SkillsAdd

smithery/willoscar

citation-diversifier

PRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.

Installation

$ npx skills add smithery/willoscar --skill citation-diversifier
View on skills.sh ↗ Website ↗

Also in this package

Other skills from smithery/willoscar · top by installs.

npx skills add smithery/willoscar
writer-selfloop 0 writer-context-pack 0 workspace-init 0 unit-planner 0 unit-executor 0 transition-weaver 0 terminology-normalizer 0 taxonomy-builder 0 table-schema 0 table-filler 0

Browse all from smithery/willoscar

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents codex

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 4,931 B
  • docs SUMMARY.md 893 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

Citation Diversifier (budget-as-constraints) [NO NEW FACTS]

Triggers & routing

  • Trigger: cite boost, citation budget, unique citations too low, add more citations, improve reference density, 引用太少, 增加引用, 引用密度.

Purpose: fix a common survey failure mode:

  • the draft reads under-cited (or reuses the same few citations everywhere)
  • the pipeline fails the global unique-citation gate

This skill does not change prose by itself. It produces a constraint sheet: output/CITATIONBUDGETREPORT.md.

Inputs

  • output/DRAFT.md
  • outline/outline.yml (H3 ids/titles; used to allocate budgets per subsection)
  • outline/writercontextpacks.jsonl (source of allowedbibkeys{selected,mapped,chapter,global} per H3)
  • citations/ref.bib

Output

  • output/CITATIONBUDGETREPORT.md

Non-negotiables (NO NEW FACTS)

  • Only propose citation keys that exist in citations/ref.bib.
  • Only propose keys that are in-scope for the target H3 (prefer subsection-first scope; use chapter/global only when truly cross-cutting).
  • Do not propose “padding citations” that would require adding new claims or new numbers.

What a good budget report looks like (contract)

The report should feel like a constraint sheet, not a random list:

  • It states the blocking policy target and the gap-to-target (how many unique keys are missing; policy default is recommended).
  • For each H3, it proposes a scope-safe budget sized to actually close the gap:

- small gaps: 3-6 keys / H3 is often enough - course_paper: cap suggestions at 3-6 keys / H3 and target the profile's 24/32 global budget - A150++ gaps: plan for ~6-12 keys / H3 (and avoid duplicates across H3 budgets)

  • It gives placement guidance (where in the subsection those keys can be embedded without adding new facts).

Canonical (parseable) lines required (downstream validators depend on these):

  • The target is derived from queries.md:citation_target (recommended by default for A150++).
  • - Global target (policy; blocking): >= <N> ...
  • - Gap: <K> (gap-to-target; if 0, injection can be a no-op PASS)

Optional (always reported; may be blocking depending on citation_target):

  • - Global recommended target: >= <N> ...
  • - Gap to recommended: <K>

Recommended prioritization (scope-safe):

  • allowedbibkeysselected → allowedbibkeysmapped → allowedbibkeyschapter
  • Use allowedbibkeysglobal only for:

- benchmarks/protocol papers - widely-used datasets/suites - cross-cutting surveys/method papers referenced across chapters

How this connects to writing (LLM-first)

After you generate the budget report:

  • Apply it using citation-injector (LLM edits to output/DRAFT.md, NO NEW FACTS).
  • Then run draft-polisher to remove any “budget dump voice” while keeping citation keys unchanged.

Important: citation-injector is LLM-first. Its script is validation-only.

Workflow

  1. Diagnose the global situation
  • Read output/DRAFT.md and estimate the “unique-key gap” (or use pipeline-auditor’s FAIL reason).
  1. Allocate budgets per H3 (scope-first)
  • Use outline/outline.yml to enumerate H3s in paper order.
  • For each H3, read its allowed key sets from outline/writercontextpacks.jsonl.
  • Pick a small set of unused keys that strengthen positioning without requiring new claims.
  1. Write output/CITATIONBUDGETREPORT.md

Required structure:

  • - Status: PASS|FAIL
  • - Global target (policy; blocking): >= <N> ...
  • - Gap: <K>
  • ## Summary (gap + strategy)
  • ## Per-subsection budgets (H3 id/title → suggested keys → placement hint)

Script (optional; deterministic report generator)

If you want a deterministic first-pass budget report, run the helper script. Treat it as a baseline and refine the plan as needed.

Quick Start

  • uv run python .codex/skills/citation-diversifier/scripts/run.py --help
  • uv run python .codex/skills/citation-diversifier/scripts/run.py --workspace <workspace>

All Options

  • --workspace <dir>
  • --unit-id <U###> (optional)
  • --inputs <semicolon-separated> (rare override; prefer defaults)
  • --outputs <semicolon-separated> (rare override; default writes output/CITATIONBUDGETREPORT.md)
  • --checkpoint <C#> (optional)

Examples

  • Default IO:

- uv run python .codex/skills/citation-diversifier/scripts/run.py --workspace <workspace>

Done criteria

  • output/CITATIONBUDGETREPORT.md exists and has actionable, in-scope budgets.
  • After applying the plan via citation-injector, pipeline-auditor no longer FAILs on global unique citations.