he-brainstorm

Define problem scope, requirements, and decision options before spec or plan stages. Use when the user has ambiguity in what to build, why it matters, or which direction to choose.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 a well-structured, gated workflow with strong validation checkpoints and concrete enums/paths, but it is somewhat redundant and its progressive-disclosure promise is undercut by references that point to files not present in the bundle.

Suggestions

Provide the missing bundle files (SKILL.full.md and references/requirements-artifact-guide.md, brainstorm-workflow-details.md, discovery-interview.md, document-review-pass.md) or remove the dead links so navigation resolves.

De-duplicate stage-routing and pressure-test guidance across Use, Outputs, Procedure, and Anti-patterns into a single source to tighten token use.

Add one complete worked example of a requirements artifact (frontmatter with schema_version/spec_required/risk_level/complexity plus R1/R2 IDs and the Resolve/Deferred question split) so output guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's competence and avoids explaining concepts, but stage-routing and pressure-test guidance is repeated across Use, Outputs, Procedure, and Anti-patterns, so it could be tightened toward the lean score-3 anchor.	2 / 3
Actionability	Concrete enums ("spec_required: none\|lite\|full", "risk_level: low\|medium\|high") and a path template ("docs/brainstorms/YYYY-MM-DD-<topic>-requirements.md") give specific guidance, but there is no complete worked requirements artifact to make output copy-paste ready.	2 / 3
Workflow Clarity	The 13-step Procedure is clearly sequenced with explicit gates (step 12 stops on Resolve-Before-Planning blockers; step 13 stops after recommending), and the Validation section is an explicit fail-fast checklist with feedback loops for error recovery.	3 / 3
Progressive Disclosure	The entry is concise and references are clearly signaled one level deep, but nearly all referenced files are missing from the bundle (SKILL.full.md, the four references/.md, Infrastructure/references/, and ../../../references/* do not exist), so navigation leads to dead ends rather than the score-3 ideal of well-organized one-level references.	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 cleanly answers both what and when with an explicit Use-when trigger, but its action language is somewhat abstract and it sits close to neighboring spec/plan skills, limiting distinctiveness.

Suggestions

Replace abstract verbs ("Define problem scope, requirements, and decision options") with more concrete brainstorm actions users would recognize, e.g. compare directions, pressure-test whether to build, and surface ranked options.

Add more natural trigger phrases users actually say (e.g. "help me think through", "should we build this", "compare options") alongside the existing ambiguity triggers.

Sharpen the boundary against he-spec/he-plan so it is clear this skill fires before a contract exists, reducing overlap with sibling stages.

Dimension	Reasoning	Score
Specificity	Quotes "Define problem scope, requirements, and decision options" name the domain and several actions, but the verbs are abstract process language rather than the multiple concrete operations the score-3 anchor requires.	2 / 3
Completeness	It states what it does ("Define problem scope, requirements, and decision options") and gives an explicit "Use when the user has ambiguity..." trigger, clearly answering both what and when.	3 / 3
Trigger Term Quality	Natural phrases like "ambiguity in what to build" and "which direction to choose" appear, but it leans on jargon ("spec or plan stages") and misses common user variations, matching the score-2 anchor rather than broad coverage.	2 / 3
Distinctiveness Conflict Risk	It targets a niche brainstorm stage but explicitly overlaps with sibling skills ("before spec or plan stages"), so it could still trigger for he-spec/he-plan work rather than being clearly non-conflicting.	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
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 9 missing, 3 deeper-than-1-level, 5 suspicious	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Commit: 5a6027f

Reviewed: 5 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.