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

80%

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

77%

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

The body delivers a clear, actionable, well-sequenced design workflow with explicit gates and feedback loops. Its main weaknesses are some restated general design philosophy and a progressive-disclosure gap: the referenced visual-companion.md is absent from the bundle and the scripts/ files are not surfaced from the body.

Suggestions

Trim the '面向隔离和清晰的设计' and anti-pattern rationale to the non-obvious, skill-specific points only, since Claude already knows general software-design principles.

Add the missing skills/brainstorming/visual-companion.md to the bundle (or inline the essential bits), and add a brief 'Bundle' note in the body pointing to the scripts/ files (frame-template.html, server.cjs, start-server.sh, etc.) so the provided tooling is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and process-specific (HARD-GATE, checklist, offer scripts), but sections like '面向隔离和清晰的设计' explain general software-design philosophy (single responsibility, well-defined interfaces) that Claude already knows, and the anti-pattern rationale is editorial; it could be tightened.	2 / 3
Actionability	For an instruction-only skill the guidance is concrete and copy-paste ready: a literal visual-companion offer message, a literal user-review-gate message, a specific spec path (docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md), and a 4-point spec self-check.	3 / 3
Workflow Clarity	A 9-step numbered checklist plus a dot flowchart gives a clear sequence, with explicit validation checkpoints (HARD-GATE, per-section design approval, spec self-check, user review gate) and feedback loops (fix inline, re-run self-check on requested changes).	3 / 3
Progressive Disclosure	Sections are well-organized and the visual-companion detail is deferred behind a clearly signaled one-level reference, but that referenced file (skills/brainstorming/visual-companion.md) is missing from the bundle, and the provided scripts/ bundle is not referenced or navigated from the body at all.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 states both what the skill does and when to use it, with natural trigger terms and explicit pre-work guidance. It is somewhat held back by high-level 'what' actions and trigger terms that overlap with implementation skills.

Suggestions

Tighten the 'what' clause to name more concrete actions the skill performs (e.g., 'surfaces assumptions, proposes 2-3 design options with tradeoffs, and writes a spec') rather than the abstract 'explore intent, requirements, and design'.

Differentiate from implementation skills by foregrounding the gating phrase (e.g., 'Use before any feature/component work to produce an approved design spec') so it does not read like the implementation skills themselves.

Dimension	Reasoning	Score
Specificity	It lists several concrete trigger activities ("创建功能、构建组件、添加功能或修改行为") and the core action ("探索用户意图、需求和设计"), but the 'what it does' action is high-level (explore intent/requirements/design) rather than the concrete mechanical actions of the score-3 anchor; closest to 'names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It explicitly answers both 'what' (explore user intent, requirements, and design) and 'when' ("在任何创造性工作之前" plus the enumerated activities), with an explicit pre-work trigger clause equivalent to 'Use when...', so it is not capped at 2.	3 / 3
Trigger Term Quality	The enumerated terms ("创建功能", "构建组件", "添加功能", "修改行为") are natural phrases a user would actually say when requesting such work, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	It carves a distinct pre-implementation design niche, but its trigger terms (add a feature, modify behavior) heavily overlap with the very implementation skills it gates, so it could still trigger for the wrong skill.	2 / 3
	Total	10 / 12 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: 12a4dc1

Reviewed: about 20 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.