oma-brainstorm

Design-first ideation that explores user intent, constraints, and approaches before any planning or implementation. Use for brainstorming, ideation, exploring concepts, and evaluating approaches.

Quality

75%

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 ./benchmarks/runs/oma/.agents/skills/oma-brainstorm/SKILL.md

Quality

Content

67%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 brainstorming workflow with clear sequencing, approval checkpoints, and concrete guardrails. Its main weakness is conciseness: the same workflow is restated across Scheduling, Structural Flow, and Execution Phases sections, which could be consolidated to respect the token budget.

Suggestions

Consolidate the overlapping Scheduling, Structural Flow/Scenes, and Execution Phases sections into a single canonical workflow description to remove repetition and tighten conciseness.

Add an explicit validate->fix->retry checkpoint around the design-write step (e.g. 'After saving to docs/plans/designs/, confirm the artifact parses and matches the approved sections before handing off to /plan') to push workflow clarity to a 5.

Provide a short example exchange or a minimal design-document template so the guidance is copy-paste ready rather than purely descriptive.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of explanations Claude already knows, but the workflow is restated across overlapping sections (Scheduling, Structural Flow/Scenes, Execution Phases, and overlapping Guardrails/Common Pitfalls) that re-cover the same steps and could be consolidated.	3 / 5
Actionability	Gives concrete, specific guidance for an instruction-only process skill ("Ask one clarifying question at a time", "Present 2-3 approaches with tradeoffs", save to docs/plans/designs/), with named guardrails and pitfalls; minor gaps are the absence of an example exchange or output template.	4 / 5
Workflow Clarity	A clearly sequenced multi-step process (PREPARE->ACQUIRE->REASON->VERIFY->FINALIZE plus Execution Phases 1-6) with approval gates and a failure/recovery section providing feedback loops; just short of a 5 because the design-write step lacks an explicit validate->fix->retry checkpoint.	4 / 5
Progressive Disclosure	Well-organized with clearly signaled references to shared protocols (../_shared/core/*.md) at one level deep, and no nested references; minor gap is that several inline tables (Actions, Resource scope) and the duplicated phase listings could be externalized into bundle files, though none are provided.	4 / 5
	Total	15 / 20 Passed

Description

82%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 strong: it clearly states both what the skill does and when to use it, with natural trigger terms and a distinct niche bounded against planning/implementation. The only weakness is that the described actions stay at an abstract process level rather than naming concrete operations.

Suggestions

Add one or two more concrete action verbs (e.g. 'compares approaches with tradeoffs', 'drafts an approved design document') to lift specificity above the abstract 'explores intent/constraints/approaches' phrasing.

Consider adding a user-natural trigger like 'I have an idea' or 'let's design something' as an explicit synonym to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("design-first ideation") and 1-2 concrete actions ("explores user intent, constraints, and approaches"), but the actions stay at an abstract process level rather than listing multiple specific concrete operations like the 5-anchor examples.	3 / 5
Completeness	Explicitly answers both what ("Design-first ideation that explores user intent, constraints, and approaches before any planning or implementation") and when ("Use for brainstorming, ideation, exploring concepts, and evaluating approaches") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("brainstorming", "ideation", "exploring concepts", "evaluating approaches") with good coverage; a few natural synonyms (e.g. "I have an idea") are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (exploratory design before planning/implementation) with distinct triggers, and explicitly bounds it against planning and implementation, giving minimal conflict risk with adjacent skills.	5 / 5
	Total	17 / 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: benchmarks/runs/oma/.agents/skills/oma-brainstorm/SKILL.md
Commit: 032c988

Reviewed: 2 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.