validate-data

Name: validate-data
Author: anthropics

2.5kinstalls2.7kforks

How to install validate-data?

anthropics/knowledge-work-plugins/validate-data

$npx -y skills add anthropics/knowledge-work-plugins --skill validate-data

Installs into the current project.

Summary

QA an analysis before sharing -- methodology, accuracy, and bias checks. Use when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually s

Files · 1

View on GitHub

SKILL.md

1	# /validate-data - Validate Analysis Before Sharing
2
3	> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
4
5	Review an analysis for accuracy, methodology, and potential biases before sharing with stakeholders. Generates a confidence assessment and improvement suggestions.
6
7	## Usage
8
9	```
10	/validate-data <analysis to review>
11	```
12
13	The analysis can be:
14	- A document or report in the conversation
15	- A file (markdown, notebook, spreadsheet)
16	- SQL queries and their results
17	- Charts and their underlying data
18	- A description of methodology and findings
19
20	## Workflow
21
22	### 1. Review Methodology and Assumptions
23
24	Examine:
25
26	- Question framing: Is the analysis answering the right question? Could the question be interpreted differently?
27	- Data selection: Are the right tables/datasets being used? Is the time range appropriate?
28	- Population definition: Is the analysis population correctly defined? Are there unintended exclusions?
29	- Metric definitions: Are metrics defined clearly and consistently? Do they match how stakeholders understand them?
30	- Baseline and comparison: Is the comparison fair? Are time periods, cohort sizes, and contexts comparable?
31
32	### 2. Run the Pre-Delivery QA Checklist
33
34	Work through the checklist below — data quality, calculation, reasonableness, and presentation checks.
35
36	### 3. Check for Common Analytical Pitfalls
37
38	Systematically review against the detailed pitfall catalog below (join explosion, survivorship bias, incomplete period comparison, denominator shifting, average of averages, timezone mismatches, selection bias).
39
40	### 4. Verify Calculations and Aggregations
41
42	Where possible, spot-check:
43
44	- Recalculate a few key numbers independently
45	- Verify that subtotals sum to totals
46	- Check that percentages sum to 100% (or close to it) where expected
47	- Confirm that YoY/MoM comparisons use the correct base periods
48	- Validate that filters are applied consistently across all metrics
49
50	Apply the result sanity-checking techniques below (magnitude checks, cross-validation, red-flag detection).
51
52	### 5. Assess Visualizations
53
54	If the analysis includes charts:
55
56	- Do axes start at appropriate values (zero for bar charts)?
57	- Are scales consistent across comparison charts?
58	- Do chart titles accurately describe what's shown?
59	- Could the visualization mislead a quick reader?
60	- Are there truncated axes, inconsistent intervals, or 3D effects that distort perception?
61
62	### 6. Evaluate Narrative and Conclusions
63
64	Review whether:
65
66	- Conclusions are supported by the data shown
67	- Alternative explanations are acknowledged
68	- Uncertainty is communicated appropriately
69	- Recommendations follow logically from findings
70	- The level of confidence matches the strength of evidence
71
72	### 7. Suggest Improvements
73
74	Provide specific, actionable suggestions:
75
76	- Additional analyses that would strengthen the conclusions
77	- Caveats or limitations that should be noted
78	- Better visualizations or framings for key points
79	- Missing context that stakeholders would want
80
81	### 8. Generate Confidence Assessment
82
83	Rate the analysis on a 3-level scale:
84
85	Ready to share -- Analysis is methodologically sound, calculations verified, caveats noted. Minor suggestions for improvement but nothing blocking.
86
87	Share with noted caveats -- Analysis is largely correct but has specific limitations or assumptions that must be communicated to stakeholders. List the required caveats.
88
89	Needs revision -- Found specific errors, methodological issues, or missing analyses that should be addressed before sharing. List the required changes with priority order.
90
91	## Output Format
92
93	```
94	## Validation Report
95
96	### Overall Assessment: [Ready to share \| Share with caveats \| Needs revision]
97
98	### Methodology Review
99	[Findings about approach, data selection, definitions]
100
101	### Issues Found
102	1. [Severity: High/Medium/Low] [Issue description and impact]
103	2. ...
104
105	### Calculation Spot-Checks
106	- [Metric]: [Verified / Discrepancy found]
107	- ...
108
109	### Visualization Review
110	[Any issues with charts or visual presentation]
111
112	### Suggested Improvements
113	1. [Improvement and why it matters]
114	2. ...
115
116	### Required Caveats for Stakeholders
117	- [Caveat that must be communicated]
118	- ...
119	```
120
121	---
122
123	## Pre-Delivery QA Checklist
124
125	Run through this checklist before sharing any analysis with stakeholders.
126
127	### Data Quality Checks
128
129	- [ ] Source verification: Confirmed which tables/data sources were used. Are they the right ones for this question?
130	- [ ] Freshness: Data is current enough for the analysis. Noted the "as of" date.
131	- [ ] Completeness: No unexpected

