brainstorm

Guided concept ideation using professional studio techniques, player psychology, creative exploration.

Quality

60%

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 ./.claude/skills/brainstorm/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 body delivers exceptionally concrete, executable workflow guidance with strong validation checkpoints — exact prompts, options, gate procedures, and verdict handling throughout. Its weaknesses are structural: a monolithic 672-line file that inlines what belongs in reference documents, and notable verbosity from duplicated next-steps lists, repeated review-mode blocks, and studio-lore padding.

Suggestions

Offload the Lean Brief flow, the per-gate spawn procedures (CD-PILLARS / AD-CONCEPT-VISUAL / TD-FEASIBILITY / PR-SCOPE handling), and the full next-steps pipeline into reference files under references/ and keep SKILL.md as a tier-dispatching overview.

Deduplicate: the "Recommended Next Steps" section repeats Phase 6's Path A/B lists and the three "Review mode check" blocks restate the same solo/lean/full rules — state the rule once and reference it.

Trim explanation of context Claude already knows (e.g., the AAA-studio pillar rationale in Phase 4 and re-explanations of MDA/Bartle/SDT framing) down to the actionable instruction.

Dimension	Reasoning	Score
Conciseness	The ~672-line body is noticeably verbose: the next-steps pipeline appears twice (Phase 6 Paths A/B, then a "Recommended Next Steps" section repeating it), three near-identical "Review mode check" blocks repeat the same solo/lean/full rules, and studio-lore padding ("Game pillars are used by real AAA studios (God of War, Hades, The Last of Us) to keep hundreds of team members...") explains context Claude does not need. It is above anchor 1 because most content is load-bearing instruction rather than generic-concept explanation, but the duplicated and padded sections exceed anchor 3's "some unnecessary explanation".	2 / 5
Actionability	Guidance is fully executable: exact AskUserQuestion prompts and option labels ("[A] Lock these in" / "[B] Rename or reframe one"), exact tab names ("Experience", "Timeline", "Dev level"), a literal tool-call structure in a code block for concept selection, concrete file paths (.claude/docs/director-gates/cd-pillars.md, design/gdd/game-concept.md), and explicit gate pass-input lists. This matches anchor 5 — copy-paste-ready guidance covering the common cases.	5 / 5
Workflow Clarity	The multi-phase flow is clearly sequenced with the workflow tier branch checked first, and every risky step has explicit validation: director gates with verdict handling (APPROVE/CONCERNS/REJECT/NOT ASSESSED), re-run instructions for missing inputs, and revision loops with per-mode exit conditions ("At autonomous — do not ask... repeat until [A] has no exit condition"). This matches anchor 5 — explicit validation steps with feedback loops for error recovery.	5 / 5
Progressive Disclosure	The skill has no bundle files (references/, scripts/, assets/ are absent) and the SKILL.md body is a monolithic ~672 lines: the entire Lean Brief flow, per-gate spawn procedures, and two full next-step lists are inlined in the main file rather than offloaded to reference files. External .claude/docs/ pointers are clearly signaled and one level deep, keeping it above anchor 1, but the bulk of detail inlined in the overview file fits anchor 2 ("content that clearly belongs in separate files is inlined").	2 / 5
	Total	14 / 20 Passed

Description

37%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 names its domain but relies on buzzword modifiers instead of concrete actions, omits any "when to use" trigger guidance, and never mentions games explicitly despite being a game-design skill. It reads more like a tagline than a trigger-ready capability statement.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to brainstorm a new game, come up with a game concept, or start pre-production on a game idea."

Replace buzzword phrases ("professional studio techniques, player psychology, creative exploration") with concrete actions: generate 3 distinct concepts, define pillars and anti-pillars, validate the core loop, and write design/gdd/game-concept.md.

State the game context explicitly ("game concept ideation") and mention the natural terms users say — brainstorm, game idea, game concept — to reduce overlap with generic ideation skills.

Dimension	Reasoning	Score
Specificity	"Guided concept ideation" names the domain with one generic action; "professional studio techniques, player psychology, creative exploration" are buzzword modifiers rather than concrete actions (no "generate concepts", "define pillars", or "write a game concept document"). It is above anchor 1 because an activity is named, but below anchor 3 because no concrete action is actually listed.	2 / 5
Completeness	A "what" is present ("guided concept ideation") but there is no "Use when..." clause or equivalent trigger guidance anywhere, which caps completeness at 3 per the judging guidelines. It cannot score 4 because the "when" half is wholly absent rather than merely implicit.	3 / 5
Trigger Term Quality	The natural phrases a user would actually say — "brainstorm", "game ideas", "come up with a game concept" — are entirely absent; "concept ideation" and "player psychology" lean technical/jargon. It falls between anchors 2 and 3, noticeably below the midpoint because the most natural trigger terms are missing.	2 / 5
Distinctiveness Conflict Risk	"Concept ideation" plus "player psychology" hints at games but the word "game" never appears, so it could plausibly fire for product, app, or writing ideation skills as well. It fits anchor 3 — somewhat specific but with real overlap risk against similar ideation skills.	3 / 5
	Total	10 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/brainstorm/SKILL.md
Commit: b21fa0f

Reviewed: 3 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.