resource-constraint
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/resource-constraintQuantifies resource constraints across compute, data, time, human, and financial categories
- Evaluates if available resources meet experiment requirements
- Uses resource-quantification, critical-chain-identification, and buffer-sizing SOPs
- Analyzes gaps between resource demand and supply to prioritize constraints
- Delivers structured tables and critical path insights for resource planning
SKILL.md
.github/skills/resource-constraintView on GitHub ↗
--- name: resource-constraint description: "Are resources sufficient? — Quantify compute, data, time, human, and financial resource constraints" version: 1.0.0 category: experiment-execution type: strategy used-by: constraint-analysis sops: - resource-quantification - critical-chain-identification - buffer-sizing tactics: - sensitivity-ranking --- # Strategy: Resource Constraint ## Methodology Systematic resource feasibility assessment: - **Demand modeling**: What does the experiment need? - **Supply inventory**: What do we actually have? - **Gap analysis**: Where does demand exceed supply? - **Critical chain**: Which resource constraints lie on the critical path? - **Buffer sizing**: How much slack do we need? Resource categories: | Category | Examples | |----------|----------| | Compute | GPU hours, CPU cores, memory, storage | | Data | Training samples, labeled data, access rights | | Time | Calendar time, researcher hours, review cycles | | Human | Expertise, headcount, availability | | Financial | Budget, cost per experiment, opportunity cost | ## Execution Flow 1. **Quantify Resources** → call `resource-quantification` SOP - Input: experiment plan, resource inventory - Output: demand/supply/gap table per category 2. **Identify Critical Chain** → call `critical-chain-identification` SOP - Input: task list with resource assignments - Output: critical chain with resource contention points 3. **Size Buffers** → call `buffer-sizing` SOP - Input: critical chain, task duration estimates - Output: project/feeding/resource buffer recommendations 4. **Rank Sensitivity** → invoke `sensitivity-ranking` tactic - Determine which resource gap is most binding 5. **Report** → synthesize feasibility assessment - Go/No-Go/Conditional recommendation ## Budget Gate | Resource | Budget | Notes | |----------|--------|-------| | Subagent calls | ≤6 | 3 SOPs + synthesis | | Iterations | ≤2 | Re-quantify if estimates change | | Output size | ≤3000 tokens | Gap table + recommendation |
More from yogsoth-ai/de-anthropocentric-research-engine
- abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
- ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
- ablation-component-mappingMap system architecture to ablatable units for ablation studies
- ablation-designDesign ablation studies to isolate component contributions in ML systems
- ablation-executionRemove components one by one from a system, record the response/impact of each removal.
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- abstraction-ladderPerform bisociation at multiple abstraction levels
- abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
- abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.