instrument-data-to-allotrope

Name: instrument-data-to-allotrope
Author: anthropics

1.7kinstalls2.7kforks

How to install instrument-data-to-allotrope?

anthropics/knowledge-work-plugins/instrument-data-to-allotrope

$npx -y skills add anthropics/knowledge-work-plugins --skill instrument-data-to-allotrope

Installs into the current project.

Summary

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of i

Files · 1

View on GitHub

SKILL.md

1	# Instrument Data to Allotrope Converter
2
3	Convert instrument files into standardized Allotrope Simple Model (ASM) format for LIMS upload, data lakes, or handoff to data engineering teams.
4
5	> Note: This is an Example Skill
6	>
7	> This skill demonstrates how skills can support your data engineering tasks—automating schema transformations, parsing instrument outputs, and generating production-ready code.
8	>
9	> To customize for your organization:
10	> - Modify the `references/` files to include your company's specific schemas or ontology mappings
11	> - Use an MCP server to connect to systems that define your schemas (e.g., your LIMS, data catalog, or schema registry)
12	> - Extend the `scripts/` to handle proprietary instrument formats or internal data standards
13	>
14	> This pattern can be adapted for any data transformation workflow where you need to convert between formats or validate against organizational standards.
15
16	## Workflow Overview
17
18	1. Detect instrument type from file contents (auto-detect or user-specified)
19	2. Parse file using allotropy library (native) or flexible fallback parser
20	3. Generate outputs:
21	- ASM JSON (full semantic structure)
22	- Flattened CSV (2D tabular format)
23	- Python parser code (for data engineer handoff)
24	4. Deliver files with summary and usage instructions
25
26	> When Uncertain: If you're unsure how to map a field to ASM (e.g., is this raw data or calculated? device setting or environmental condition?), ask the user for clarification. Refer to `references/field_classification_guide.md` for guidance, but when ambiguity remains, confirm with the user rather than guessing.
27
28	## Quick Start
29
30	```python
31	# Install requirements first
32	pip install allotropy pandas openpyxl pdfplumber --break-system-packages
33
34	# Core conversion
35	from allotropy.parser_factory import Vendor
36	from allotropy.to_allotrope import allotrope_from_file
37
38	# Convert with allotropy
39	asm = allotrope_from_file("instrument_data.csv", Vendor.BECKMAN_VI_CELL_BLU)
40	```
41
42	## Output Format Selection
43
44	ASM JSON (default) - Full semantic structure with ontology URIs
45	- Best for: LIMS systems expecting ASM, data lakes, long-term archival
46	- Validates against Allotrope schemas
47
48	Flattened CSV - 2D tabular representation
49	- Best for: Quick analysis, Excel users, systems without JSON support
50	- Each measurement becomes one row with metadata repeated
51
52	Both - Generate both formats for maximum flexibility
53
54	## Calculated Data Handling
55
56	IMPORTANT: Separate raw measurements from calculated/derived values.
57
58	- Raw data → `measurement-document` (direct instrument readings)
59	- Calculated data → `calculated-data-aggregate-document` (derived values)
60
61	Calculated values MUST include traceability via `data-source-aggregate-document`:
62
63	```json
64	"calculated-data-aggregate-document": {
65	"calculated-data-document": [{
66	"calculated-data-identifier": "SAMPLE_B1_DIN_001",
67	"calculated-data-name": "DNA integrity number",
68	"calculated-result": {"value": 9.5, "unit": "(unitless)"},
69	"data-source-aggregate-document": {
70	"data-source-document": [{
71	"data-source-identifier": "SAMPLE_B1_MEASUREMENT",
72	"data-source-feature": "electrophoresis trace"
73	}]
74	}
75	}]
76	}
77	```
78
79	Common calculated fields by instrument type:
80	\| Instrument \| Calculated Fields \|
81	\|------------\|-------------------\|
82	\| Cell counter \| Viability %, cell density dilution-adjusted values \|
83	\| Spectrophotometer \| Concentration (from absorbance), 260/280 ratio \|
84	\| Plate reader \| Concentrations from standard curve, %CV \|
85	\| Electrophoresis \| DIN/RIN, region concentrations, average sizes \|
86	\| qPCR \| Relative quantities, fold change \|
87
88	See `references/field_classification_guide.md` for detailed guidance on raw vs. calculated classification.
89
90	## Validation
91
92	Always validate ASM output before delivering to the user:
93
94	```bash
95	python scripts/validate_asm.py output.json
96	python scripts/validate_asm.py output.json --reference known_good.json # Compare to reference
97	python scripts/validate_asm.py output.json --strict # Treat warnings as errors
98	```
99
100	Validation Rules:
101	- Based on Allotrope ASM specification (December 2024)
102	- Last updated: 2026-01-07
103	- Source: https://gitlab.com/allotrope-public/asm
104
105	Soft Validation Approach:
106	Unknown techniques, units, or sample roles generate warnings (not errors) to allow for forward co

