quieter

Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.

1.05x

Quality

67%

Does it follow best practices?

Impact

91%

1.05x

Average score across 3 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/quieter/SKILL.md

Quality

Content

77%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 body is a well-sequenced, highly actionable design-refinement workflow with explicit checkpoints, but it is a monolithic single file with no progressive disclosure to references and contains some filler and duplicated sentences that should be tightened.

Suggestions

Fix the duplicated/corrupted instructions in MANDATORY PREPARATION (e.g. "MUST STOP and STOP", "clarify. whether", "clarifying questions first") and remove motivational filler to tighten the body.

Consider moving the detailed per-dimension refinement lists (Color, Visual Weight, Simplification, Motion, Composition) into a references file referenced one level deep, keeping the core workflow in SKILL.md.

Trim entries that re-state what Claude already knows (e.g. 'Color saturation: Overly bright or saturated colors') so every line earns its tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly tactical and lean, but it includes motivational filler ("Great quiet design is harder than great bold design. Subtlety requires precision.") plus duplicated/corrupted sentences ("MUST STOP and STOP", "clarify. whether", "clarifying questions first"), so it earns 'mostly efficient but could be tightened'.	2 / 3
Actionability	Guidance is concrete and specific throughout — "70-85% saturation", "font weights (900 → 600, 700 → 500)", "10-20px instead of 40px", "ease-out-quart" — giving copy-paste-ready instruction that fully matches the actionable anchor; absence of code is acceptable for an instruction-only skill.	3 / 3
Workflow Clarity	The body sequences Context Gathering → Assess → Plan → Refine → Verify, with explicit validation gates ("Do NOT proceed until you have answers", STOP-and-clarify directives, and a closing Verify Quality checklist), matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	The skill is a single ~107-line file with no bundle files (references/scripts/assets absent) and all content inline; sections are well-organized but nothing is split out to one-level-deep references, fitting 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

57%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 communicates a clear, distinct design niche and decent trigger terms, but it lacks an explicit 'Use when...' clause and enumerates only high-level actions rather than multiple concrete operations.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a design feels too bold, loud, busy, or overstimulating and needs to become more refined.'

List concrete actions (e.g. 'desaturate colors, lighten typography, reduce motion, simplify layout') instead of the single 'reduces intensity' phrasing.

Include common user phrasings like 'too loud', 'too busy', or 'overwhelming' alongside 'bold' and 'aggressive' to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	"Tone down overly bold or visually aggressive designs" and "Reduces intensity" name the design domain and the core action, but stop short of listing multiple concrete operations, matching the 'names domain and some actions' anchor rather than the multi-action level-3 example.	2 / 3
Completeness	It states what the skill does clearly, but lacks any explicit 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger clause caps completeness at 2, with 'when' only implied by the adjective 'overly bold'.	2 / 3
Trigger Term Quality	Terms like "overly bold", "visually aggressive", and "intensity" are natural, but common variations a user might actually say ("too loud", "too busy", "overstimulating", "make it calmer") are missing, so it lands at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	"Tone down overly bold or visually aggressive designs" carves out a clear niche (reducing visual intensity) that is unlikely to trigger for unrelated skills, fitting the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 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/quieter/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.