trellis-brainstorm

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

Quality

83%

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

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 brainstorm workflow with concrete templates and commands. Its main weaknesses are length/redundancy and a monolithic structure that would benefit from splitting stable reference material into separate files.

Suggestions

Deduplicate the CoreRule, Core Principles, and Anti-Patterns sections — consolidate into a single principles list to cut length and redundancy.

Extract the large PRD template blocks (Step 0 seed, PRD Target Structure, Research output format) into a references/prd-template.md file and link to it, improving progressive disclosure.

Move the Research-first Mode detail (sub-agent dispatch patterns, Codex exception) into a references/research.md file, keeping SKILL.md as a concise overview that signals when to consult it.

Dimension	Reasoning	Score
Conciseness	Mostly actionable content (templates, commands, tables) but noticeably long at ~549 lines with redundant restatements — CoreRule, Core Principles, and Anti-Patterns repeat the same guidance — that could be tightened; not 2 because the bulk is genuinely useful rather than padded concept explanation.	3 / 5
Actionability	Provides copy-paste-ready bash commands (e.g. 'python3 ./.trellis/scripts/task.py create "brainstorm: <short goal>" --slug <auto>') and complete PRD/markdown templates covering the common cases.	5 / 5
Workflow Clarity	Steps 0–8 are explicitly sequenced with Gate A/B/C checkpoints and per-step PRD-update rules; the question gate acts as a validation checkpoint before proceeding, satisfying the clear-sequence-with-explicit-checkpoints anchor.	5 / 5
Progressive Disclosure	Well-organized with clear section headers, but it is a 549-line monolith with no bundle files — PRD templates, research-output format, and expansion-sweep content that could live in separate reference files are all inlined; not 4 because there are no one-level-deep reference files to navigate to.	3 / 5
	Total	16 / 20 Passed

Description

88%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, third-person description that clearly states both capabilities and trigger conditions with concrete actions. Minor room to improve trigger synonym coverage and reduce overlap with generic coding-skill triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope' — matching the comprehensive-coverage anchor; not below because each action is specific rather than generic.	5 / 5
Completeness	Explicitly answers both what ('Guides collaborative requirements discovery...Creates task directory, seeds PRD...') and when ('Use when requirements are unclear, there are multiple valid approaches...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('requirements are unclear', 'multiple valid approaches', 'new feature', 'complex task') but lacks synonyms/variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	'Requirements discovery before implementation' / 'converges on MVP scope' carves a clear brainstorm niche, but 'new feature or complex task' triggers overlap somewhat with general coding skills, keeping it below 5.	4 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (549 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: mindfold-ai/Trellis
Path: .omp/skills/trellis-brainstorm/SKILL.md
Commit: 64e6636

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.