CtrlK
BlogDocsLog inGet started
Tessl Logo

brainstorm

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

69

Quality

84%

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

The canonical home for this skill is brainstorm in NeoLabHQ/context-engineering-kit

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 body is a well-structured, actionable dialogue workflow with explicit checkpoints and a feedback loop. The only notable weakness is redundancy between "The Process" and "Key Principles", and a lack of concrete example dialogue.

Suggestions

Remove or tighten the "Key Principles" section since most bullets duplicate guidance already stated under "The Process", to recover the token budget.

Add one short example exchange (e.g., a sample multiple-choice refining question and a brief design-section excerpt) to make the collaborative dialogue pattern concrete.

Clarify the conditional in "After the Design" by showing the exact section ordering expected in the specification file with a one-line template.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, but the "Key Principles" section largely restates points already made in "The Process" (one question at a time, multiple choice, explore alternatives, incremental validation, be flexible).

4 / 5

Actionability

Concrete directives are given (one question per message, six approaches with numeric probabilities, 200-300 word sections, where to write the approach in the spec file), but no example dialogue or sample design section is provided to anchor the guidance.

4 / 5

Workflow Clarity

The process is clearly sequenced (understanding → exploring → presenting → after) with explicit per-section validation checkpoints ("Ask after each section whether it looks right"), a feedback loop ("Be ready to go back and clarify"), and a coverage checklist (architecture, components, data flow, error handling, testing).

5 / 5

Progressive Disclosure

The skill is a self-contained single-purpose dialogue process under ~50 lines with no need for external bundle files, and content is well-organized into clearly signaled sections, satisfying the simple-skill exception.

5 / 5

Total

18

/

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.

The description is well-crafted: it states both what the skill does and when to use it, with concrete trigger phrases and a useful negative trigger. Minor gaps in synonym coverage keep trigger term quality and distinctiveness just below maximum.

DimensionReasoningScore

Specificity

Lists several concrete techniques — "collaborative questioning, alternative exploration, and incremental validation" — naming the domain and three specific actions, though coverage of the full brainstorming process is not exhaustive.

4 / 5

Completeness

Explicitly answers both what ("refines rough ideas into fully-formed designs...") and when ("Use when creating or developing, before writing code or implementation plans"), plus a concrete negative trigger ("Don't use during clear 'mechanical' processes").

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("creating or developing", "before writing code or implementation plans") that users would plausibly say, but common synonyms like "brainstorm", "design", or "refine an idea" are missing.

4 / 5

Distinctiveness Conflict Risk

The pre-implementation "refine ideas" niche is mostly distinct from execution skills, and the negative "mechanical processes" trigger reduces overlap, though it could still collide with general planning/design skills.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeoLabHQ/context-engineering-kit
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.