jy00295005/decision-grade-memory/dgm-citation-audit
Claude Code and agent skill by jy00295005/decision-grade-memory
- community
Checking that the SKILL.md file is still in the repository.
Use for citation-quality audits in this repository: identify claims needing citations, flag unsupported or weakly supported claims, keep only strong sources, and conservatively update references/library.bib with verified entries for paper drafts and review-analysis chapters.
Install
npx vskill@latest install jy00295005/decision-grade-memory/dgm-citation-auditSKILL.md
DGM Citation Audit
Use this skill when the task is to audit citation quality in a draft, review note, or manuscript section.
When to use
Trigger this skill when the user asks to:
- audit citations
- find unsupported claims
- identify weakly supported claims
- decide which sources are strong enough to keep
- update
references/library.bibconservatively
Typical repository inputs:
manuscript/references/library.bibreferences/notes/
Typical outputs:
- a citation audit note in
references/notes/ - conservative
.bibupdates
Core rules
- No invented references.
- No fake numeric placeholders.
- Prefer formal academic sources over product pages or generic web summaries.
- If source attribution is uncertain, mark it uncertain instead of guessing.
- Do not make the bibliography look fuller by adding unverified entries.
- Separate these categories clearly:
- claim needs citation
- claim is weakly supported
- source is strong enough to retain
- source needs replacement or verification
Workflow
- Read the target draft first.
- Mark claims in four buckets:
- clearly supported
- citation needed
- weakly supported
- should be softened or removed
- Cross-check cited author/year forms against actual verified records.
- Update
references/library.bibonly when metadata are verified. - Produce an audit note that tells the next writer exactly what to fix.
Preferred audit structure
- Claims that need citations
- Unsupported or weakly supported claims
- Sources strong enough to keep
- Places where more formal references are needed
- Bibliography changes made
- Uncertain areas that were intentionally left unresolved
Repository-specific guidance
- Default output path:
references/notes/<draft_name>_citation_audit.md- When a claim is conceptually useful but weakly supported, prefer softening the wording instead of forcing a citation.
- In this repo, review-analysis writing should preserve reviewer trust over rhetorical sharpness.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcodex/skills/dgm-citation-audit/SKILL.md
Popularity
- Repository stars
- 184
- Repository forks
- 18
- 7-day trend score
- 26
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jy00295005/decision-grade-memory/dgm-citation-audit)