detect-silent-processing-failures
Identifies suspicious pipeline outputs even when no exceptions occur by validating metadata and file structures.
Install
mkdir -p .claude/skills/detect-silent-processing-failures && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18496" && unzip -o skill.zip -d .claude/skills/detect-silent-processing-failures && rm skill.zipInstalls to .claude/skills/detect-silent-processing-failures
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use to detect suspicious processor outputs even when no exception is thrown. Keywords: silent failure, metadata validation, glb checks, anomaly detection.Key capabilities
- →Report metadata accounting inconsistencies
- →Validate referenced models for existence and size
- →Flag suspicious mesh and bounds values
- →Run checks in strict mode for more rigorous validation
- →Provide a compact summary of findings
- →Offer detailed per-item evidence for flagged issues
How it works
This skill executes a Python script to check processed outputs for silent failures by validating metadata, model references, and mesh/bounds values.
Inputs & outputs
When to use detect-silent-processing-failures
- →Validating pipeline outputs
- →Checking metadata consistency
- →Flagging suspicious mesh or bounds data
About this skill
Detect Silent Processing Failures Skill
Use this skill after processor runs to identify suspicious outcomes.
Outcomes
- Metadata accounting inconsistencies are reported.
- Referenced models are validated for existence and size.
- Suspicious mesh and bounds values are flagged.
Core Command
python3 scripts/check_processed_outputs.py --metadata data/outputs/metadata.json
Strict mode:
python3 scripts/check_processed_outputs.py --metadata data/outputs/metadata.json --strict
Warning Heuristics
hhh_countdiffers fromhhh_inspected.model_count + export_failed_countdiffers fromhhh_inspected.- Item references missing or empty model file.
- Invalid
mesh_boundsstructure.
Agent Guidance
- Default to warnings only unless strict mode requested.
- Provide a compact summary and detailed per-item evidence.
- Keep checks deterministic and schema-version aware.
When not to use it
- →When an exception is already thrown by the processor
- →When only basic error detection is needed
- →When schema-version awareness is not a concern
Limitations
- →Relies on specific warning heuristics for detection
- →Default behavior is warnings only unless strict mode is requested
- →Checks are deterministic and schema-version aware
How it compares
This skill proactively identifies subtle processing failures that do not throw exceptions, providing a deeper level of data integrity validation than relying solely on error codes.
Compared to similar skills
detect-silent-processing-failures side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| detect-silent-processing-failures (this skill) | 0 | 4mo | Review | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| backtesting-frameworks | 17 | 2mo | No flags | Advanced |
| python-repl | 6 | 4mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
backtesting-frameworks
wshobson
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.
python-repl
gptme
Interactive Python REPL automation with common helpers and best practices
python-playground
pydantic
Run and test Python code in a dedicated playground directory. Use when you need to execute Python scripts, test code snippets, investigate CPython behavior, or experiment with Python without affecting the main codebase.
mflux-manual-testing
filipstrand
Manually validate mflux CLIs by exercising the changed paths and reviewing output images/artifacts.
examples-auto-run
openai
Run python examples in auto mode with logging, rerun helpers, and background control.