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.

1.81x

Quality

78%

Does it follow best practices?

Impact

100%

1.81x

Average score across 1 eval scenario

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%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.

A highly actionable, well-sequenced process skill with explicit gates and feedback loops throughout. Its weaknesses are repetition — the same approval rule is hammered six-plus ways — and a broken/missing reference target plus unlinked bundle scripts that undermine navigation.

Suggestions

Consolidate the repeated approval-gate material: the HARD-GATE block, the anti-pattern section, and the red flags table all restate the same rule — merging the red flags into the HARD-GATE section would cut substantial length without losing force.

Fix or relativize the reference `skills/brainstorming/visual-companion.md`, which does not exist in this bundle — either move it to references/ alongside SKILL.md or reference its actual location.

Point the Visual Companion section at the actual bundle scripts (e.g., scripts/start-server.sh with the --open flag) so the 'start the server' instruction has a resolvable target.

Dimension	Reasoning	Score
Conciseness	The body is mostly directive rather than explanatory, but the approval gate is restated in at least six forms — the HARD-GATE block, the three path definitions, the anti-pattern section, the seven-row red flags table, the checklists, and the dot graph — which is more than the minor tightening of the 4 anchor.	3 / 5
Actionability	Guidance is copy-paste concrete: a verbatim companion-offer message, the exact spec path `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md`, explicit terminal-state skill routing ("the ONLY skill you invoke after brainstorming is writing-plans"), and per-path checklists with concrete steps like "2-3 sentences" probe framing.	5 / 5
Workflow Clarity	Each path has a numbered checklist with explicit validation checkpoints (approval gates at every stage), a spec self-review with fix-inline loop, and feedback loops for error recovery ("User approves design? -> no, revise"; "changes requested -> re-run review"), plus a full process-flow diagram — matching the 5 anchor.	5 / 5
Progressive Disclosure	The sole external reference, `skills/brainstorming/visual-companion.md`, is one-level-deep and just-in-time signaled (good), but it does not exist in the bundle, and the five scripts/ files (server, start/stop scripts, template) are never referenced from SKILL.md, leaving navigation gaps that go beyond the 4 anchor's minor organization issues.	3 / 5
	Total	16 / 20 Passed

Description

80%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, imperative trigger clause, four concrete trigger actions, and a clear what/when pairing. Its main weakness is breadth: claiming precedence over "any creative work" raises conflict risk with adjacent skills in the workflow.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "creating features, building components, adding functionality, or modifying behavior" — though the capability statement "Explores user intent, requirements and design" stays somewhat abstract, leaving minor gaps versus the comprehensive 5 anchor.	4 / 5
Completeness	Both questions are answered explicitly and concretely: the what is "Explores user intent, requirements and design before implementation" and the when is "You MUST use this before any creative work" followed by four concrete trigger phrases — clearly above the 4 anchor whose 'when' is less explicit.	5 / 5
Trigger Term Quality	Natural phrases like "creating features", "building components", and "modifying behavior" map well to what users say, but common variations such as "implement", "new project", or "refactor" are missing, matching the good-but-incomplete keyword coverage anchor.	4 / 5
Distinctiveness Conflict Risk	The design-first intent is distinguishable, but the trigger "before any creative work" is broad enough to fire on nearly every feature request, creating real overlap risk with planning, implementation, and review skills — somewhat specific, but overlap remains.	3 / 5
	Total	16 / 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: obra/superpowers
Path: skills/brainstorming/SKILL.md
Commit: 8ca22db

Reviewed: 5 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.