cite-check
Skill0 starsChanged 6 days agoMITView on GitHub
Citation consistency gate for Quarto/Pandoc academic work (.qmd + .bib). Use for /check_cite, before a build or submission, or when the user asks to check citations / 引用格式 / 引用檢查 / 檢查引用. Runs ./fw check-citations (broken, unused, incomplete, duplicate keys; APA-zh split bib) instead of a hand-rolled grep, enforces [@key] format and p. / para. locators, and strips NotebookLM [loc] residue. Whether a source actually supports a claim is source-kit, not this.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Walsworth-Group/physkittheir own version, first seen Nov 8, 2026
- zedxter/utility-belttheir own version, first seen Nov 1, 2026
- williamhorschak-dev/wisconsin-legal-ai-skillstheir own version, first seen Oct 25, 2026
- Sprintlaw/legal-skillstheir own version, first seen Oct 17, 2026
- opelpleple/meta-skillstheir own version, first seen Oct 11, 2026
- reutavidan/zetesis-plugintheir own version, first seen Aug 6, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Walsworth-Group/physkit★ 7same name
- zedxter/utility-belt★ 4same name
- williamhorschak-dev/wisconsin-legal-ai-skills★ 2same name
- opelpleple/meta-skills★ 0same name
- reutavidan/zetesis-plugin★ 0same name
- Sprintlaw/legal-skills★ 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- count-zhSkill
- deck-imageSkill
- deck-planSkill
- deck-runtimeSkill
- deck-svgSkill
- diagramSkill
- fix-termsSkill
- flow-checkSkill
- gpt-reviewSkill
- house-styleSkill
- safe-editSkill
- source-kitSkill
- topic-scoutSkill
- yt2subSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Use the Quarto/Pandoc standard: [@citation_key].
- Distinctive: line 33
When a citation supports a specific point or datum, mark the position precisely:
- Very specific: line 59
Run this last, as a consistency pass — the substantive review (cross-reading each claim against <unit>/refs/<key>.md) is source-kit § …
“Common” is measured: kept by at least 6 in 10 of the 6 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
cite-check — citation hygiene gate
The mechanical citation gate for .qmd manuscripts. It checks that citations are
well-formed and consistent — it does not check that a source backs its
claim. That semantic check is source-kit § Source review; this skill is the
form check, and house-style reference/content-integrity.md rule 3 ("citations
stay attached to their claims") is the standard it enforces.
Extend ./fw check-citations (below) rather than hand-rolling a
grep/awk/python script to diff [@key]s against the .bib — it already does it,
including the APA-zh split-bib case, and exits non-zero to fail the build.
Format rules
- Use the Quarto/Pandoc standard:
[@citation_key]. - Forbidden: NotebookLM-generated
[loc],Location, orSource Xlabels. Strip any that survived a paste from NotebookLM.
Locators (定位標示)
When a citation supports a specific point or datum, mark the position precisely:
- PDF / book source →
p. <page>(e.g.[@smith_2024, p. 15]). - Web / HTML source →
para. <paragraph>(e.g.[@cnn_report, para. 3]).
Run the consistency check
./fw check-citations <unit> # exits non-zero if broken or incompleteIt checks all <unit>/**/*.qmd against both tiers — <unit>/references.bib
and library/references.bib — and reports four things (APA-zh units use the
same single bib; entries carry langid and the build groups 中文／西文):
| Class | Meaning | Fails build? |
| Broken | cited [@key] with no matching bib entry | yes |
| Unused | bib entry never cited | no (warning) |
| Incomplete | bib entry missing author / title / year | yes |
| Duplicate | same key in two places in the course repo — two units, or a unit and library/ — so one source has two diverging audit histories; fix with ./fw refs promote <key> | yes |
What it does NOT do
It confirms citation keys resolve to bib entries; it does not confirm the
source actually supports the claim, nor that locators point at the right page.
Run this last, as a consistency pass — the substantive review (cross-reading
each claim against <unit>/refs/<key>.md) is source-kit § Source review. A
green check-citations.py over unverified sources is a false sense of safety.
Backs the /check_cite macro.
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.