oma-brainstorm
Explore goals, constraints, and alternative approaches before choosing a design. Use when the user requests ideation or design exploration.
How do I install this agent skill?
npx skills add https://github.com/first-fluke/oh-my-agent --skill oma-brainstormIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The oma-brainstorm skill is a design-focused ideation tool following the Open Management Agent (OMA) protocol. It incorporates structured design phases, mandatory blind reviews for sensitive changes, and strict execution guardrails that prevent unauthorized code execution or infrastructure changes. No security risks were identified.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Brainstorm - Design-First Ideation
Scheduling
Goal
Explore user intent, constraints, and alternative approaches before planning or implementation, then preserve an approved design for downstream planning.
Intent signature
- User says they have an idea, want to brainstorm, compare approaches, explore concepts, or design before planning.
- Request is ambiguous enough that implementation or task planning would be premature.
When to use
- Exploring a new feature idea before planning
- Understanding user intent and constraints before committing to an approach
- Comparing multiple design approaches with trade-offs
- When the user says "I have an idea" or "let's design something"
- Before invoking
/planfor complex or ambiguous requests
When NOT to use
- Requirements are already clear and well-defined -> use
oma-pmdirectly - Implementing actual code -> delegate to specialized agents
- Performing code reviews -> use
oma-qa - Debugging existing issues -> use
oma-debug
Expected inputs
- Early idea, ambiguous goal, product concept, design question, or set of constraints
- Existing project context when the idea must fit a codebase or product direction
- User preferences and approval gates
Expected outputs
- Clarified intent and constraints
- Viable approaches as prose briefs (scenario, mechanism, residual risk), with comparison and recommendation when alternatives aid the decision
- Section-by-section approved design document
- Blind-review issue list (Tier 1 resolved, Tier 2/3 resolved or explicitly deferred)
- Saved design artifact before handoff to planning
Dependencies
- Shared context loading, clarification protocol, quality principles, and skill routing
- Optional
resources/triz-lite.mdfor contradiction-shaped approach seeding - Per-agent reviewer dispatch (e.g.
qa-reviewer,architecture-reviewer) for the high-stakes blind-review escalation path - Downstream PM workflow for task decomposition after design approval
- Project memory for coordination summaries;
docs/decisions/for retained approach proposals
Structural Flow
Transitions
- If requirements become clear and implementation-ready, transition to PM planning.
- If user rejects an approach, revise before moving to detailed design.
- If implementation pressure appears early, defer it until design approval.
- If approaches collapse into knob-turning on one axis, load
resources/triz-lite.mdand reseed, then re-present prose briefs.
Failure and recovery
- If the user cannot answer a question, propose assumptions and ask for confirmation.
- If scope expands, split the design into smaller sections.
- If alternatives collapse into one option, identify the real constraint causing that; use TRIZ-lite only when that constraint is a technical/UX contradiction.
Exit
- Success: approved design exists and is ready for planning.
- Partial success: open questions and assumptions are explicit.
Logical Operations
Canonical workflow path
- Confirm that the request is exploratory or ambiguous rather than ready for implementation, and load enough project context to understand constraints. Ask one clarifying question at a time, starting with intent and constraints, not solutions.
- (Optional) If technical/UX contradiction or same-axis approaches only →
resources/triz-lite.md. - Present viable alternatives as prose briefs and compare them when useful; do not invent extra options to meet a count; reuse an existing selection or delegated choice and resolve only an open material choice. In an active OMA workflow, record the actual approach, rationale, evidence, and design/option revision with
brainstorm.option-selection; verify with the matchinginstanceIdas--instance(workflow Step 3 owns the commands). - Design section by section within existing authorization, then blind review: independent lenses suited to the uncertainty and stakes critique the design; consolidate a tiered issue list and resolve Tier 1 issues (fresh-context reviewer subagents for high-stakes designs).
- Save the approved approach to
docs/decisions/{NNN}-{name}.mdand updatedocs/decisions/index.mdbefore handing off to planning. Keep this directory versioned. Readdocs/plans/designs/anddocs/design-docs/only as legacy fallback until migration;designnames UI work. Record a coordination summary that links the decision document, then hand off with a summary.
Resource scope and effects
Reads existing project context when the idea must fit a codebase. Writes the approved design under docs/decisions/ (the design document may carry an optional TRIZ-lite appendix), updates docs/decisions/index.md, and records a coordination summary in project memory. The high-stakes blind review is the only subagent-spawning path in this skill. The saved design feeds downstream planning; this skill does not implement code.
Guardrails
- No implementation or planning before design approval - brainstorm produces a design document, not code or task plans
- One question at a time - ask clarification and approval questions through the available asynchronous question tool first, following
references/_shared/core/clarification-protocol.md; fall back to a permitted question tool or plain text. Continue independent work while waiting, and never infer approval from silence or a preselected option. - Compare viable approaches - offer two or three when they aid the decision, and explain constraints when fewer remain. Recommend according to the actual goal, effort, reversibility, and risk. Do not favor a larger structural change solely because of its label.
- Explain viable approaches in prose - state scenario, mechanism, residual risk, and effort. Use a comparison matrix when it helps the decision, then give the recommendation; a single constrained option needs its rationale, not invented alternatives
- Section-by-section design - present the design incrementally; reuse existing decisions and delegated authority, asking only for unresolved material choices under the shared execution policy
- Blind review before save - mandatory unless the design is trivially small (1-2 files, low stakes); lenses critique independently; use fresh-context reviewer subagents for architecturally significant, hard-to-reverse, or security-/compliance-sensitive designs
- YAGNI - do not over-engineer; design only what is needed for the stated goal
- TRIZ-lite is optional - only for technical/UX contradictions or same-axis collapse; max 3–5 principles from the curated set; no fake scores, full TRIZ/ARIZ, or classical matrices; seeds feed Step 3 briefs and do not replace user approval
- Save the selected approach, then transition - persist it in
docs/decisions/before handing off to/plan. Run-specific critique andresult-*.mdreports belong in.agents/results/; leave the destination in the source report when promoting a document intodocs/
References
- TRIZ-lite (optional Step 3 seeding):
resources/triz-lite.md - Context loading:
references/_shared/core/context-loading.md - Clarification protocol:
references/_shared/core/clarification-protocol.md - Quality principles:
references/_shared/core/quality-principles.md - Skill-to-agent mapping:
references/_shared/core/skill-routing.md
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/first-fluke/oh-my-agent/oma-brainstorm">View oma-brainstorm on skillZs</a>