brainstorming

在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/brainstorming/SKILL.md

Quality

Content

66%Weight 40%Scale 1-5

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

The content is a strong, well-sequenced workflow with explicit checkpoints and feedback loops, and mostly actionable guidance. Its main weaknesses are a dangling reference to a non-existent visual-companion.md file and un-signaled bundle scripts, which hurt progressive disclosure, plus some padding that could be trimmed.

Suggestions

Resolve the broken reference: either add the missing visual-companion.md to the bundle or change the path to a real file under references/ so the in-body pointer is navigable.

Add a short '## Visual companion tooling' section that signals the scripts/ files (start-server.sh, stop-server.sh, server.cjs, frame-template.html, helper.js) and when to use them, so the bundle is discoverable rather than orphaned.

Trim padded rationale (e.g. the paragraph on why small files help Claude reason, and redundant restatements of the 'simple projects need design too' point) to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids teaching concepts Claude already knows, but sections like the anti-pattern rationale, the repeated isolation/clarity justifications ('更小、边界清晰的单元也更便于你工作...'), and verbatim offer scripts add padding that could be tightened without losing clarity.	3 / 5
Actionability	It gives concrete, executable guidance — a numbered checklist, a dot flowchart, exact spec path template, a quoted user-review prompt, and concrete self-check criteria — with only minor gaps (e.g. no exact command for the git commit step).	4 / 5
Workflow Clarity	The multi-step process is clearly sequenced with both a numbered checklist and a flowchart, explicit approval checkpoints ('用户批准设计?','用户审查规格?'), feedback loops ('要求修改' routes back), and an inline spec self-check with fix-and-continue guidance.	5 / 5
Progressive Disclosure	Structure exists (sections, checklist, flowchart) but the detailed visual-companion guide is referenced as 'skills/brainstorming/visual-companion.md' which is not present in the bundle, and the heavy server/script tooling (server.cjs, start-server.sh, frame-template.html) is never linked or navigated from the body — detailed content that belongs in referenced files is inlined or un-signaled.	2 / 5
	Total	14 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 well-constructed: it states what the skill does and explicitly when to use it, with a strong mandatory-trigger framing. Its main weakness is slightly generic trigger vocabulary that could overlap with general implementation skills.

Suggestions

Add more varied/synonym trigger phrases (e.g. 'brainstorm', 'design before building', 'plan a feature') so the description matches a wider range of how users phrase the need.

Sharpen the 'what' to name the concrete deliverable (e.g. 'produces a design spec the user approves before implementation') rather than only the abstract action of exploring intent.

Narrow distinctiveness by signaling the boundary against plain coding skills (e.g. 'Use before any build work — not for execution itself').

Dimension	Reasoning	Score
Specificity	The description names a concrete domain (creative/design work) and lists several concrete triggering activities ('创建功能、构建组件、添加功能或修改行为') plus an explicit action ('探索用户意图、需求和设计'), giving good but not exhaustive coverage of actions.	4 / 5
Completeness	It explicitly answers both 'what' ('探索用户意图、需求和设计') and 'when' ('在任何创造性工作之前必须使用此技能') with a clear trigger clause, satisfying the what-and-when requirement concretely.	5 / 5
Trigger Term Quality	It surfaces natural phrases a user might say ('创建功能','构建组件','添加功能','修改行为') which are reasonable trigger terms, though it lacks synonyms and more abstract phrasings like 'brainstorm' or 'design' that users might also say.	4 / 5
Distinctiveness Conflict Risk	The pre-implementation framing carves a fairly distinct niche (design-before-build), but the trigger terms ('创建功能','修改行为') are broad enough to risk overlap with general coding/build skills, leaving minor conflict risk.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: jnMetaCode/superpowers-zh
Path: skills/brainstorming/SKILL.md
Commit: c68725b

Reviewed: 4 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.