baram2584/AbaqusSubroutineDev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: refresh Abaqus subroutine guidance

Browse Source
This commit is contained in:
KOKO\Mimi
2026-08-18 11:27:22 +09:00
parent a3197dc2e3
commit e76c1b96fd
64 changed files with 498 additions and 4560 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.codex/skills/abaqus-subroutine-research/SKILL.md
+14 -6
View File
@@ -7,6 +7,8 @@ description: Use when collecting Abaqus User Subroutine research evidence from o
Use this skill to collect source-backed Research evidence for Abaqus User Subroutine work while separating verified facts from inference.
**REQUIRED SUB-SKILL:** Use `fem-theory-query` for finite element theory, formulation, solver behavior, benchmark, or numerical verification knowledge.
## Inputs
Read first:
@@ -15,17 +17,22 @@ Read first:
- `docs/ABAQUS_SUBROUTINE_AGENT_DESIGN.md`
- `docs/research/README.md`
- `docs/requirements/<feature-id>.md`
- `docs/AbaqusUserSubroutineManual/INDEX_MAP.md`
- `docs/AbaqusUserSubroutineManual/INDEX.md`
- User-provided references, official Abaqus documentation links, books, papers, and benchmark sources
## Workflow
1. Define exact research questions from requirements and open issues.
2. Search source priorities in order: official Abaqus documentation, Abaqus User Subroutines Reference Guide, Abaqus Analysis User's Guide, books, papers, and benchmark sources.
3. Record source reliability tier, citation, scope, assumptions, and applicability limits.
4. Extract only facts needed by downstream formulation, Abaqus ABI interface definition, TDD test models, and Fortran implementation.
5. Separate verified facts from inference.
6. Identify candidate benchmark models, closed-form checks, patch tests, tangent checks, and negative tests.
7. Record unresolved conflicts or missing evidence as open issues.
2. For FEM knowledge, use `fem-theory-query` and retain the returned wiki evidence.
3. For Abaqus User Subroutine manual facts, locate the section in `INDEX_MAP.md`, read the complete `INDEX.md` record, then read every listed `source_ranges` span in order.
4. Treat `INDEX.md` summaries, keywords, and content anchors as retrieval metadata rather than authoritative facts.
5. Search other sources as needed: books, peer-reviewed papers, official benchmarks, and project-provided references.
6. Record source reliability tier, citation, scope, assumptions, and applicability limits.
7. Extract only facts needed by downstream formulation, Abaqus ABI interface definition, TDD test models, and Fortran implementation.
8. Separate verified facts from inference.
9. Identify candidate benchmark models, closed-form checks, patch tests, tangent checks, and negative tests.
10. Record unresolved conflicts or missing evidence as open issues.
## Output Contract
@@ -44,6 +51,7 @@ Produce or revise `docs/research/<feature-id>-research.md` with Source Inventory
- Source tiers are explicit.
- Each extracted fact links to a cited source.
- Each FEM claim traces to `fem-theory-query` evidence; each Abaqus manual claim traces to a section and every source span used.
- Inference is labeled as inference.
- Benchmark applicability limits are clear enough for Formulation and Reference Model Agents.