brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Quality

78%

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 ./app/skills/brainstorming/SKILL.md

Quality

Content

70%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 body delivers an exceptionally clear gated workflow with strong validation checkpoints and feedback loops, and mostly concrete, executable instruction. Its weaknesses are redundancy (the DOT graph duplicates the checklist), some padded rationale, and references to files that are missing from the bundle.

Suggestions

Remove the DOT flow graph (or the checklist) — the graph restates the checklist step-for-step at a cost of roughly 30 lines with no new information.

Fix the progressive-disclosure references: ship visual-companion.md and spec-document-reviewer-prompt.md in the bundle (e.g. under references/) and reference them with correct bundle-relative paths.

Trim persuasive rationale such as 'Smaller well-bounded units are also easier for you to work with - you reason better about code you can hold in context' down to the actionable boundary criteria.

Dimension	Reasoning	Score
Conciseness	The ~30-line DOT graph restates the 9-item checklist almost verbatim, and sections like "Design for isolation and clarity" include persuasive rationale Claude does not need, so it is mostly efficient with clear trimming opportunities. Not 2 because it never explains concepts Claude already knows, and not 4 because the duplicated flow graph is a substantial redundancy, not a minor one.	3 / 5
Actionability	Guidance is highly concrete for an instruction-only skill: exact spec path ("docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md"), verbatim offer and review messages, "Only one question per message", "max 5 iterations", and "Propose 2-3 approaches". Not 5 because two referenced files ("spec-document-reviewer-prompt.md" and "skills/brainstorming/visual-companion.md") do not exist in the bundle, leaving the reviewer-dispatch step under-specified.	4 / 5
Workflow Clarity	The 9-step checklist is explicitly ordered with a MUST-create-tasks directive, plus approval gates after each design section, a spec-review feedback loop ("fix, re-dispatch, repeat until Approved" capped at 5 iterations then surfaced to a human), and a user review gate with change handling. This matches anchor 5: clear sequence, explicit validation, feedback loops, and a checklist.	5 / 5
Progressive Disclosure	The body is reasonably structured, but its only two references are broken or ambiguous: "skills/brainstorming/visual-companion.md" uses a non-bundle-relative path and neither it nor "spec-document-reviewer-prompt.md" exists in the bundle (references/, scripts/, assets/ are absent). This matches anchor 3's 'references present but not clearly signaled' rather than 4, since absent referenced files are more than a minor organization gap.	3 / 5
	Total	15 / 20 Passed

Description

75%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.

A strong description with an explicit and unusually specific 'when' clause backed by concrete trigger phrases, and a clear if abstract 'what'. Main weaknesses are the broad 'any creative work' trigger surface that invites conflicts with other skills, and a 'what' that names intent rather than the skill's concrete behaviors.

Dimension	Reasoning	Score
Specificity	The 'what' is a single conceptual action ("Explores user intent, requirements and design") with no enumeration of the skill's concrete behaviors (one-question-at-a-time, proposing approaches, writing a spec), matching anchor 3's '1-2 concrete actions, not comprehensive'. It is not 4 because the enumerated items are trigger contexts rather than specific capabilities, and the second-person "You MUST use this" phrasing further weakens capability specificity.	3 / 5
Completeness	It explicitly answers 'when' with four concrete trigger conditions ("before any creative work - creating features, building components, adding functionality, or modifying behavior") and 'what' with "Explores user intent, requirements and design before implementation". This matches anchor 5's requirement of both answers with concrete trigger phrases, exceeding anchor 4's less-specific 'when'.	5 / 5
Trigger Term Quality	"creating features, building components, adding functionality, or modifying behavior" are natural phrases users would say, giving good keyword coverage. Not 5 because common synonyms and variations like 'design', 'brainstorm', 'new feature', or 'implement' are missing.	4 / 5
Distinctiveness Conflict Risk	The pre-implementation design niche is somewhat specific, but the claim to trigger before "ANY creative work" creates real overlap risk with every implementation and planning skill (frontend-design, writing-plans, etc.). Falls between anchor 2's 'very broad, high overlap' and anchor 3's 'somewhat specific' — noticeably below the midpoint of distinctiveness.	3 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ZHangZHengEric/Sage
Path: app/skills/brainstorming/SKILL.md
Commit: 81bddde

Reviewed: 7 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.