brainstorming

Socratic questioning protocol + user communication. MANDATORY for complex requests, new features, or unclear requirements. Includes progress reporting and error handling.

Quality

65%

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/brainstorming/SKILL.md

Quality

Content

62%

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

The body is well-structured with clear sequenced workflows and concrete templates, but it pads in generic communication guidance Claude already knows and references a detail file (dynamic-questioning.md) that is not present in the bundle.

Suggestions

Trim the generic 'Communication Principles' and 'Error Categories' tables, which restate knowledge Claude already has, to recover token budget.

Add the missing dynamic-questioning.md reference file to references/, or inline only its essential principles and drop the dangling pointer.

Make remaining pattern-level guidance concrete, e.g. replace 'Offer specific solutions with trade-offs' with an example trade-off response for a representative error category.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean structured tables rather than prose, but generic sections like 'Communication Principles' (Concise, Visual, Specific) and 'Error Categories' add tokens for knowledge Claude already has and could be tightened.	2 / 3
Actionability	Provides concrete templates such as the question format (Question, Why This Matters, Options, If Not Specified) and the numbered Socratic Gate, but some guidance stays at the pattern level ('Offer specific solutions with trade-offs', 'Suggest next step after completion') without specifics.	2 / 3
Workflow Clarity	The Socratic Gate is a clearly sequenced five-step process (STOP, CHECK, ASK, WAIT, SAVE) with an explicit checkpoint ('WAIT - Get response before proceeding') and a feedback loop; no destructive or batch operations are involved so the validation cap does not apply.	3 / 3
Progressive Disclosure	References are one level deep and clearly signaled ('see: dynamic-questioning.md'), but no bundle files exist so dynamic-questioning.md is a dangling reference, and progress/error/completion content that could be separate is inlined into SKILL.md.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly answers both what the skill does and when to trigger it, with an explicit mandatory-use clause. It is weakened by abstract action categories, partial trigger-term coverage, and broad scope that risks overlap with general communication skills.

Suggestions

Replace abstract action categories with concrete operations, e.g. 'Asks clarifying questions, surfaces trade-offs, generates prioritized question banks' instead of 'user communication'.

Add natural trigger terms users actually say ('brainstorm ideas', 'help me decide', 'explore options') alongside 'new features' and 'clarifying requirements'.

Narrow the scope so it doesn't read as a catch-all for progress reporting and error handling, which lowers distinctiveness against general communication skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Socratic questioning protocol', 'user communication') and several action areas ('progress reporting and error handling'), but these are abstract categories rather than the concrete, executable actions the top anchor expects.	2 / 3
Completeness	Explicitly states what it does ('Socratic questioning protocol + user communication... progress reporting and error handling') and when to use it ('MANDATORY for complex requests, new features, or unclear requirements' plus the when_to_use trigger clause), answering both clearly.	3 / 3
Trigger Term Quality	Includes some natural terms ('complex requests', 'new features', 'clarifying requirements', 'Use with /brainstorm workflow') but misses common variations users actually say like 'brainstorm ideas', 'help me decide', or 'what are my options'.	2 / 3
Distinctiveness Conflict Risk	The 'Socratic questioning' framing and /brainstorm trigger carve out a niche, but the 'user communication', 'progress reporting', and 'error handling' scope is broad and could overlap with general communication skills.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/brainstorming/SKILL.md
Commit: 04514f0

Reviewed: about 13 hours 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.