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

81%

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

73%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 well-structured, highly actionable planning skill with strong workflow checkpoints. Main weaknesses are cross-section redundancy of the approval/evidence rules and a generic thinking-framework section that dilutes focus.

Suggestions

Consolidate the repeated explicit-approval and 'explore the codebase before asking' rules into one authoritative section and reference it instead of restating across Planning Contract, Planning Flow, Question Rules, and Quality Bar.

Add one worked example showing a complete high-value question (decision, why it matters, recommendation, trade-off) to make the Question Rules concrete.

Consider moving the First Principles thinking framework to a reference file or trimming it, since it is generic and not tightly coupled to the Trellis planning flow.

Dimension	Reasoning	Score
Conciseness	Per-section directives are tight and do not over-explain known concepts, but the explicit-approval gate and 'ask one question / explore codebase first' rules are restated across Non-Negotiable Planning Contract, Planning Flow, Question Rules, and Quality Bar, which could be consolidated.	3 / 5
Actionability	Provides a copy-paste `task.py create` command, an explicit question-component structure, concrete convergence-gate and quality-bar checklists, and detailed PRD-pass operations; minor gap is the absence of a worked example of a filled-in high-value question or PRD.	4 / 5
Workflow Clarity	The 9-step Planning Flow is clearly sequenced with explicit validation checkpoints (requirement convergence gate, PRD convergence pass, final review gate, fresh approval), a feedback loop in step 5, and checklists for the complex process.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references, but at ~200 lines with no bundle files the generic First Principles thinking framework is tangential to the planning flow and could be trimmed or externalized.	4 / 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, specific description that clearly states both capabilities and trigger conditions with concrete actions. Minor room to broaden natural trigger phrasings and sharpen distinctiveness.

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' — covering the full planning flow comprehensively.	5 / 5
Completeness	Explicitly answers both what (guides discovery, creates task dir, seeds PRD, asks questions, researches, converges on MVP) and when ('Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task').	5 / 5
Trigger Term Quality	Triggers like 'requirements are unclear', 'multiple valid approaches', 'new feature or complex task' are natural, but common user phrasings (e.g. 'help me plan', 'I want to build X') and synonyms are not fully covered.	4 / 5
Distinctiveness Conflict Risk	The requirements-discovery/Trellis-planning niche is mostly distinct, but 'new feature or complex task' is broad enough to risk minor overlap with general implementation skills.	4 / 5
	Total	18 / 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: mindfold-ai/Trellis
Path: .agents/skills/trellis-brainstorm/SKILL.md
Commit: 64e6636

Reviewed: 6 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.