Input File Skill
Parse, modify, validate, and patch simulator input files. Use when working with reservoir simulation input files, testing scenarios, or validating simulation configurations. This implementation supports reference format (.DATA); other simulators use different extensions (e.g., .afi, .DAT). Supports natural language modifications, keyword patching, and syntax validation.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/NVIDIA/GenerativeAIExamples --skill input_file_skillWhat comes with it
38 811 bytes besides the instructionThe instruction itself
11 sections, as written by the authorDATA File Processing Skill
This skill provides tools for working with simulator input files. The reference format uses .DATA as the primary input extension; other simulators use different extensions.
Overview
The DATA File Processing skill enables agents to:
- Parse simulator input files to understand their structure and sections
- Modify simulator input files using natural language instructions
- Validate simulator input files for syntax and consistency
- Patch specific keyword blocks without rewriting entire files
Tools
parse_simulation_input_file
Parses a simulator input file and returns its structure (sections found). Reference format uses .DATA extension.
Usage:
parse_simulation_input_file(file_path: str) -> str
Example:
parse_simulation_input_file("data/example_cases/SPE10/CASE/SPE10_TOPLAYER.DATA")
Returns: A string listing all sections found (e.g., "Sections found: HEADER, RUNSPEC, GRID, PROPS, SOLUTION, SUMMARY, SCHEDULE")
When to use: First step in scenario testing chain (TOOL_DECISION_TREE.md Section 2.4) or when user asks to parse/list sections of a simulator input file.
modify_simulation_input_file
Modifies a simulator input file based on natural language instructions. Can modify entire file or target specific keyword blocks.
Usage:
modify_simulation_input_file(
file_path: str,
modifications: str,
output_path: Optional[str] = None,
llm_model: Optional[str] = None,
manual_context: Optional[str] = None,
example_context: Optional[str] = None,
target_keyword: Optional[str] = None
) -> str
Parameters:
file_path: Path to the simulator input file to modifymodifications: Natural language description of changes (e.g., "Increase water injection rate for well I1 to 55")output_path: Where to save modified file (default: overwrite original)llm_model: Optional model override for LLM-based modificationsmanual_context: Optional simulator manual excerpt for the relevant keywordexample_context: Optional example DATA snippets for the relevant keywordtarget_keyword: If set, only this keyword block is edited; rest of file is copied unchanged
Example:
modify_simulation_input_file(
file_path="SPE1CASE1.DATA",
modifications="Increase water injection rate for well I1 in WCONINJE to 55",
output_path="SPE1CASE1_AGENT_GENERATED.DATA",
target_keyword="WCONINJE"
)
When to use: In scenario test chain (Section 2.4) after parse_simulation_input_file → simulator_manual → simulator_examples, or when user requests modifications to a simulator input file.
patch_simulation_input_keyword
Patches a specific keyword block in a simulator input file without modifying other parts. Useful for auto-fixes.
Usage:
patch_simulation_input_keyword(
file_path: str,
keyword: str,
output_path: str,
item_index: Optional[int] = None,
new_value: Optional[str] = None,
new_block_content: Optional[str] = None
) -> str
Parameters:
file_path: Path to the simulator input filekeyword: Keyword to patch (e.g., WELLDIMS, TABDIMS)output_path: Path for the new file (original is unchanged)item_index: 1-based index of the numeric item to replacenew_value: New value for the item (used with item_index)new_block_content: Exact new block content (keyword line + data). If set, item_index/new_value are ignored.
Example:
patch_simulation_input_keyword(
file_path="SPE1CASE1.DATA",
keyword="WELLDIMS",
output_path="SPE1CASE1_FIXED.DATA",
item_index=1,
new_value="10"
)
When to use: In HITL apply fix flow (Section 2.2) for auto-fixes, or when only a specific keyword needs to be changed.
