claim trace and voice trace filled in, to lift actionability.

Make the 'Quality check' a short checklist of pass/fail criteria rather than a prose paragraph so the validation step is unambiguous.

Tighten the Guardrails so they do not repeat routing/invention rules already stated in the Workflow, recovering a few tokens.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's competence, with little padding or explanation of concepts Claude already knows; only a few slightly redundant restatements (e.g. guardrails re-stating routing and invention prohibitions) keep it from level 5.	4 / 5
Actionability	Guidance is specific (explicit return tokens like `ROUTE: write-openers`, `STOP`, `NEEDS VERIFICATION`, `DRAFT FOR HUMAN REVIEW`) but there is no executable example of an actual transformed/audited message or a worked input-output case, so it stops short of copy-paste-ready concreteness.	3 / 5
Workflow Clarity	A clear 7-step sequence with explicit gates and return tokens plus a final Quality check; it is a safety-gated drafting process with checkpoints, though the validation is rule-based rather than a validate->fix->retry loop, which fits an instruction skill.	4 / 5
Progressive Disclosure	Well-organized sections (Purpose, Required inputs, Workflow, Output format, Guardrails, Quality check, Example invocation) with no nested or buried references; there are no bundle files, so there is nothing to split out, and the structure is appropriately flat for a ~58-line skill.	4 / 5
	Total	15 / 20 Passed

Description

46%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 scopes a niche task but is written in procedural/conditional jargon rather than natural trigger language, weakening trigger-term quality and making the 'when' clause dense. It is specific enough to be distinct but not maximally clear.

Suggestions

Lead with natural trigger phrases a user would actually say, e.g. 'Use when rewriting or checking the tone/voice of an already-scoped one-off message against approved brand voice rules.'

State the concrete actions more plainly (e.g. 'adjust word choice, tone, and phrasing to match voice rules') instead of relying on 'transforming or auditing'.

Move the conditional sequencing ('after its message type is chosen') out of the description or into a dependent clause so the what/when pair reads cleanly.

Dimension	Reasoning	Score
Specificity	Names the domain ('transforming or auditing ... one-off draft against ... voice rules') and the concrete actions of transforming and auditing, but the actions are abstract and few compared to anchors listing multiple specific actions.	3 / 5
Completeness	It has a clear 'Use when ...' trigger clause and a 'what' (transform/audit a draft against voice rules), but the 'when' is buried in conditional jargon and is not as explicit or concrete as the level-4/5 anchors.	3 / 5
Trigger Term Quality	It lacks natural user-said keywords like 'voice', 'tone', or 'rewrite'; instead it uses procedural jargon ('after its message type is chosen', 'provisional voice rules') that a user would rarely utter when they need this skill.	2 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct ('one-off draft ... after its message type is chosen ... after routing') with limited overlap risk against related drafting skills, though the phrasing is dense enough to keep it from level 5.	4 / 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: llaskin/AI-SDR-Skill-Pack
Path: skills/write-in-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.