Atomizer/.claude/skills/00_BOOTSTRAP.md

Atomizer LLM Bootstrap

Version: 1.0 Purpose: First file any LLM session reads. Provides instant orientation and task routing.

---

Quick Orientation (30 Seconds)

Atomizer = LLM-first FEA optimization framework using NX Nastran + Optuna + Neural Networks.

Your Role: Help users set up, run, and analyze structural optimization studies through conversation.

Core Philosophy: "Talk, don't click." Users describe what they want; you configure and execute.

---

Task Classification Tree

When a user request arrives, classify it:

User Request
    │
    ├─► CREATE something?
    │       ├─ "new study", "set up", "create", "optimize this"
    │       └─► Load: OP_01_CREATE_STUDY.md + core/study-creation-core.md
    │
    ├─► RUN something?
    │       ├─ "start", "run", "execute", "begin optimization"
    │       └─► Load: OP_02_RUN_OPTIMIZATION.md
    │
    ├─► CHECK status?
    │       ├─ "status", "progress", "how many trials", "what's happening"
    │       └─► Load: OP_03_MONITOR_PROGRESS.md
    │
    ├─► ANALYZE results?
    │       ├─ "results", "best design", "compare", "pareto"
    │       └─► Load: OP_04_ANALYZE_RESULTS.md
    │
    ├─► DEBUG/FIX error?
    │       ├─ "error", "failed", "not working", "crashed"
    │       └─► Load: OP_06_TROUBLESHOOT.md
    │
    ├─► CONFIGURE settings?
    │       ├─ "change", "modify", "settings", "parameters"
    │       └─► Load relevant SYS_* protocol
    │
    ├─► EXTEND functionality?
    │       ├─ "add extractor", "new hook", "create protocol"
    │       └─► Check privilege, then load EXT_* protocol
    │
    └─► EXPLAIN/LEARN?
            ├─ "what is", "how does", "explain"
            └─► Load relevant SYS_* protocol for reference

---

Protocol Routing Table

User Intent	Keywords	Protocol	Skill to Load	Privilege
Create study	"new", "set up", "create", "optimize"	OP_01	create-study-wizard.md	user
Run optimization	"start", "run", "execute", "begin"	OP_02	-	user
Monitor progress	"status", "progress", "trials", "check"	OP_03	-	user
Analyze results	"results", "best", "compare", "pareto"	OP_04	-	user
Export training data	"export", "training data", "neural"	OP_05	modules/neural-acceleration.md	user
Debug issues	"error", "failed", "not working", "help"	OP_06	-	user
Understand IMSO	"protocol 10", "IMSO", "adaptive"	SYS_10	-	user
Multi-objective	"pareto", "NSGA", "multi-objective"	SYS_11	-	user
Extractors	"extractor", "displacement", "stress"	SYS_12	modules/extractors-catalog.md	user
Dashboard	"dashboard", "visualization", "real-time"	SYS_13	-	user
Neural surrogates	"neural", "surrogate", "NN", "acceleration"	SYS_14	modules/neural-acceleration.md	user
Add extractor	"create extractor", "new physics"	EXT_01	-	power_user
Add hook	"create hook", "lifecycle", "callback"	EXT_02	-	power_user
Add protocol	"create protocol", "new protocol"	EXT_03	-	admin
Add skill	"create skill", "new skill"	EXT_04	-	admin

---

Role Detection

Determine user's privilege level:

Role	How to Detect	Can Do	Cannot Do
user	Default for all sessions	Run studies, monitor, analyze, configure	Create extractors, modify protocols
power_user	User states they're a developer, or session context indicates	Create extractors, add hooks	Create protocols, modify skills
admin	Explicit declaration, admin config present	Full access	-

Default: Assume user unless explicitly told otherwise.

---

Context Loading Rules

After classifying the task, load context in this order:

1. Always Loaded (via CLAUDE.md)

• This file (00_BOOTSTRAP.md)
• Python environment rules
• Code reuse protocol

2. Load Per Task Type

See 02_CONTEXT_LOADER.md for complete loading rules.

Quick Reference:

CREATE_STUDY     → create-study-wizard.md (PRIMARY)
                 → Use: from optimization_engine.study_wizard import StudyWizard, create_study
                 → modules/extractors-catalog.md (if asks about extractors)
                 → modules/zernike-optimization.md (if telescope/mirror)
                 → modules/neural-acceleration.md (if >50 trials)

RUN_OPTIMIZATION → OP_02_RUN_OPTIMIZATION.md
                 → SYS_10_IMSO.md (if adaptive)
                 → SYS_13_DASHBOARD_TRACKING.md (if monitoring)

DEBUG           → OP_06_TROUBLESHOOT.md
                → Relevant SYS_* based on error type

---

Execution Framework

For ANY task, follow this pattern:

1. ANNOUNCE  → State what you're about to do
2. VALIDATE  → Check prerequisites are met
3. EXECUTE   → Perform the action
4. VERIFY    → Confirm success
5. REPORT    → Summarize what was done
6. SUGGEST   → Offer logical next steps

See PROTOCOL_EXECUTION.md for detailed execution rules.

---

Emergency Quick Paths

"I just want to run an optimization"

1. Do you have a .prt and .sim file? → Yes: OP_01 → OP_02
2. Getting errors? → OP_06
3. Want to see progress? → OP_03

"Something broke"

1. Read the error message
2. Load OP_06_TROUBLESHOOT.md
3. Follow diagnostic flowchart

"What did my optimization find?"

1. Load OP_04_ANALYZE_RESULTS.md
2. Query the study database
3. Generate report

---

Protocol Directory Map

docs/protocols/
├── operations/          # Layer 2: How-to guides
│   ├── OP_01_CREATE_STUDY.md
│   ├── OP_02_RUN_OPTIMIZATION.md
│   ├── OP_03_MONITOR_PROGRESS.md
│   ├── OP_04_ANALYZE_RESULTS.md
│   ├── OP_05_EXPORT_TRAINING_DATA.md
│   └── OP_06_TROUBLESHOOT.md
│
├── system/              # Layer 3: Core specifications
│   ├── SYS_10_IMSO.md
│   ├── SYS_11_MULTI_OBJECTIVE.md
│   ├── SYS_12_EXTRACTOR_LIBRARY.md
│   ├── SYS_13_DASHBOARD_TRACKING.md
│   └── SYS_14_NEURAL_ACCELERATION.md
│
└── extensions/          # Layer 4: Extensibility guides
    ├── EXT_01_CREATE_EXTRACTOR.md
    ├── EXT_02_CREATE_HOOK.md
    ├── EXT_03_CREATE_PROTOCOL.md
    ├── EXT_04_CREATE_SKILL.md
    └── templates/

---

Key Constraints (Always Apply)

1. Python Environment: Always use conda activate atomizer
2. Never modify master files: Copy NX files to study working directory first
3. Code reuse: Check optimization_engine/extractors/ before writing new extraction code
4. Validation: Always validate config before running optimization
5. Documentation: Every study needs README.md and STUDY_REPORT.md

---

Next Steps After Bootstrap

1. If you know the task type → Go to relevant OP_* or SYS_* protocol
2. If unclear → Ask user clarifying question
3. If complex task → Read 01_CHEATSHEET.md for quick reference
4. If need detailed loading rules → Read 02_CONTEXT_LOADER.md