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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/trellis-brainstorm/SKILL.md

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.

The content is a well-sequenced, gate-driven planning skill with strong validation checkpoints and feedback loops, plus concrete commands and artifact schemas. Its main weakness is moderate directive repetition that inflates token usage without adding new guidance.

Suggestions

Consolidate the repeated "no implementation without explicit fresh approval" directive into a single authoritative location and reference it from the Planning Flow and Quality Bar instead of restating it.

Move the First Principles Thinking Framework (Steps 1–5) into a references/ file and link to it from a one-line pointer, reducing inline bulk for users who already have a clear problem statement.

Add the exact `task.py start` / `prd.md update` command signatures alongside the create command so the execution path is uniformly concrete.

Dimension	Reasoning	Score
Conciseness	The body is largely instruction-bearing rather than padding over known concepts, but the same directives are restated several times — the "don't start implementation without explicit approval" rule appears in the Planning Contract, steps 8–9, and the Quality Bar, and "explore the codebase instead" repeats across the Evidence Rule and step 2 — so it could be tightened.	3 / 5
Actionability	Provides an executable task.py create command, explicit artifact field lists for prd.md/design.md/implement.md, and concrete question components (decision, why, recommendation, trade-off), with only minor gaps around the exact update/start command signatures.	4 / 5
Workflow Clarity	A 9-step Planning Flow is backed by explicit validation checkpoints — the Requirement Convergence Gate checklist, the lossless PRD Convergence Pass, the Quality Bar, and feedback loops ("repeat from step 2," "repeat the final review," blocking-open-question gating) — matching the clear-sequence-with-validation-and-feedback-loops anchor.	5 / 5
Progressive Disclosure	Single-file skill with clear section headers and no nested references (no bundle files exist); the one-level-deep structure is easy to navigate, though the self-contained First Principles Thinking Framework is inline content that arguably belongs in a separate reference, keeping it just below a clean 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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 description that concretely states multiple capabilities and pairs them with an explicit, natural "Use when..." trigger clause. It is held back only by a slightly abstract closing action and some missing synonyms that would push specificity and trigger-term quality to the top level.

Suggestions

Replace or sharpen "converges on MVP scope" with a more concrete action (e.g., "writes Goal / In-Scope / Out-of-Scope / Acceptance Criteria into prd.md") to raise specificity.

Add common synonyms users say (e.g., "brainstorming," "planning," "writing a spec") to the trigger clause for broader keyword coverage.

Tighten the when-clause's distinctiveness by naming the Trellis artifact output (PRD/design/implement docs) so it cannot be mistaken for a generic planning skill.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices"), but "converges on MVP scope" is comparatively abstract, leaving minor coverage gaps relative to the fully concrete 5-anchor.	4 / 5
Completeness	It explicitly answers both what ("Guides collaborative requirements discovery...Creates task directory, seeds PRD...converges on MVP scope") and when ("Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like "requirements are unclear," "multiple valid approaches," "new feature," and "complex task" match what users actually say, but common synonyms (brainstorm, planning, spec) are missing, so it stops short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The PRD/MVP/task-directory framing carves a distinct Trellis-planning niche, but trigger terms like "requirements are unclear" and "multiple valid approaches" carry some overlap risk with generic planning skills, keeping it just below a clear-niche 5.	4 / 5
	Total	17 / 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: 88f4834

Reviewed: 9 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.