claim-evidence-matrix

Name: claim-evidence-matrix
Author: WILLOSCAR

53installs39forks

How to install claim-evidence-matrix?

willoscar/research-units-pipeline-skills/claim-evidence-matrix

$npx -y skills add WILLOSCAR/research-units-pipeline-skills --skill claim-evidence-matrix

Installs into the current project.

Summary

Build a section-by-section claim–evidence matrix (outline/claim_evidence_matrix.md) from the outline and paper notes. Trigger: claim–evidence matrix, evidence mapping, 证据矩阵, 主张-证据对齐. Use when: 写 prose 之前需要把每个小节的可检验主张与证据来源显式化（outline + paper notes 已就绪）。 Skip if: 缺少 `

Files · 1

View on GitHub

SKILL.md

1	# Claim–Evidence Matrix
2
3	Make the survey’s claims explicit and auditable before writing prose.
4
5	This should stay bullets-only (NO PROSE). The goal is to make later writing easy and to prevent “template prose” from sneaking in.
6
7	## Inputs
8
9	- `outline/outline.yml`
10	- `papers/paper_notes.jsonl`
11	- Optional: `outline/mapping.tsv`
12
13	## Output
14
15	- `outline/claim_evidence_matrix.md`
16
17	## Workflow (heuristic)
18	Uses: `outline/outline.yml`, `outline/mapping.tsv`.
19
20
21	1. For each subsection, write 1–3 claims that are:
22	- specific (mechanism / assumption / empirical finding)
23	- falsifiable (“X reduces tool errors under Y evaluation”, not “X is important”)
24	2. For each claim, list ≥2 evidence sources:
25	- prefer different styles of evidence (method paper + eval/benchmark paper, or two competing approaches)
26	3. Keep it tight: claim → evidence → (optional) caveat/limitations.
27	4. If evidence is weak or only abstract-level, say so explicitly (don’t overclaim).
28	5. If `bibkey` exists in `papers/paper_notes.jsonl`, include `[@BibKey]` next to evidence items to make later prose/LaTeX conversion smoother.
29
30	## Quality checklist
31
32	- [ ] Every subsection has ≥1 claim.
33	- [ ] Each claim lists ≥2 evidence sources (or an explicit exception).
34	- [ ] Claims are not copy-pasted templates (avoid “围绕…总结…” boilerplate).
35
36	## Helper script (optional)
37
38	### Quick Start
39
40	- `uv run python .codex/skills/claim-evidence-matrix/scripts/run.py --help`
41	- `uv run python .codex/skills/claim-evidence-matrix/scripts/run.py --workspace <workspace>`
42
43	### All Options
44
45	- See `--help` (this helper is intentionally minimal)
46
47	### Examples
48
49	- Generate a first-pass matrix, then refine manually:
50	- Run the helper once, then refine `outline/claim_evidence_matrix.md` by tightening claims and adding caveats when evidence is abstract-level.
51
52	### Notes
53
54	- The helper generates a baseline matrix (claims + evidence) and never overwrites non-placeholder work; in `pipeline.py --strict` it will be blocked only if placeholder markers remain.
55
56	## Troubleshooting
57
58	### Issue: claims are generic or read like outline boilerplate
59
60	Fix:
61	- Tighten each claim to a falsifiable statement and add an explicit caveat if evidence is abstract-only.
62
63	### Issue: you cannot add `[@BibKey]` because keys are missing
64
65	Fix:
66	- Run `citation-verifier` to generate `citations/ref.bib`, then use the produced keys in the matrix.

People who liked this also viewed

6 picks

Type

claim-evidence-matrix

53installs39forks

View on GitHub

How to install claim-evidence-matrix?

willoscar/research-units-pipeline-skills/claim-evidence-matrix

$npx -y skills add WILLOSCAR/research-units-pipeline-skills --skill claim-evidence-matrix

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Claim–Evidence Matrix
2
3	Make the survey’s claims explicit and auditable before writing prose.
4
5	This should stay bullets-only (NO PROSE). The goal is to make later writing easy and to prevent “template prose” from sneaking in.
6
7	## Inputs
8
9	- `outline/outline.yml`
10	- `papers/paper_notes.jsonl`
11	- Optional: `outline/mapping.tsv`
12
13	## Output
14
15	- `outline/claim_evidence_matrix.md`
16
17	## Workflow (heuristic)
18	Uses: `outline/outline.yml`, `outline/mapping.tsv`.
19
20
21	1. For each subsection, write 1–3 claims that are:
22	- specific (mechanism / assumption / empirical finding)
23	- falsifiable (“X reduces tool errors under Y evaluation”, not “X is important”)
24	2. For each claim, list ≥2 evidence sources:
25	- prefer different styles of evidence (method paper + eval/benchmark paper, or two competing approaches)
26	3. Keep it tight: claim → evidence → (optional) caveat/limitations.
27	4. If evidence is weak or only abstract-level, say so explicitly (don’t overclaim).
28	5. If `bibkey` exists in `papers/paper_notes.jsonl`, include `[@BibKey]` next to evidence items to make later prose/LaTeX conversion smoother.
29
30	## Quality checklist
31
32	- [ ] Every subsection has ≥1 claim.
33	- [ ] Each claim lists ≥2 evidence sources (or an explicit exception).
34	- [ ] Claims are not copy-pasted templates (avoid “围绕…总结…” boilerplate).
35
36	## Helper script (optional)
37
38	### Quick Start
39
40	- `uv run python .codex/skills/claim-evidence-matrix/scripts/run.py --help`
41	- `uv run python .codex/skills/claim-evidence-matrix/scripts/run.py --workspace <workspace>`
42
43	### All Options
44
45	- See `--help` (this helper is intentionally minimal)
46
47	### Examples
48
49	- Generate a first-pass matrix, then refine manually:
50	- Run the helper once, then refine `outline/claim_evidence_matrix.md` by tightening claims and adding caveats when evidence is abstract-level.
51
52	### Notes
53
54	- The helper generates a baseline matrix (claims + evidence) and never overwrites non-placeholder work; in `pipeline.py --strict` it will be blocked only if placeholder markers remain.
55
56	## Troubleshooting
57
58	### Issue: claims are generic or read like outline boilerplate
59
60	Fix:
61	- Tighten each claim to a falsifiable statement and add an explicit caveat if evidence is abstract-only.
62
63	### Issue: you cannot add `[@BibKey]` because keys are missing
64
65	Fix:
66	- Run `citation-verifier` to generate `citations/ref.bib`, then use the produced keys in the matrix.

People who liked this also viewed

6 picks

Type