evidence-review
Skill141 starsChanged 5 months agoMITView on GitHub
Assess and promote corpus slices toward citation readiness. Use when deciding whether a piece of evidence can be cited, upgrading machine-translated layers to reviewed translations, building evidence matrices for writing, or prioritizing which sources to review first.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- itsmostafa/agent-skillstheir own version, first seen Nov 8, 2026
- grcmana/grc-ostheir own version, first seen Nov 8, 2026
- grcmana/grcskillstheir own version, first seen Nov 8, 2026
- sainteye/clawdlinetheir own version, first seen Nov 1, 2026
- 01jiyuge/signaldesktheir own version, first seen Nov 1, 2026
- Zack-Grogan/agentos-foundationtheir own version, first seen Sep 8, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- itsmostafa/agent-skills★ 4same name
- MKTerXiaoV/pharma-review-skills★ 4same name
- xiejianjun000/FlowWiki★ 4same name
- grcmana/grc-os★ 2same name
- grcmana/grcskills★ 2same name
- sainteye/clawdline★ 2same name
- 01jiyuge/signaldesk★ 0same name
- Zack-Grogan/agentos-foundation★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- corpus-buildingSkill
- literature-discoverySkill
- research-writingSkill
- source-intakeSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 7 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Only level 3 slices should appear as direct citations in writing.
- Distinctive: line 31
Don't review everything. Identify which slices are thesis-critical first:
- Distinctive: line 43
Verify that the source text (original excerpt or OCR text) accurately represents the page.
- Distinctive: line 47
If this slice is suitable for direct quotation or citation:
- Distinctive: line 65
Before each writing session, verify:
- Very specific: line 66
Every slice you plan to cite has at least verification_status: checked
- Very specific: line 67
Every slice you plan to quote directly has quote_ready: true
- Distinctive: line 68
Every citekey in your evidence matrix resolves in your bibliography
- Very specific: line 72
Do not promote a slice to quote_ready based on quality scores alone.
- Very specific: line 73
Do not cite from machine_draft or agent_draft translation layers directly.
- Distinctive: line 76
When you first use a slice in writing, add it to the evidence matrix immediately.
- Very specific: line 81
Read references/citation-criteria.md for the full checklist of what each ladder level requires for text and image slices.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Evidence Review
The core problem
Most corpus slices are created by automated pipelines: OCR, machine translation, auto-generated descriptions. They are useful for browsing, but not safe to cite. The gap between "we have 10,000 slices" and "we can write the paper" is evidence review — the deliberate process of deciding which slices are trustworthy enough to quote and cite.
Without a clear ladder between "raw" and "citation-ready," researchers either over-trust machine output or spend time reviewing everything equally. Neither is efficient.
The citation readiness ladder
| Level | Status | What it means |
| 0 | draft | Auto-generated, not yet looked at by a human |
| 1 | checked | Source text verified against the original document |
| 2 | reviewed | Working translation confirmed accurate; can be paraphrased safely |
| 3 | quote_ready | Can be quoted or cited directly; citekey and page locator confirmed |
Only level 3 slices should appear as direct citations in writing. Level 2 is sufficient for paraphrase and synthesis.
The key insight: levels 0 and 1 are about accuracy of the source text. Levels 2 and 3 are about the translation/working layer. They are separate judgments.
Workflow
1. Prioritize what to review
Don't review everything. Identify which slices are thesis-critical first:
- Slices already referenced in your writing or notes
- Slices from your highest-value sources
- Slices that answer your core research questions directly
For each priority cluster, look at quality scores from corpus building (P1 pages need review before any other use; P2 should be sampled).
2. Per-slice review procedure
For each slice you're reviewing:
- Open the original source page alongside the slice card.
- Verify that the source text (original excerpt or OCR text) accurately represents the page. Correct OCR errors if found.
- Set
verification_status: checkedwhen source text is confirmed. - Review the working translation: does it accurately convey the source meaning? Correct or rewrite as needed.
- Set
translation_status: reviewedwhen the working layer is trusted. - If this slice is suitable for direct quotation or citation:
- Confirm the citekey exists in your bibliography
- Confirm the page locator is correct
- Set
quote_ready: true
3. Maintain an evidence matrix
For each chapter or section you're writing, keep a simple matrix:
| Slice ID | Chapter | Section | Role | Status | Notes |
| SLC-0001-T003 | Ch2 | 2.1 | supports claim about X | reviewed | paraphrase only |
| SLC-0007-T012 | Ch3 | 3.2 | direct quotation | quote_ready | cite p.47 |
This makes the link between your argument and your evidence explicit and checkable.
4. Run the integrity check before writing
Before each writing session, verify:
- Every slice you plan to cite has at least
verification_status: checked - Every slice you plan to quote directly has
quote_ready: true - Every citekey in your evidence matrix resolves in your bibliography
Rules
- Do not promote a slice to
quote_readybased on quality scores alone. Human review of both source text and translation is required. - Do not cite from
machine_draftoragent_drafttranslation layers directly. These are working materials, not citation materials. - Separate source text accuracy from translation accuracy — they are different judgments, made at different stages.
- A slice at
reviewedlevel is safe to paraphrase. A slice atquote_readylevel is safe to quote. - When you first use a slice in writing, add it to the evidence matrix immediately.
- OCR-assisted image descriptions (
ocr_assisted_draft) are not citation-ready visual evidence.
References
- Read
references/citation-criteria.mdfor the full checklist of what each ladder level requires for text and image slices.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

