oma-brainstorm

Explore goals, constraints, and alternative approaches before choosing a design. Use when the user requests ideation or design exploration.

Quality

68%

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 ./skills/oma-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 body is a well-sequenced, actionable orchestration skill with strong validation checkpoints and feedback loops. Its main drag is conciseness: the same workflow rules are repeated across several overlapping sections.

Suggestions

Consolidate the repeated workflow guidance: 'one question at a time', 'blind review before save', 'TRIZ-lite optional', and '2-3 approaches' each appear in Scheduling, Scenes, Canonical workflow path, Guardrails, Execution Phases, and Pitfalls — state each once in Guardrails and reference it.

Reduce redundancy between the Scenes list, the Canonical workflow path, and the Execution Phases, which describe the same flow three times in different shapes.

Move the detailed TRIZ-lite usage into the referenced resources/triz-lite.md and keep only the trigger condition inline, so the body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body adds no concept-padding Claude already knows, but the same core rules (one question at a time, blind review before save, TRIZ-lite optional, 2-3 approaches, save-then-transition) are restated across Scheduling, Scenes, Canonical workflow path, Guardrails, Execution Phases, and Pitfalls, so it could be tightened noticeably.	3 / 5
Actionability	Gives concrete commands ('oma state emit', 'oma state verify --checkpoint option-selection') and specific structural guidance (prose briefs with scenario/mechanism/residual risk, 4-8 lenses, Tier 1/2/3 issues), with only minor gaps keeping it from fully copy-paste-ready.	4 / 5
Workflow Clarity	Sequences the process clearly via Scenes and seven Execution Phases, with explicit validation checkpoints (section-by-section approval, blind review, state verify), feedback loops in the Failure-and-recovery section, and checklists in Guardrails and Pitfalls.	5 / 5
Progressive Disclosure	A clear References section points one level deep to shared resources (triz-lite.md, _shared/core/*.md) and the body is an overview, but the workflow detail is largely inlined in SKILL.md and the referenced triz-lite file is not present in the bundle, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

62%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 cleanly states what the skill does and when to use it with an explicit trigger clause, avoiding vague fluff. Its main weakness is narrow trigger coverage that omits the most natural phrasings like 'brainstorm'.

Suggestions

Broaden the trigger clause to include natural user phrasings such as 'brainstorm', 'I have an idea', or 'compare approaches' rather than only 'ideation or design exploration'.

Make the 'what' slightly more concrete by naming the concrete artifacts produced (e.g., 'produce 2-3 approach briefs and an approved design document') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('Explore goals, constraints, and alternative approaches', 'choosing a design') but they stay at a moderate abstraction rather than the concrete, multiple-action coverage of the 4/5 anchors.	3 / 5
Completeness	Explicitly answers both what ('Explore goals, constraints, and alternative approaches before choosing a design') and when ('Use when the user requests ideation or design exploration'); the 'when' clause is present and specific but narrow, so not a 5.	4 / 5
Trigger Term Quality	Includes 'ideation' and 'design exploration' as triggers but misses common natural variants a user would say, notably 'brainstorm' (the skill's own name) and 'I have an idea', so it lands at 'some relevant keywords, missing variations'.	3 / 5
Distinctiveness Conflict Risk	Carves a clear ideation/design-exploration niche with distinct triggers and minimal conflict risk, though it could still overlap with general planning skills, keeping it just below a 5.	4 / 5
	Total	14 / 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: first-fluke/oh-my-agent
Path: skills/oma-brainstorm/SKILL.md
Commit: ce19702

Reviewed: 4 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.