distill

Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.

1.00x

Quality

48%

Does it follow best practices?

Impact

94%

1.00x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./archived/legacy-companion/.agents/skills/distill/SKILL.md

Quality

Content

47%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill has a strong, well-gated workflow with explicit checkpoints, but it is significantly over-written with generic design principles Claude already knows and lacks concrete examples or any progressive disclosure into reference files.

Suggestions

Cut generic design/writing advice Claude already knows (color-palette ranges, active-voice tips, 'plain language always wins') and keep only distillation-specific guidance and the stop/verify workflow.

Add at least one concrete before/after example showing a cluttered design reduced to its essence, so the guidance is actionable rather than abstract.

Move the long per-dimension heuristic checklists (Visual, Layout, Interaction, Content, Code Simplification) into a referenced reference file, leaving SKILL.md as a lean overview with well-signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is padded with basic design and writing principles Claude already knows ('Use 1-2 colors plus neutrals', 'Active voice: Save changes not Changes will be saved', 'Remove jargon: Plain language always wins'), so it fails to assume Claude's competence and earns its tokens.	1 / 3
Actionability	It offers some concrete heuristics ('never nest cards inside cards', 'ONE primary action', '3-4 sizes maximum') but mixes them with vague questioning ('What's the 20% that delivers 80% of value?') and provides no concrete before/after examples, so guidance is incomplete.	2 / 3
Workflow Clarity	It lays out a clear ordered sequence (Context Gathering -> Assess -> Plan -> Simplify -> Verify -> Document) with explicit STOP/checkpoint gates, an AskUserQuestion feedback loop, and a Verify checklist, matching the explicit-validation anchor.	3 / 3
Progressive Disclosure	There are no bundle files and the >50-line body keeps all detailed heuristic checklists inline in a single SKILL.md rather than splitting them into one-level-deep reference files, so structure exists but content that should be separate is inline.	2 / 3
	Total	8 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 third-person and names a clear niche, but it is vague on actions and entirely missing a 'Use when' trigger clause, leaving every dimension at the middle anchor.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when simplifying a UI, cleaning up a cluttered design, or reducing visual/content complexity').

List a couple more concrete actions beyond stripping complexity (e.g., 'consolidate redundant elements, establish clear hierarchy, apply progressive disclosure').

Include natural user-facing terms like 'simplify', 'clean up', and 'reduce clutter' rather than the editorial phrase 'strip designs to their essence'.

Dimension	Reasoning	Score
Specificity	It names the domain ('designs') and one concrete action ('Strip designs to their essence by removing unnecessary complexity'), but does not list multiple specific concrete actions, so it falls short of a 3.	2 / 3
Completeness	It states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	It contains some relevant keywords ('designs', 'complexity', 'simple') but omits the natural terms a user would actually say ('simplify', 'clean up the UI', 'reduce clutter'), so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The design-simplification niche is somewhat specific, but without explicit triggers it could still overlap with a general frontend-design or design skill rather than being clearly distinct.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: The-Vibe-Company/companion
Path: archived/legacy-companion/.agents/skills/distill/SKILL.md
Commit: 90804d3

Reviewed: 18 days 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.