People who liked this also viewed

6 picks

Type

validate-data

2.5kinstalls2.7kforks

View on GitHub

How to install validate-data?

anthropics/knowledge-work-plugins/validate-data

$npx -y skills add anthropics/knowledge-work-plugins --skill validate-data

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /validate-data - Validate Analysis Before Sharing
2
3	> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
4
5	Review an analysis for accuracy, methodology, and potential biases before sharing with stakeholders. Generates a confidence assessment and improvement suggestions.
6
7	## Usage
8
9	```
10	/validate-data <analysis to review>
11	```
12
13	The analysis can be:
14	- A document or report in the conversation
15	- A file (markdown, notebook, spreadsheet)
16	- SQL queries and their results
17	- Charts and their underlying data
18	- A description of methodology and findings
19
20	## Workflow
21
22	### 1. Review Methodology and Assumptions
23
24	Examine:
25
26	- Question framing: Is the analysis answering the right question? Could the question be interpreted differently?
27	- Data selection: Are the right tables/datasets being used? Is the time range appropriate?
28	- Population definition: Is the analysis population correctly defined? Are there unintended exclusions?
29	- Metric definitions: Are metrics defined clearly and consistently? Do they match how stakeholders understand them?
30	- Baseline and comparison: Is the comparison fair? Are time periods, cohort sizes, and contexts comparable?
31
32	### 2. Run the Pre-Delivery QA Checklist
33
34	Work through the checklist below — data quality, calculation, reasonableness, and presentation checks.
35
36	### 3. Check for Common Analytical Pitfalls
37
38	Systematically review against the detailed pitfall catalog below (join explosion, survivorship bias, incomplete period comparison, denominator shifting, average of averages, timezone mismatches, selection bias).
39
40	### 4. Verify Calculations and Aggregations
41
42	Where possible, spot-check:
43
44	- Recalculate a few key numbers independently
45	- Verify that subtotals sum to totals
46	- Check that percentages sum to 100% (or close to it) where expected
47	- Confirm that YoY/MoM comparisons use the correct base periods
48	- Validate that filters are applied consistently across all metrics
49
50	Apply the result sanity-checking techniques below (magnitude checks, cross-validation, red-flag detection).
51
52	### 5. Assess Visualizations
53
54	If the analysis includes charts:
55
56	- Do axes start at appropriate values (zero for bar charts)?
57	- Are scales consistent across comparison charts?
58	- Do chart titles accurately describe what's shown?
59	- Could the visualization mislead a quick reader?
60	- Are there truncated axes, inconsistent intervals, or 3D effects that distort perception?
61
62	### 6. Evaluate Narrative and Conclusions
63
64	Review whether:
65
66	- Conclusions are supported by the data shown
67	- Alternative explanations are acknowledged
68	- Uncertainty is communicated appropriately
69	- Recommendations follow logically from findings
70	- The level of confidence matches the strength of evidence
71
72	### 7. Suggest Improvements
73
74	Provide specific, actionable suggestions:
75
76	- Additional analyses that would strengthen the conclusions
77	- Caveats or limitations that should be noted
78	- Better visualizations or framings for key points
79	- Missing context that stakeholders would want
80
81	### 8. Generate Confidence Assessment
82
83	Rate the analysis on a 3-level scale:
84
85	Ready to share -- Analysis is methodologically sound, calculations verified, caveats noted. Minor suggestions for improvement but nothing blocking.
86
87	Share with noted caveats -- Analysis is largely correct but has specific limitations or assumptions that must be communicated to stakeholders. List the required caveats.
88
89	Needs revision -- Found specific errors, methodological issues, or missing analyses that should be addressed before sharing. List the required changes with priority order.
90
91	## Output Format
92
93	```
94	## Validation Report
95
96	### Overall Assessment: [Ready to share \| Share with caveats \| Needs revision]
97
98	### Methodology Review
99	[Findings about approach, data selection, definitions]
100
101	### Issues Found
102	1. [Severity: High/Medium/Low] [Issue description and impact]
103	2. ...
104
105	### Calculation Spot-Checks
106	- [Metric]: [Verified / Discrepancy found]
107	- ...
108
109	### Visualization Review
110	[Any issues with charts or visual presentation]
111
112	### Suggested Improvements
113	1. [Improvement and why it matters]
114	2. ...
115
116	### Required Caveats for Stakeholders
117	- [Caveat that must be communicated]
118	- ...
119	```
120
121	---
122
123	## Pre-Delivery QA Checklist
124
125	Run through this checklist before sharing any analysis with stakeholders.
126
127	### Data Quality Checks
128
129	- [ ] Source verification: Confirmed which tables/data sources were used. Are they the right ones for this question?
130	- [ ] Freshness: Data is current enough for the analysis. Noted the "as of" date.
131	- [ ] Completeness: No unexpected

People who liked this also viewed

6 picks

Type