Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
# Use model IDs from the live catalog (list_models)
"brainstorming"
"primary_model"
"internal"
"explorer_models"
"(model resolved from list_models)"
Model Requirements
Role
Min Context
Capabilities
Primary
200K tokens
Complex reasoning, orchestration
Explorer
100K tokens
Code generation, analysis
Workflow
Phase 0: Problem Analysis (200-300 words)
Objective: Capture problem scope, constraints, and success criteria
How to Ask Users (Without AskUserQuestion):
// Pattern: Use Tasks to track questions, Read/Write for presentation// 1. Write question to temp fileawaitWrite({
file_path: "/tmp/brainstorm-q1.md",
content: `## Question 1 of 3
**What are the main constraints or requirements for this feature?**
Please respond with:
- Functional requirements (what it must do)
- Non-functional requirements (performance, scale)
- Any existing dependencies or integrations
`
});
// 2. Present file and wait for user response// User reads file, provides input via conversation// 3. Summarize understandingconst problemSummary = awaitWrite({
file_path: "/tmp/brainstorm-problem.md",
content: `## Problem Understanding
**Constraints identified:**
- [From user response]
**Success criteria:**
- [Measurable outcomes]
**Scope boundaries:**
- [What's in/out]
---
**Does this accurately capture the problem?** (Reply "yes" to proceed or clarify)
`
});
Gate Type: USER_GATE (requires confirmation)
Phase 1: Parallel Exploration
Objective: Generate diverse solutions via multi-model brainstorming
Fallback Chain Implementation:
interfaceModelResult {
model: string;
success: boolean;
output?: string;
error?: string;
}
asyncfunctionexploreWithFallback(prompt: string,
role: "explorer"): Promise<ModelResult> {
// Use model IDs from `list_models` — pick current models for the task//const fallbackModels = role === "explorer"
? [/* models resolved from `list_models` for code */]
: ["internal"/* plus models from list_models */];
for (const model of fallbackModels) {
try {
const result = awaitTask({
model: model,
prompt: prompt,
timeout_ms: 120000// 2 minute timeout
});
return { model, success: true, output: result };
} catch (error) {
console.warn(`Model ${model} failed:`, error.message);
continue; // Try next in chain
}
}
thrownewError(`All models in fallback chain failed`);
}
# Required for multi-model
OPENROUTER_API_KEY=...
# Optional
BRAINSTORM_TIMEOUT_MS=120000
BRAINSTORM_MAX_RETRIES=2
BRAINSTORM_MIN_MODELS=2 # Minimum models for valid consensus
Model Configuration
{"brainstorming":{"primary":["internal"],"explorers":{// Use model IDs from the live catalog (list_models)"primary_chain":["(another model from list_models)","(another model from list_models)"],"fallback_chain":["(model from list_models)","(model from list_models)"]},"thresholds":{"auto_gate":95,"confirm_gate":60}}}
Performance
Metric
v1.0
v2.0
Improvement
Model failure recovery
0%
95%
Fallback chains
Consensus calculation
Undefined
Defined
Mathematically specified
User interaction
AskUserQuestion
Task+Write
No tool dependency
Parallel execution
Implicit
Explicit
Documented patterns
Comparison: v1.0 vs v2.0
Aspect
v1.0
v2.0
AskUserQuestion
Required
Removed
Model fallbacks
None
3+ per role
Parallel pattern
Described
Code example
Consensus algorithm
Table example
Full implementation
Confidence formula
Mentioned
Math specified
Troubleshooting
4 items
10+ items
Prerequisites
None
Setup guide
Version History
v2.0.0 (2026-01-30):
Removed AskUserQuestion dependency
Added model fallback chains
Explicit parallel execution patterns
Defined consensus matrix algorithm
Added confidence scoring formula
Added prerequisites and setup guide
Expanded troubleshooting section
Winner of blind multi-model voting (3/3 votes, avg confidence 8.7/10)
v1.0.0 (2026-01-30):
Initial release
6-phase workflow
Multi-model exploration
Confidence-based gating
Status: v2.0 Ready for use
Tested: Fallback chains, parallel execution, consensus algorithm
Known Limitations: Requires OpenRouter for multi-model access
