CtrlK
BlogDocsLog inGet started
Tessl Logo

brainstorming

Use before creative or constructive work (features, architecture, behavior). Transforms vague ideas into validated designs through disciplined reasoning and collaboration.

61

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

This is a strong instruction/process skill: highly actionable prompts and checklists with excellent sequencing and hard-gate validation. Its main weaknesses are moderate redundancy of the core constraints plus generic boilerplate at the end, and a lack of progressive disclosure with all detail kept inline in SKILL.md.

Suggestions

Collapse the repeated no-implementation / explicit-assumptions / YAGNI statements (currently restated in Operating Mode, Exit Criteria, and Key Principles) into a single authoritative 'Non-Negotiables' section to recover tokens.

Remove or replace the generic 'When to Use' and 'Limitations' boilerplate with skill-specific content, since 'applicable to execute the workflow described in the overview' adds no information Claude does not already infer.

Move the detailed Decision Log format, NFR checklist, and documentation template into a reference file (e.g., references/TEMPLATES.md) linked one level deep from SKILL.md so the main file stays a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly prescriptive directives rather than concept explanations, but the no-implementation / explicit-assumptions / YAGNI themes recur across Operating Mode, Exit Criteria, and Key Principles, and the trailing 'When to Use' and 'Limitations' sections are generic boilerplate that could be trimmed.

2 / 3

Actionability

It gives concrete, copy-paste-ready guidance: exact confirmation prompts ('Does this accurately reflect your intent?'), a 5-7 bullet Understanding Summary checklist, an explicit NFR category list, 200-300 word section limits, and a defined Decision Log structure.

3 / 3

Workflow Clarity

A clearly numbered 7-step sequence is reinforced by explicit hard gates (Understanding Lock with 'Do NOT proceed until explicit confirmation'), incremental per-section checkpoints, feedback loops ('If any criterion is unmet: Continue refinement'), and an Exit Criteria checklist.

3 / 3

Progressive Disclosure

Sections are well-organized and there are no broken or nested references, but no bundle/reference files exist and ~120 lines of detail (Decision Log format, NFR checklist, documentation template) are all inline rather than offloaded to one-level-deep references.

2 / 3

Total

10

/

12

Passed

Description

67%

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 cleanly states both purpose and an explicit trigger, but its action vocabulary is narrow and its trigger terms are only partially aligned with natural user phrasing. The broad 'creative or constructive work' framing leaves moderate overlap risk with other design/planning skills.

Suggestions

Replace the single verb 'Transforms' with a short list of concrete actions (e.g., 'Clarifies intent, surfaces assumptions, proposes 2-3 design approaches, and locks understanding before design') to raise specificity.

Add natural trigger phrasing users actually say, such as 'Use when the user wants to brainstorm, plan, or design a feature/architecture before building it', to improve trigger-term coverage.

Tighten the scope language from 'creative or constructive work' to a more distinctive boundary like 'pre-implementation design facilitation' to reduce conflict with general coding or planning skills.

DimensionReasoningScore

Specificity

It names the domain ('features, architecture, behavior') and one concrete action ('Transforms vague ideas into validated designs'), but the action set is not comprehensive — a single core verb rather than multiple specific actions.

2 / 3

Completeness

It explicitly answers what ('Transforms vague ideas into validated designs through disciplined reasoning and collaboration') and when ('Use before creative or constructive work'), with an explicit 'Use before...' trigger clause equivalent to 'Use when...'.

3 / 3

Trigger Term Quality

'features, architecture, behavior' are terms a user might say, but common variations like 'brainstorm', 'plan', 'design', or 'spec' are absent, and 'validated designs' / 'disciplined reasoning' read as the skill's framing rather than natural user language.

2 / 3

Distinctiveness Conflict Risk

The pre-implementation design niche is somewhat specific, but 'creative or constructive work (features, architecture, behavior)' is broad and could overlap with general development or planning skills.

2 / 3

Total

9

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/antigravity-awesome-skills
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.