brainstorming

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

1.66x

Quality

54%

Does it follow best practices?

Impact

93%

1.66x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/brainstorming/SKILL.md

The canonical home for this skill is brainstorming in sickn33/agentic-awesome-skills

Quality

Content

77%Scale 1-3

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-only skill with excellent workflow clarity and actionability — every step has concrete guidance, explicit gates, and validation checkpoints. Its main weaknesses are moderate verbosity (some redundant sections and principles Claude could infer) and a monolithic structure that could benefit from splitting documentation templates or decision log formats into separate reference files.

Suggestions

Trim the 'Operating Mode' section and 'This skill exists to prevent' list, as these are largely redundant with the process steps and exit criteria.

Consider extracting the Decision Log format and Documentation template into a separate reference file to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-structured but includes some redundancy (e.g., 'Operating Mode' section restates what's already clear from the process steps, and 'Key Principles' repeats guidance already embedded in the workflow). Some sections like 'This skill exists to prevent' list things Claude can infer. However, it's not egregiously verbose.	2 / 3
Actionability	The skill provides highly specific, concrete guidance at every step: exact question formats to use, specific output formats (5-7 bullet summaries), exact confirmation prompts to ask, word count limits for design sections (200-300 words), and explicit gate conditions. For an instruction-only skill (no code needed), this is fully actionable.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced with numbered steps, explicit hard gates (Understanding Lock, Exit Criteria), validation checkpoints ('Does this accurately reflect your intent?', 'Does this look right so far?'), and feedback loops (continue refinement if criteria unmet). The workflow includes clear stop conditions preventing premature progression.	3 / 3
Progressive Disclosure	The content is well-organized with clear section headers and logical flow, but it's entirely monolithic — everything is in one file with no references to external resources. The 'After the Design' and 'Implementation Handoff' sections could potentially be separated. The reference to 'multi-agent-brainstorming' skill is a good cross-reference but is somewhat buried at the end.	2 / 3
	Total	10 / 12 Passed

Description

32%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 too abstract and relies on buzzwords ('disciplined reasoning', 'validated designs', 'collaboration') without specifying concrete actions or outputs. It lacks natural trigger terms users would actually say and is so broad it would conflict with many other skills. The 'Use before...' framing is a good structural choice but the content within it is too vague to be useful for skill selection.

Suggestions

List specific concrete actions the skill performs, e.g., 'Generates design documents, defines API contracts, creates architecture diagrams, writes technical specifications'.

Add natural trigger terms users would say, e.g., 'Use when the user asks to design a feature, write a spec, create an RFC, plan a system, or draft architecture for a new component'.

Narrow the scope to reduce conflict risk—specify what kind of designs (software architecture? UI? system design?) and what outputs are produced (documents, diagrams, decision records?).

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'creative or constructive work', 'vague ideas', and 'validated designs'. It does not list any concrete actions—'transforms' and 'disciplined reasoning and collaboration' are buzzwords rather than specific capabilities.	1 / 3
Completeness	It has a 'when' clause ('Use before creative or constructive work') and a vague 'what' ('Transforms vague ideas into validated designs'), but the 'what' is too abstract to be useful and the 'when' triggers are overly broad. The 'Use before...' clause partially satisfies the trigger guidance requirement.	2 / 3
Trigger Term Quality	It includes some relevant terms like 'features', 'architecture', and 'behavior' that users might mention, but these are very broad and could apply to many domains. Missing natural user phrases like 'design doc', 'spec', 'RFC', 'plan', 'proposal', etc.	2 / 3
Distinctiveness Conflict Risk	Terms like 'features', 'architecture', 'creative or constructive work', and 'validated designs' are extremely broad and would overlap with many skills—architecture skills, feature planning skills, design skills, brainstorming skills, etc.	1 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/brainstorming/SKILL.md
Commit: 7520423

Reviewed: ~15 hours 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.