CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cw-draft

Turn an outline, notes, source material, or partial prose into a complete draft while preserving the writer's voice, thesis ownership, and source provenance. Use when the user asks to draft a piece or section.

Quality

75%

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-draft/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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-organized, instruction-only drafting skill with a clear process and concrete handoff tooling. Its weakness is that much of the core execution guidance is principle-level rather than concrete executable steps, and the workflow lacks explicit validation checkpoints.

Suggestions

Convert the Voice/Sentence Structure/Things to Avoid principle lists into concrete checks or a short worked example so the guidance is executable rather than abstract.

Add an explicit validation step before completion (e.g. re-check that source provenance is preserved and that AI-pattern residue was removed via cw-ai-check) to give the workflow a clear checkpoint.

Consider moving the Hook Arsenal and structural-moves detail into a one-level reference file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly lean, using tight bullets and concrete lists without explaining concepts Claude already knows; minor instances could be trimmed (e.g. the 'Use judgment about pacing' paragraph reiterates the preceding check-in guidance), so it is efficient but not perfectly lean.

4 / 5

Actionability

It provides some concrete, copy-pasteable guidance (handoff phrases, the Hook Arsenal, the structural-moves table, the drafts/<piece-slug>/ convention), but the bulk of Silent Enforcement is principle-level ('Vary sentence length', 'Active voice preferred') rather than specific executable steps, leaving notable gaps.

3 / 5

Workflow Clarity

A discernible sequence exists (Load Context → draft section by section with check-ins → silent enforcement → Completion), but there are no explicit validation checkpoints and the process deliberately defers to judgment ('Use judgment about pacing', 'Don't block on approval'), matching anchor 3.

3 / 5

Progressive Disclosure

The body is well-sectioned into clear headers and points to a single well-signaled one-level-deep reference ('Read ../../references/context-contract.md'); minor organization gaps (some inline lists such as the Hook Arsenal could live in a reference file) keep it just below anchor 5.

4 / 5

Total

14

/

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.

A strong description: it states a concrete capability and an explicit, natural trigger clause answering both what and when. The main gap is that it describes one core action rather than enumerating several specific actions.

DimensionReasoningScore

Specificity

It names the domain (drafting) and a core transformation action with concrete preservation sub-goals ('preserving the writer's voice, thesis ownership, and source provenance'), but it is essentially a single action rather than a list of several specific actions, so it sits at anchor 3 rather than 4.

3 / 5

Completeness

It explicitly answers both 'what' (turn outline/notes/source material/partial prose into a complete draft while preserving voice, thesis, provenance) and 'when' ('Use when the user asks to draft a piece or section') with a concrete trigger phrase, matching anchor 5.

5 / 5

Trigger Term Quality

'draft a piece or section' is a natural phrase a user would actually say, giving good keyword coverage; a few common synonyms ('write up', 'flesh out', 'turn into prose') are missing, keeping it just below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Drafting prose from source material with voice/thesis/provenance preservation is a clear niche, but it belongs to a family of sibling writing skills (cw-setup-project, cw-ai-check) creating minor overlap risk, so it is mostly distinct rather than minimal-conflict.

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

EveryInc/compound-writing

Path

skills/cw-draft/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.