CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cw-onboarding

Begin or refresh the separate VOICE.md, STYLE.md, and optional AUDIENCE.md guides in a writer's durable writing home from a short conversation, existing writing, or maintained context. Use during first-run writing-home setup and when the user wants to define, calibrate, import, or update voice, style, or audience context.

Quality

80%

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 ./skills/cw-onboarding/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-structured, actionable instruction skill with a clear workflow and sensible approval gates. Its main weakness is conciseness — the voice/style/audience routing is repeated across several sections — and reference pointers that could be more explicit.

Suggestions

Consolidate the voice/style/audience routing rules into a single canonical table or classification test, then reference it from other sections instead of restating the routing each time.

Add an explicit validation step for destructive cases (e.g., 'before overwriting VOICE.md, diff the proposed rules against the existing file and confirm with the writer') to turn approval gates into a validate-fix-retry loop.

Convert path mentions like 'defaults/project-template/AUDIENCE.md relative to the plugin root' into clear link-style pointers with a one-line description of what the file provides, so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The body is mostly efficient and substantive, but the voice/style/audience routing logic is restated across 'Keep The Destinations Distinct', 'Calibrating A Voice Profile', and 'Write The Profile', which could be tightened; not a 4 because the redundancy is noticeable rather than minor.

3 / 5

Actionability

As an instruction-only skill it gives concrete executable guidance: a classification test, explicit per-guide routing rules, specific interview dimensions, and a concrete VOICE.md coverage checklist; not a 5 because some guidance remains high-level ('follow the user's energy').

4 / 5

Workflow Clarity

Clear sequenced sections (Load Context → Route → Audience → Interview → Calibrate → Write → Migrate → Handoff) with approval checkpoints ('Do not overwrite an existing profile without explicit approval', 'Show the proposed content before changing a high-authority or shared file') and a handoff checklist; not a 5 because explicit validate-fix-retry loops are absent.

4 / 5

Progressive Disclosure

Well-organized sections with one-level-deep, signaled references ('../../references/context-contract.md', 'defaults/project-template/AUDIENCE.md', 'examples/'); not a 5 because some references are path mentions rather than cleanly linked pointers, and no bundle files were available to verify the structure.

4 / 5

Total

15

/

20

Passed

Description

83%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.

A strong, well-targeted description that clearly states both capability and trigger conditions with concrete natural-language terms. It is held back only by minor jargon and slight overlap risk with adjacent writing skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Begin or refresh the separate VOICE.md, STYLE.md, and optional AUDIENCE.md guides', 'define, calibrate, import, or update voice, style, or audience context'), with only minor coverage gaps; not a 5 because the first clause ('from a short conversation, existing writing, or maintained context') is somewhat abstract.

4 / 5

Completeness

Explicitly answers both what ('Begin or refresh the separate VOICE.md, STYLE.md, and optional AUDIENCE.md guides') and when ('Use during first-run writing-home setup and when the user wants to define, calibrate, import, or update voice, style, or audience context') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good coverage of natural terms a writer would say ('voice', 'style', 'audience', 'define', 'update', 'first-run setup'); a few natural phrasings are missing and some jargon ('writing home', 'maintained context') is present, so it sits below the comprehensive-5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche (writing-home voice/style/audience guides) with distinct triggers and minimal conflict risk; not a 5 because it could overlap with closely related Compound Writing or general editing skills.

4 / 5

Total

17

/

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

EveryInc/compound-writing

Path

skills/cw-onboarding/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.