People who liked this also viewed

6 picks

Type

instrument-data-to-allotrope

1.7kinstalls2.7kforks

View on GitHub

How to install instrument-data-to-allotrope?

anthropics/knowledge-work-plugins/instrument-data-to-allotrope

$npx -y skills add anthropics/knowledge-work-plugins --skill instrument-data-to-allotrope

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Instrument Data to Allotrope Converter
2
3	Convert instrument files into standardized Allotrope Simple Model (ASM) format for LIMS upload, data lakes, or handoff to data engineering teams.
4
5	> Note: This is an Example Skill
6	>
7	> This skill demonstrates how skills can support your data engineering tasks—automating schema transformations, parsing instrument outputs, and generating production-ready code.
8	>
9	> To customize for your organization:
10	> - Modify the `references/` files to include your company's specific schemas or ontology mappings
11	> - Use an MCP server to connect to systems that define your schemas (e.g., your LIMS, data catalog, or schema registry)
12	> - Extend the `scripts/` to handle proprietary instrument formats or internal data standards
13	>
14	> This pattern can be adapted for any data transformation workflow where you need to convert between formats or validate against organizational standards.
15
16	## Workflow Overview
17
18	1. Detect instrument type from file contents (auto-detect or user-specified)
19	2. Parse file using allotropy library (native) or flexible fallback parser
20	3. Generate outputs:
21	- ASM JSON (full semantic structure)
22	- Flattened CSV (2D tabular format)
23	- Python parser code (for data engineer handoff)
24	4. Deliver files with summary and usage instructions
25
26	> When Uncertain: If you're unsure how to map a field to ASM (e.g., is this raw data or calculated? device setting or environmental condition?), ask the user for clarification. Refer to `references/field_classification_guide.md` for guidance, but when ambiguity remains, confirm with the user rather than guessing.
27
28	## Quick Start
29
30	```python
31	# Install requirements first
32	pip install allotropy pandas openpyxl pdfplumber --break-system-packages
33
34	# Core conversion
35	from allotropy.parser_factory import Vendor
36	from allotropy.to_allotrope import allotrope_from_file
37
38	# Convert with allotropy
39	asm = allotrope_from_file("instrument_data.csv", Vendor.BECKMAN_VI_CELL_BLU)
40	```
41
42	## Output Format Selection
43
44	ASM JSON (default) - Full semantic structure with ontology URIs
45	- Best for: LIMS systems expecting ASM, data lakes, long-term archival
46	- Validates against Allotrope schemas
47
48	Flattened CSV - 2D tabular representation
49	- Best for: Quick analysis, Excel users, systems without JSON support
50	- Each measurement becomes one row with metadata repeated
51
52	Both - Generate both formats for maximum flexibility
53
54	## Calculated Data Handling
55
56	IMPORTANT: Separate raw measurements from calculated/derived values.
57
58	- Raw data → `measurement-document` (direct instrument readings)
59	- Calculated data → `calculated-data-aggregate-document` (derived values)
60
61	Calculated values MUST include traceability via `data-source-aggregate-document`:
62
63	```json
64	"calculated-data-aggregate-document": {
65	"calculated-data-document": [{
66	"calculated-data-identifier": "SAMPLE_B1_DIN_001",
67	"calculated-data-name": "DNA integrity number",
68	"calculated-result": {"value": 9.5, "unit": "(unitless)"},
69	"data-source-aggregate-document": {
70	"data-source-document": [{
71	"data-source-identifier": "SAMPLE_B1_MEASUREMENT",
72	"data-source-feature": "electrophoresis trace"
73	}]
74	}
75	}]
76	}
77	```
78
79	Common calculated fields by instrument type:
80	\| Instrument \| Calculated Fields \|
81	\|------------\|-------------------\|
82	\| Cell counter \| Viability %, cell density dilution-adjusted values \|
83	\| Spectrophotometer \| Concentration (from absorbance), 260/280 ratio \|
84	\| Plate reader \| Concentrations from standard curve, %CV \|
85	\| Electrophoresis \| DIN/RIN, region concentrations, average sizes \|
86	\| qPCR \| Relative quantities, fold change \|
87
88	See `references/field_classification_guide.md` for detailed guidance on raw vs. calculated classification.
89
90	## Validation
91
92	Always validate ASM output before delivering to the user:
93
94	```bash
95	python scripts/validate_asm.py output.json
96	python scripts/validate_asm.py output.json --reference known_good.json # Compare to reference
97	python scripts/validate_asm.py output.json --strict # Treat warnings as errors
98	```
99
100	Validation Rules:
101	- Based on Allotrope ASM specification (December 2024)
102	- Last updated: 2026-01-07
103	- Source: https://gitlab.com/allotrope-public/asm
104
105	Soft Validation Approach:
106	Unknown techniques, units, or sample roles generate warnings (not errors) to allow for forward co

People who liked this also viewed

6 picks

Type