Workflow Integration
This skill integrates with the Simulator Agent's decision tree (TOOL_DECISION_TREE.md):
- Scenario Test Chain (Section 2.4):
parse_simulation_input_file → simulator_manual → simulator_examples → modify_simulation_input_file → run_and_heal
- HITL Apply Fix (Section 2.2):
patch_simulation_input_keyword or modify_simulation_input_file → run_and_heal
Implementation Details
Tools are implemented as LangChain tools with Pydantic input schemas. The skill uses:
- utils.py: Shared utility functions for parsing, keyword finding, and LLM integration
- Tool modules: Individual tool implementations in separate modules
- LLM integration: Uses ChatOpenAI for natural language modifications
Error Handling
All tools return descriptive error messages if:
- Files are not found
- Syntax errors occur during parsing
- LLM modifications fail
- Validation checks fail
References
- OPM Flow Manual - Detailed keyword reference
- Tool Decision Tree - Routing logic
- Examples - Usage examples
Testing
Run the test suite:
python -m simulator_agent.skills.input_file_skill.test --file path/to/test.DATA
Or test individual tools:
python -m simulator_agent.skills.input_file_skill.test --file path/to/test.DATA --tool parse_simulation_input_file
The test script is located in test.py at the root of the skill directory.
Other skills for the same job
different authors, same section of the catalogue
Plan, write, and diagnose Instagram Reels that earn cold-audience reach. Use whenever someone wants a reels script or reels hook for a specific Reel, is debugging why a Reel flopped, wants to know if a draft is worth testing with Trial Reels before going public, or needs a reels caption tuned for the post-hashtag instagram algorithm. Built around what Mosseri has publicly named as the signal hierarchy (watch time, sends per reach, likes per reach), the Trial Reels test-then-publish loop, the Original Content Guidelines and 30-day recovery window, the Edits app, and Reels Insights metrics (skip rate, share rate, followers from this post). Covers a Reels-specific reels strategy: send-driving CTAs, originality without watermarks, audio licensing by account type, captions as the primary SEO signal, and the anti-patterns that quietly cap distribution. Pattern-based guidance, not a virality promise.
Perform relative value analysis on bonds by combining pricing, yield curve context, credit spreads, and scenario stress testing. Use when analyzing bond richness/cheapness, computing spread decomposition, comparing bonds, assessing bond value vs curves, or running rate shock scenarios.
Build quick IRR/MOIC sensitivity tables for PE deal evaluation. Models returns across entry multiple, leverage, exit multiple, growth, and hold period scenarios. Use when sizing up a deal, stress-testing assumptions, or preparing IC returns exhibits. Triggers on "returns analysis", "IRR sensitivity", "MOIC table", "what's the return at", "model the returns", or "back of the envelope".
Design lean startup experiments (pretotypes) for a new product. Creates XYZ hypotheses and suggests low-effort validation methods like landing pages, explainer videos, and pre-orders. Use when validating a new product idea, creating pretotypes, or testing market demand.
Amazon Alexa for Shopping Q&A automation: submits questions to Amazon's Alexa/Rufus AI shopping assistant and collects response text; supports optional keyword search context (navigate to search results page before asking for category-specific answers). Use when user mentions Amazon Alexa, Rufus, Amazon shopping assistant, Amazon AI chat, ask Amazon, Amazon Q&A, automate Alexa questions, Rufus chatbot, Amazon assistant automation, collect Alexa responses, bulk question submission to Amazon, keyword search context, category research. Also applies to extracting Amazon product recommendations from conversational AI, automating repeated queries to Amazon's AI shopping feature, collecting Alexa shopping responses at scale, or market research within a specific product category.
When the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions 'UGC,' 'user-generated content,' 'creator ads,' 'Spark Ads,' 'whitelisting,' 'AI UGC,' 'Arcads,' 'Creatify,' 'creator brief,' or 'UGC testing.' This skill covers the UGC growth framework from creator recruitment through AI-powered scaling. Do NOT use for technical implementation, code review, or software architecture.
Triage ASM/recon output for ownership before testing — separate the target's real assets from namespace-collision noise. Automated recon keyword-matches on the brand name, so for any target whose name is a common/dictionary word, the output is dominated by assets belonging to UNRELATED same-named companies (repos, cloud buckets, mobile apps, breach corpora, typosquats). Built from an authorized engagement where an ASM report's "Criticals" were overwhelmingly false positives and the combo/repos/mobile/bucket lists were polluted with unrelated same-named orgs. Use at the START of any engagement, immediately on receiving any ASM/recon/OSINT dataset, BEFORE testing anything.
Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calculator; not for organic dark-social share attribution or GA4 direct-traffic decomposition — use dark-social-attributor. 付费广告归因对账/去重/增量
How to use it
Take nvidia/input_file_skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.