citation-auditor
Skill1 starsChanged 7 months agoApache-2.0View on GitHub
Audit a markdown file by chunking it, extracting claims with structured output, routing each claim to verifier skills, aggregating verdicts, and rendering annotated markdown.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jurgendn/agent-skillstheir own version, first seen Sep 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jurgendn/agent-skills★ 15same 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 repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- citation-checkerSkill
- cover-memo-writerSkill
- cross-document-checkerSkill
- document-parserSkill
- formatting-reviewerSkill
- ingestSkill
- known-issues-managerSkill
- library-managerSkill
- quality-gateSkill
- redline-generatorSkill
- scoring-engineSkill
- structure-checkerSkill
- substance-reviewerSkill
- writing-quality-reviewerSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 7 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Do not extract speculation, forecasts, rumors, advocacy, or soft prediction language such as:
- Distinctive: line 36
Keep claim offsets chunk-relative.
- Very specific: line 38
If suggested_verifier is set and exactly matches a loaded verifier skill name, use it.
- Very specific: line 40
If nothing matches, fall back to general-web.
- Very specific: line 76
Write that JSON to a temp file and run: python -m citation_auditor aggregate <tmpfile>
- Distinctive: line 78
Write the aggregate output to a temp file and run:
- Very specific: line 80
Do not use render --mode=append for WF1 DOCX review output.
- Distinctive: line 82
If claim extraction validation fails, retry once with a repair prompt.
- Distinctive: line 83
If a verifier subagent returns invalid JSON, drop that candidate instead of inventing a verdict.
- Distinctive: line 84
If a line was skipped because it is a forecast, opinion, rumor, or unattributed speculation, treat that as expected behavior rather than an …
- Distinctive: line 85
If the user asks why a forecast or opinion line was not audited, explain that this plugin audits verifiable factual claims and citations, …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Audit the markdown file at $0.
Invocation Contexts
This skill has two roles in this repo:
- Standalone
/audit(default): user-triggered via/audit <file.md>on an existing markdown file. Uses inline mode — per-claim badges injected into the body plus a per-claim audit report at the end. Does not altercheckpoint.json,verification-audit.json, or any WF1 artifact. - WF1 native verifier backend: Step 3 may reuse the verifier pool under
.claude/skills/verifiers/, but it must not use this skill's markdown renderer as a DOCX review output. Native WF1 results must go throughcitation-checker/scripts/adapt-citation-auditor.pyandmerge-verification-audits.pyso the final artifact remainsworking/verification-audit.json.
There is no automatic Step 10 in this repo. WF1 remains an 8-step review pipeline.
Procedure
- Confirm
$0exists and is a markdown file. If it does not, stop and ask for a valid path. - Run:
python -m citation_auditor chunk "$0" --max-tokens 3000 - Parse stdout as JSON with the schema
{ "chunks": [...] }. - For each chunk, extract only factual, citation-bearing claims using structured output with this schema:
text: stringsentence_span: { start: integer, end: integer }claim_type: factual | citation | quantitative | temporal | othersuggested_verifier: string | null
- Do not extract speculation, forecasts, rumors, advocacy, or soft prediction language such as:
전망이다예상된다업계 관계자에 따르면가능성이 있다Unless the sentence also contains a concrete verifiable factual assertion that stands on its own.
- Keep claim offsets chunk-relative. Do not convert them to document offsets yourself.
- Route each claim to verifier skills:
- If
suggested_verifieris set and exactly matches a loaded verifier skill name, use it. - Otherwise test the claim text against each verifier skill frontmatter
patternsusing case-insensitive regex matching and use every match. - If nothing matches, fall back to
general-web.
- If
- For each
(claim, verifier)pair, use the Task tool to dispatch a subagent that loads that verifier skill and receives the claim JSON. - Require each verifier subagent to return only this JSON:
{ "label": "...", "rationale": "...", "supporting_urls": ["..."], "authority": 0.0 } supporting_urlsmay contain either clickable source URLs or plain-language source references when no stable URL exists. Preserve them verbatim and do not invent clickable URLs for non-linkable sources such as precedent search-result IDs.Build aggregate input JSON locally. The exact top-level shape is
{ "verdicts": [ <bundle>, ... ] }where each<bundle>covers one(chunk, claim)pair and holds all verifier candidates for that claim. Do not invent other top-level keys.Exact schema (copy this structure):
{ "verdicts": [ { "chunk": { "index": 0, "text": "<full chunk text>", "segments": [ { "chunk_start": 0, "chunk_end": 44, "document_start": 0, "document_end": 44 } ] }, "claim": { "text": "<claim sentence>", "sentence_span": { "start": 64, "end": 268 }, "claim_type": "citation", "suggested_verifier": "us-law" }, "candidates": [ { "claim": { "text": "<same claim as above>", "sentence_span": { "start": 64, "end": 268 }, "claim_type": "citation", "suggested_verifier": "us-law" }, "verifier_name": "us-law", "authority": 0.9, "label": "contradicted", "rationale": "<Korean rationale from verifier>", "evidence": [ { "url": "https://..." } ] } ] } ] }Rules:
- One bundle per
(chunk, claim)pair. If the same claim has two verifiers, put both candidates inside the same bundle'scandidatesarray — do NOT create a second bundle for the same claim. - The top-level
claiminside each bundle is the canonical claim; each candidate'sclaimmust match it verbatim. evidenceitems require a non-emptyurlstring. If the verifier returnedsupporting_urls: [], emit"evidence": []— do not emit[{"url": ""}].labelmust be one ofverified/contradicted/unknown.authoritymust match the verifier skill's declared authority value.
- One bundle per
- Write that JSON to a temp file and run:
python -m citation_auditor aggregate <tmpfile> - Write the aggregate output to a temp file and run:
- Standalone
/audit:python -m citation_auditor render "$0" <aggfile>(inline mode is default). - Do not use
render --mode=appendfor WF1 DOCX review output.
- Standalone
- Return only the final annotated markdown unless the user explicitly asked for intermediate JSON.
- If claim extraction validation fails, retry once with a repair prompt. If it still fails, skip that chunk and note it briefly.
- If a verifier subagent returns invalid JSON, drop that candidate instead of inventing a verdict.
- If a line was skipped because it is a forecast, opinion, rumor, or unattributed speculation, treat that as expected behavior rather than an extraction failure.
- If the user asks why a forecast or opinion line was not audited, explain that this plugin audits verifiable factual claims and citations, not predictions or commentary.
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.

