CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 well-structured process skill with a clearly sequenced workflow, explicit gates, and highly actionable rules. Weaknesses are moderate inlining that could be offloaded to reference files and some repetition of the approval gate across sections.

Suggestions

Move the Thinking Framework: First Principles Analysis section into a references/ file and link to it, keeping SKILL.md focused on the planning workflow and gates.

Consolidate the implementation-approval rule into the Non-Negotiable Planning Contract and reference it once from the Planning Flow, Question Rules, and Quality Bar instead of restating it in each.

Add one concrete example of a well-formed single question (decision needed, why it matters, recommendation, trade-off) and a minimal prd.md skeleton to make the common case copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of concept over-explanation, but the implementation-approval rule is restated in roughly four sections (Planning Contract, Planning Flow steps 8-9, Question Rules, Quality Bar) and could be consolidated.

4 / 5

Actionability

Provides an executable task.py create command, exact per-question required structure, and explicit artifact section lists, but lacks a concrete example of a well-formed question or a minimal prd.md skeleton covering the common case.

4 / 5

Workflow Clarity

The 9-step Planning Flow has explicit validation checkpoints (Requirement Convergence Gate, PRD Convergence Pass, Quality Bar) and feedback loops ("repeat from step 2", "repeat the final review" after material changes).

5 / 5

Progressive Disclosure

No bundle files exist and all ~200 lines are inlined; section headers give reasonable structure, but self-contained material like the First Principles Thinking Framework is inlined rather than split into a referenced file.

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 description: third-person voice, five concrete actions, and an explicit multi-condition "Use when" clause. The only weaknesses are a few missing natural trigger synonyms and slightly broad trigger conditions that could overlap other planning-related skills.

DimensionReasoningScore

Specificity

"Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope" lists five concrete, distinct actions with comprehensive coverage of the skill's behavior.

5 / 5

Completeness

Explicitly answers both "what" (five concrete actions) 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

"requirements are unclear", "multiple valid approaches", and "describes a new feature or complex task" are natural user phrasings, but common synonyms like "brainstorm", "planning", "spec", or "requirements gathering" are missing.

4 / 5

Distinctiveness Conflict Risk

"requirements discovery before implementation" is a distinct planning niche, but the broad triggers "multiple valid approaches" and "complex task" carry minor overlap risk with generic planning or architecture skills.

4 / 5

Total

18

/

20

Passed

Validation

100%

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
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.