brainstorm

Chain-loaded brainstorming. 4-phase dual-mode with auto multi-role and single-role paths.

Quality

64%

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/workflow-skills/brainstorm/SKILL.md

Quality

Content

76%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 lean, executable routing skill that gets Claude to the chain_loader with concrete commands, but it under-specifies entry-point selection and leaves the actual phase workflow and variable usage to external files. Structure and token efficiency are strong; workflow depth is the weak spot.

Suggestions

Add a one-line guide on when to use each entry point (e.g., default to mode-routing; use --entry=auto for multi-perspective exploration, --entry=single-role for focused output).

Show how `goal` and `auto_yes` are supplied (CLI flag, env var, or prompt) so the commands are fully self-contained.

Either list the phase files in the phases directory or briefly name the 4 phases so the delegated workflow is visible without opening external files.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a single instruction, three terse annotated commands, and two pointer lines — with no padding or over-explanation; every token earns its place.	5 / 5
Actionability	The three `chain_loader start` commands are copy-paste ready and cover the entry cases, but "Variables: goal, auto_yes" never shows how those variables are passed, a minor executable gap.	4 / 5
Workflow Clarity	Entry points are listed as concrete commands, but there is no guidance on when to choose auto vs single-role vs mode-routing, and the 4-phase sequence with its checkpoints is delegated entirely to the external phases directory.	3 / 5
Progressive Disclosure	The body is a clear overview pointing one level deep to `.claude/skills/brainstorm/phases/`, but the reference is a terse directory pointer that does not enumerate or link the individual phase files.	4 / 5
	Total	16 / 20 Passed

Description

53%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 identifies a distinct niche and partial capability but is dominated by internal mechanism jargon and omits any trigger guidance for when Claude should use it. It reads more like an architecture summary than a user-facing skill description.

Suggestions

Rewrite the description in third person stating what the skill produces (e.g., "Expands a goal into brainstormed options and structured plans") instead of internal mode mechanics.

Add an explicit "Use when..." clause with natural trigger terms (brainstorm, ideate, explore options, generate ideas).

Include synonyms and concrete actions to lift specificity and trigger-term coverage beyond the single keyword "brainstorming".

Dimension	Reasoning	Score
Specificity	Names the domain ("brainstorming") and structural specifics ("auto multi-role and single-role paths"), but describes internal mode mechanics rather than concrete user-facing actions like generating or organizing ideas.	3 / 5
Completeness	Gives a partial "what" (a 4-phase dual-mode brainstorming process) but entirely lacks a "when"/"Use when..." clause, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"brainstorming" is a natural user term, but the rest ("chain-loaded", "4-phase dual-mode", "multi-role") is internal jargon with no synonyms or variations such as ideation, ideas, or options.	3 / 5
Distinctiveness Conflict Risk	"Brainstorming" is a clearly distinct niche unlikely to clash with unrelated skills, though the jargon-heavy framing keeps the triggers from being as cleanly expressed as a 5.	4 / 5
	Total	13 / 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: catlog22/Claude-Code-Workflow
Path: .claude/workflow-skills/brainstorm/SKILL.md
Commit: 07491b0

Reviewed: 7 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.