bolder

Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.

1.03x

Quality

56%

Does it follow best practices?

Impact

94%

1.03x

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/bolder/SKILL.md

Quality

Content

62%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 content is well-structured with a clear, validated workflow and concrete design guidance, but it is verbose with recurring AI-slop warnings and keeps all detail inline in one file rather than progressively disclosing it. It is solid but leaves room for tightening and better file organization.

Suggestions

De-duplicate the recurring 'AI slop' / 'purple-to-blue gradient' / 'glassmorphism' warnings into a single consolidated callout to reduce token cost.

Split the detailed per-dimension amplification lists (Typography, Color, Spatial, Effects, Motion, Composition) into a referenced file, keeping SKILL.md as a lean overview with signaled links.

Tighten abstract bullets like 'introduce unexpected color combinations' into concrete, actionable specifics to lift actionability.

Dimension	Reasoning	Score
Conciseness	The ~120-line body has concrete actionable bullets but repeats the same warnings multiple times (e.g. 'purple-to-blue gradient AI slop' and 'glassmorphism is overused AI slop' recur across sections) and restates motivational points ('Bold means distinctive, not more effects'). It could be tightened materially. Not score 1 because the lists are substantive; not score 3 because of clear redundancy.	2 / 3
Actionability	Provides specific, actionable guidance in places ('3x-5x differences', 'Pair 900 weights with 200 weights', '100-200px gaps', '50-100ms delays', 'ease-out-quart/quint/expo'), but many bullets stay abstract ('introduce unexpected color combinations', 'choose a lane'). As an instruction-only skill this is acceptable, but it is not fully copy-paste ready. Not score 1 (lots of concrete detail); not score 3 (mixed with vague direction).	2 / 3
Workflow Clarity	A clear sequenced workflow (Context Gathering → frontend-design skill → Assess → Plan → Amplify → Verify) with explicit checkpoints ('STOP and call AskUserQuestionTool') and a Verify Quality feedback loop ('if yes, start over'). Not score 2 because checkpoints and validation are explicit rather than implicit.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are empty), and the body is a single ~120-line file with all dimension detail inline rather than split into referenced files. Sections are well-organized, but content that could be separate (detailed amplification lists) is inline. Not score 1 (clear section structure); not score 3 (monolithic, no file split).	2 / 3
	Total	9 / 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 clearly conveys the skill's purpose and target domain but is missing an explicit 'Use when...' trigger clause and lacks a comprehensive list of concrete actions. It is functional but not exemplary, placing it squarely at the midpoint of the scale.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a design feels too safe, generic, or visually underwhelming and the user wants more impact.'

List concrete actions or outcomes (e.g. 'intensify typography, color, and spatial contrast') instead of abstract phrases like 'visually interesting and stimulating'.

Include natural trigger phrasings users would actually say (e.g. 'make this pop', 'make it bolder', 'more striking') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the design domain and actions ('Amplify safe or boring designs', 'make them more visually interesting', 'Increases impact'), but does not list multiple distinct concrete actions as the score-3 anchor requires; 'visually interesting and stimulating' is somewhat abstract.	2 / 3
Completeness	States what the skill does but provides no explicit 'when' trigger; there is no 'Use when...' clause, which the guideline explicitly caps at 2. Not score 1 because the 'what' is present.	2 / 3
Trigger Term Quality	Contains some relevant keywords ('safe or boring designs', 'visually interesting', 'impact'), but lacks common natural variations a user would say ('make this pop', 'more striking') and has no enumerated trigger list. Not score 1 because relevant terms exist; not score 3 because coverage of natural phrasings is thin.	2 / 3
Distinctiveness Conflict Risk	The visual-boldness niche is somewhat specific and unlikely to conflict with non-design skills, but it overlaps with the frontend-design skill it depends on. Not score 1 (not generic), not score 3 (potential overlap with adjacent design skills).	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/bolder/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.