stats

Name: stats
Author: richard-kim-79

44stars10forks

How to install stats?

richard-kim-79/archora-skills/stats

$npx -y skills add richard-kim-79/archora-skills --skill stats

Installs into the current project.

Summary

Detects statistical errors, logical fallacies, and methodological issues in research content. Checks for p-hacking, correlation/causation confusion, underpowered samples, multiple comparisons problems, overgeneralization, and other common fallacies. Use when the user asks to vali

Files · 1

View on GitHub

SKILL.md

1	# Statistical Validator
2
3	Detect statistical errors and methodological fallacies in research content.
4
5	## Fallacy Types Detected
6
7	\| Type \| Description \|
8	\|------\|-------------\|
9	\| `P_HACKING` \| Selective reporting, post-hoc hypothesis changes, stopped when p<0.05 \|
10	\| `CORRELATION_CAUSATION` \| Causal claims from correlational data \|
11	\| `SMALL_SAMPLE` \| Sample size insufficient for claimed effect size \|
12	\| `MULTIPLE_COMPARISONS` \| Multiple tests without Bonferroni/FDR correction \|
13	\| `OVERGENERALIZATION` \| Results from specific sample applied to broader population \|
14	\| `CIRCULAR_REASONING` \| Conclusion assumes what it claims to prove \|
15	\| `CHERRY_PICKING` \| Selective evidence presentation \|
16	\| `EFFECT_SIZE_MISSING` \| Statistical significance without practical effect size \|
17	\| `CONFOUND` \| Alternative explanations not controlled for \|
18
19	## Severity Levels
20
21	- HIGH — fatal flaw; invalidates the finding
22	- MEDIUM — significant concern; finding is weakened
23	- LOW — minor issue; addressable in discussion
24
25	## Output Format
26
27	### When issues are found:
28
29	```markdown
30	# 📐 Statistical Validation
31
32	> Found 3 issue(s) requiring attention.
33
34	## Issues
35
36	### 🔴 HIGH — P_HACKING
37
38	Post: [reference to source]
39	Claim: "[exact statistical claim]"
40	Issue: [specific explanation of the problem]
41	Suggestion: [concrete fix]
42
43	---
44
45	### 🟡 MEDIUM — CORRELATION_CAUSATION
46	...
47
48	## Summary
49	[Overall assessment + priority order for fixes]
50	```
51
52	### When no issues are found:
53
54	```markdown
55	# 📐 Statistical Validation
56
57	> ✅ No statistical issues detected.
58
59	## Assessment
60	[Explanation: e.g., "This content is theoretical/conceptual and contains no quantitative claims to validate."]
61
62	## Proactive Checklist
63	When empirical data is added, watch for:
64	- [ ] [Domain-specific statistical concern 1]
65	- [ ] [Domain-specific statistical concern 2]
66	```
67
68	## When content has no statistics
69
70	If the content is purely theoretical or conceptual, note this explicitly and provide a domain-appropriate proactive checklist. Do NOT generate phantom issues.

People who liked this also viewed

6 picks

Type

stats

44stars10forks

View on GitHub

How to install stats?

richard-kim-79/archora-skills/stats

$npx -y skills add richard-kim-79/archora-skills --skill stats

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Statistical Validator
2
3	Detect statistical errors and methodological fallacies in research content.
4
5	## Fallacy Types Detected
6
7	\| Type \| Description \|
8	\|------\|-------------\|
9	\| `P_HACKING` \| Selective reporting, post-hoc hypothesis changes, stopped when p<0.05 \|
10	\| `CORRELATION_CAUSATION` \| Causal claims from correlational data \|
11	\| `SMALL_SAMPLE` \| Sample size insufficient for claimed effect size \|
12	\| `MULTIPLE_COMPARISONS` \| Multiple tests without Bonferroni/FDR correction \|
13	\| `OVERGENERALIZATION` \| Results from specific sample applied to broader population \|
14	\| `CIRCULAR_REASONING` \| Conclusion assumes what it claims to prove \|
15	\| `CHERRY_PICKING` \| Selective evidence presentation \|
16	\| `EFFECT_SIZE_MISSING` \| Statistical significance without practical effect size \|
17	\| `CONFOUND` \| Alternative explanations not controlled for \|
18
19	## Severity Levels
20
21	- HIGH — fatal flaw; invalidates the finding
22	- MEDIUM — significant concern; finding is weakened
23	- LOW — minor issue; addressable in discussion
24
25	## Output Format
26
27	### When issues are found:
28
29	```markdown
30	# 📐 Statistical Validation
31
32	> Found 3 issue(s) requiring attention.
33
34	## Issues
35
36	### 🔴 HIGH — P_HACKING
37
38	Post: [reference to source]
39	Claim: "[exact statistical claim]"
40	Issue: [specific explanation of the problem]
41	Suggestion: [concrete fix]
42
43	---
44
45	### 🟡 MEDIUM — CORRELATION_CAUSATION
46	...
47
48	## Summary
49	[Overall assessment + priority order for fixes]
50	```
51
52	### When no issues are found:
53
54	```markdown
55	# 📐 Statistical Validation
56
57	> ✅ No statistical issues detected.
58
59	## Assessment
60	[Explanation: e.g., "This content is theoretical/conceptual and contains no quantitative claims to validate."]
61
62	## Proactive Checklist
63	When empirical data is added, watch for:
64	- [ ] [Domain-specific statistical concern 1]
65	- [ ] [Domain-specific statistical concern 2]
66	```
67
68	## When content has no statistics
69
70	If the content is purely theoretical or conceptual, note this explicitly and provide a domain-appropriate proactive checklist. Do NOT generate phantom issues.

People who liked this also viewed

6 picks

Type