brainstorm

Dual-mode brainstorming pipeline. Auto mode: framework generation → parallel role analysis (spawn_agents_on_csv) → cross-role synthesis. Single role mode: individual role analysis. CSV-driven parallel coordination with NDJSON discovery board.

Quality

36%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.codex/skills/brainstorm/SKILL.md

Quality

Content

55%

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

The skill is highly actionable with excellent workflow clarity, providing complete executable code and a well-sequenced multi-phase pipeline with validation checkpoints and error recovery. However, it is severely over-engineered for a single SKILL.md file—the ~500+ lines of inlined implementation code, CSV schemas, utility functions, and role instruction templates make it a monolithic document that wastes token budget. The content would benefit enormously from splitting into referenced sub-files while keeping the SKILL.md as a concise overview.

Suggestions

Extract utility functions (parseCsv, updateMasterCsvRow, buildRoleInstruction) into separate referenced files and keep only their signatures/purpose in SKILL.md

Move the detailed role instruction template (buildRoleInstruction) to a separate ROLE-TEMPLATE.md file, referencing it from the main skill

Compress the session initialization and argument parsing code into a brief specification of flags and their effects—Claude can implement the parsing logic from a concise spec

Move the Available Roles table and CSV schema details to a separate ROLES-REFERENCE.md file, keeping only a brief summary in the main skill

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~500+ lines. It includes extensive implementation details (full JavaScript code for argument parsing, CSV parsing, session setup) that Claude could infer from a concise specification. The ASCII pipeline diagram, while helpful, is duplicated by the detailed phase descriptions. The role instruction template alone is massive and could be significantly compressed.	1 / 3
Actionability	The skill provides fully executable JavaScript code for every phase, concrete CSV schemas with examples, specific file paths, complete function implementations (parseCsv, updateMasterCsvRow, buildRoleInstruction), and clear API calls (spawn_agents_on_csv, spawn_agent). Everything is copy-paste ready with real parameters.	3 / 3
Workflow Clarity	The multi-phase pipeline is clearly sequenced (Phase 1→2→3→4 for auto, Phase 1→3S for single role) with explicit routing logic. Validation checkpoints exist (user validation in Phase 2, status checking in Phase 3, error handling table). The compact protection directive provides recovery steps for context compression, and the error handling table covers failure modes with recovery actions.	3 / 3
Progressive Disclosure	This is a monolithic wall of text with no bundle files to offload content to. The entire implementation—argument parsing, CSV schema, role instruction templates, utility functions, all phase implementations—is inlined in a single massive file. The session structure section, available roles table, utility functions, and role instruction template could all be separate referenced files to keep the SKILL.md as a navigable overview.	1 / 3
	Total	8 / 12 Passed

Description

17%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads like internal implementation documentation rather than a skill description designed for selection. It focuses on pipeline mechanics (CSV-driven coordination, NDJSON boards, spawn_agents_on_csv) rather than explaining what user problem it solves or when it should be triggered. The lack of natural trigger terms and a 'Use when...' clause makes it very difficult for Claude to appropriately select this skill.

Suggestions

Add a clear 'Use when...' clause with natural trigger terms like 'brainstorm ideas', 'explore different perspectives', 'multi-angle analysis', or 'creative ideation session'.

Replace implementation jargon (spawn_agents_on_csv, NDJSON discovery board) with user-facing language that explains the purpose and outcome, e.g., 'Generates diverse perspectives on a topic by analyzing it through multiple expert roles and synthesizing insights.'

Clarify the domain or use case — what kind of brainstorming? Business strategy, product ideas, problem-solving? This would improve both specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names some actions like 'framework generation', 'parallel role analysis', 'cross-role synthesis', and mentions two modes (auto and single role). However, these are process-oriented rather than concrete user-facing actions, and the domain/purpose of the brainstorming is never clarified.	2 / 3
Completeness	The description explains a process pipeline (a partial 'what') but never addresses 'when' Claude should use this skill. There is no 'Use when...' clause or any explicit trigger guidance, and even the 'what' is unclear in terms of user-facing purpose.	1 / 3
Trigger Term Quality	The description uses highly technical jargon ('spawn_agents_on_csv', 'NDJSON discovery board', 'CSV-driven parallel coordination') that no user would naturally say. 'Brainstorming' is the only natural keyword, but it's buried among implementation details. Users would say things like 'brainstorm ideas', 'explore perspectives', or 'creative thinking' — none of which are present.	1 / 3
Distinctiveness Conflict Risk	The highly specific implementation details (spawn_agents_on_csv, NDJSON discovery board) make it unlikely to conflict with other skills, but the vague 'brainstorming' framing could overlap with any ideation or creative thinking skill. The distinctiveness comes from jargon rather than clear domain boundaries.	2 / 3
	Total	6 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (724 lines); consider splitting into references/ and linking	Warning
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	8 / 11 Passed

Repository: catlog22/Claude-Code-Workflow
Commit: 5ff5e86

Reviewed: about 1 month 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.