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

88%

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 1-3

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

The body is highly actionable with clear sequenced workflow and validation gates, but it leans long and keeps all material inline in a single file. Tightening the conceptual First Principles section and splitting long reference material into bundle files would lift the weaker dimensions.

Suggestions

Condense or remove the 'Thinking Framework: First Principles Analysis' section — the restate/list-truths/challenge-assumptions pattern is knowledge Claude already has; keep only any skill-specific guidance.

Move the detailed Artifact Rules (prd.md/design.md/implement.md field specs) and the PRD Convergence Pass into a reference file (e.g. references/artifacts.md) and link to it one level deep, keeping SKILL.md as an overview.

If the First Principles content must stay, relocate it to references/first-principles.md and reference it only when solutions feel over-engineered, reducing baseline token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the 'First Principles Analysis' section teaches a reasoning framework Claude already knows (restate, list truths, challenge assumptions) and could be tightened; the artifact and convergence rules are otherwise dense and purposeful.	2 / 3
Actionability	Provides an executable bash snippet for task.py create and concrete, copy-ready guidance: a numbered Planning Flow, exact Question Rules per-message inclusions, and per-artifact field requirements.	3 / 3
Workflow Clarity	The Planning Flow is a clear 8-step sequence with explicit validation checkpoints — the PRD Convergence Pass and Quality Bar act as gating checks before task.py start, with a feedback loop (update prd.md after each answer).	3 / 3
Progressive Disclosure	No bundle files exist and the body is a single monolithic SKILL.md; sections are well-organized but long reference-worthy material (the full First Principles framework, detailed Artifact Rules) is inline rather than split into separate files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is third-person, specific, and pairs a concrete action list with an explicit 'Use when...' trigger clause. It cleanly satisfies all four dimensions without padding.

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 anchor for several specific concrete actions.	3 / 3
Completeness	Clearly answers both what (the enumerated actions) and when (the 'Use when...' clause with explicit triggers), satisfying the top completeness anchor.	3 / 3
Trigger Term Quality	The explicit trigger clause covers natural user situations — 'requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task' — phrases a user would plausibly say.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche — pre-implementation requirements discovery and planning — with triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: EcoPasteHub/EcoPaste
Path: .agents/skills/trellis-brainstorm/SKILL.md
Commit: 6dbbf4f

Reviewed: 12 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.