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.
46
36%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/brainstorm/SKILL.mdQuality
Discovery
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 more like internal technical documentation than a skill description meant to help Claude select the right tool. It is heavy on implementation jargon (spawn_agents_on_csv, NDJSON, CSV-driven parallel coordination) while failing to explain what user problem it solves or when it should be triggered. The absence of a 'Use when...' clause and lack of natural trigger terms significantly limit its effectiveness for skill selection.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'brainstorm ideas', 'explore a problem from multiple perspectives', 'multi-role analysis', or 'generate ideas'.
Replace implementation jargon (spawn_agents_on_csv, NDJSON discovery board) with user-facing language that describes the benefit, e.g., 'Generates ideas by analyzing a topic from multiple expert perspectives in parallel, then synthesizes insights across roles.'
Rewrite to clearly state the user-facing outcome, e.g., 'Facilitates structured brainstorming by generating frameworks and analyzing topics from multiple expert roles simultaneously. Use when the user wants to brainstorm, explore ideas from different perspectives, or conduct multi-angle analysis of a problem.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions like 'framework generation', 'parallel role analysis', 'cross-role synthesis', and mentions two modes (auto and single role), but the actions are described in abstract/jargon-heavy terms rather than concrete user-facing capabilities. It's unclear what the actual output or benefit is. | 2 / 3 |
Completeness | The 'what' is partially addressed but in very abstract terms, and there is no 'when' clause at all — no 'Use when...' or equivalent guidance for when Claude should select this skill. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the weak 'what' brings it down to 1. | 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. The word 'brainstorming' is a natural term, but the rest are internal implementation details rather than user-facing trigger terms. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of specific implementation details like 'spawn_agents_on_csv' and 'NDJSON discovery board' makes it somewhat distinctive from generic brainstorming skills, but the core concept of 'brainstorming pipeline' could overlap with other ideation or analysis skills. The jargon helps distinguish it but at the cost of clarity. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely thorough and actionable with excellent workflow clarity, providing complete executable code for a complex multi-phase brainstorming pipeline. However, it is severely over-long and monolithic — the ~500+ lines could be cut significantly by extracting utility functions, role instruction templates, and phase-specific details into referenced sub-files. The verbosity undermines its effectiveness as a skill that must fit within a context window alongside conversation history.
Suggestions
Extract utility functions (CSV parser, CSV row updater, buildRoleInstruction template) into separate referenced files to reduce the main skill from ~500 lines to ~150 lines.
Remove the ASCII pipeline diagram and context flow diagram — the phase headings and numbered steps already communicate the workflow clearly.
Move the Available Roles table and CSV Schema details into a referenced ROLES.md or SCHEMA.md file, keeping only a brief summary inline.
Consolidate the Session Initialization and Phase 1 sections — there's significant overlap in the argument parsing and mode detection code that could be tightened.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Contains extensive ASCII diagrams, redundant flow descriptions, and implementation details that could be dramatically condensed. The full role instruction template, CSV parsing utilities, and session initialization code are all spelled out in exhaustive detail that Claude doesn't need repeated verbatim. | 1 / 3 |
Actionability | Highly actionable with complete, executable JavaScript code for every phase, concrete CSV schemas, specific file paths, exact command-line flag parsing, and detailed instruction templates. Every step is copy-paste ready with real function calls and data structures. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (Phase 1→2→3→4 for auto, Phase 1→3S for single role), explicit validation checkpoints (user validation in Phase 2, status tracking in CSV), error recovery table, and compact protection directives for context loss mid-execution. | 3 / 3 |
Progressive Disclosure | Monolithic wall of content with everything inline — the full role instruction template, CSV utilities, session initialization, all phase implementations, and the synthesis protocol are all in one massive file. No references to separate files for detailed templates, utility functions, or role-specific configurations. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
72%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
0f8e801
- Reviewed
Table of Contents
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.