Draft Polisher

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass, no license.

.claude/skills

return hashlib.sha1((text or "").encode("utf-8", errors="ignore")).hexdigest()

Audit 0.4.1 · source sha 81994516a430 · 19 Oct 2026Report an issue or request a re-scan

• PublisherWILLOSCAR GitHub userOwner of the repository this skill is read from
• Source folderWILLOSCAR/research-units-pipeline-skills/.codex/skills/draft-polisherThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdict81994516a430A new audit runs when the source changes
• Repository statusNot archivedLast push 14 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring.

---
name: draft-polisher
description: "Audit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce citation anchoring."
---

# Draft Polisher (Audit-style editing)

## Triggers & routing

- **Trigger**: polish draft, de-template, coherence pass, remove boilerplate, 润色, 去套话, 去重复, 统一术语.
- **Use when**: a first-pass draft exists but reads like scaffolding (repetition/ellipsis/template phrases) or needs a coherence pass before global review/LaTeX.


Goal: turn a first-pass draft into readable survey prose **without breaking the evidence contract**.

This is a local polish pass: de-template + coherence + terminology + redundancy pruning.

Note: if the main issue is structural redundancy from section accumulation, push the change upstream to `sections/` and use `paragraph-curator` before merge. `draft-polisher` should not be the primary place where you decide which paragraphs to keep.



## Role cards (use explicitly)

### Style Harmonizer (editor)

Mission: remove generator voice and make prose read like one author wrote it.

Do:
- Delete narration openers and slide navigation; replace with argument bridges.
- Vary rhythm; remove repeated template stems.
- Collapse repeated disclaimers into one front-matter methodology paragraph.

Avoid:
- Adding or removing citation keys.
- Moving citations across subsections.

### Evidence Contract Guard (skeptic)

Mission: prevent polishing from inflating claims beyond evidence.

Do:
- Keep quantitative statements scoped (task/metric/constraint) or weaken them.
- Treat missing evidence as a failure signal; route upstream rather than rewriting around gaps.

Avoid:
- Overconfident language when evidence is abstract-only.


## Role prompt: Style Harmonizer (editor expert)

```text
You are the style and coherence editor for a technical survey.

Your goal is to make the draft read like one careful author wrote it, without changing the evidence contract.

Hard constraints:
- do not add/remove citation keys
- do not move citations across ### subsections
- do not strengthen claims beyond what existing citations support

High-leverage edits:
- delete generator voice (This subsection..., Next we move..., We now turn...)
- replace navigation with argument bridges (content-bearing handoffs)
- collapse repeated disclaimers into one methodology paragraph in front matter
- keep quantitative statements well-scoped (task/metric/constraint in the same sentence)

Working style:
- rewrite sentences so they carry content, not process
- vary rhythm, but avoid “template stems” repeating across H3s
```

## Inputs

- `output/DRAFT.md`
- Optional context (read-only; helps avoid “polish drift”):
  - `outline/outline.yml`
  - `outline/subsection_briefs.jsonl`
  - `outline/evidence_drafts.jsonl`
  - `citations/ref.bib`

## Outputs

- `output/DRAFT.md` (in-place refinement)
- `output/citation_anchors.prepolish.jsonl` (baseline, generated on first run by the script)

## Non-negotiables (hard rules)

1) **Citation keys are immutable**
- Do not add new `[@BibKey]` keys.
- Do not delete citation markers.
- If `citations/ref.bib` exists, do not introduce any key that is not defined there.

2) **Citation anchoring is immutable**
- Do not move citations across `###` subsections.
- If you must restructure across subsections, stop and push the change upstream (outline/briefs/evidence), then regenerate.

3) **No evidence inflation**
- If a sentence sounds stronger than the evidence level (abstract-only), rewrite it into a qualified statement.
- When in doubt, check the subsection’s evidence pack in `outline/evidence_drafts.jsonl` and keep claims aligned to snippets.

4) **Citation shape normalization**
- Merge adjacent citation blocks in the same sentence (avoid `[@a] [@b]`).
- Deduplicate keys inside one block (avoid `[@a; @a]`).
- Avoid tail-only citation dumps: keep some citations in the claim sentence itself (mid-sentence), not only paragraph end.

5) **Quantitative claim hygiene**
- If you keep a number, ensure the sentence also states (without guessing): task type + metric definition + relevant constraint (budget/cost/tool access), and the citation is embedded in that sentence.
- Avoid ambiguous model naming (e.g., “GPT-5”) unless the cited paper uses that exact label; otherwise use the paper’s naming or a neutral description.

6) **No pipeline voice**
- Remove scaffolding phrases like:
  - “We use the following working claim ...”
  - “The main axes we track are ...”
  - “abstracts are treated as verification targets ...”
  - “Method note (evidence policy): ...” (avoid labels; rewrite as plain survey methodology)
  - “this run is ...” (rewrite as survey methodology: “This survey is ...”)
  - “Scope and definitions / Design space / Evaluation practice ...”
  - “Next, we move from ...”
  - “We now turn to ...”
  - “From <X> to <Y>, ...” (title narration; rewrite as an argument bridge)
  - “In the next section/subsection ...”
  - “Therefore/As a result, survey synthesis/comparisons should ...” (rewrite as literature-facing observation)
- Also remove generator-like thesis openers that read like outline narration:
  - “This subsection surveys ...”
  - “This subsection argues ...”

## Three passes (recommended)

### Pass 1 — Subsection polish (structure + de-template)

Best-of-2 micro-polish (recommended):
- For any sentence/paragraph you touch, draft 2 candidate rewrites, then keep the better one.
- Choose with a simple rubric: move clarity, no template stem, citations stay anchored, and citation shape stays reader-facing (no adjacent cite blocks / dup keys).
- Do not keep both candidates. Pick one and move on (the goal is convergence, not endless rewriting).

Role split:
- **Editor**: rewrite sentences for clarity and flow.
- **Skeptic**: deletes any generic/template sentence.

Targets:
- Each H3 reads like: tension → contrast → evidence → limitation.
- Remove repeated “disclaimer paragraphs”; keep evidence-policy in **one** place (prefer a singl

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-19
   ✓SAFE B 89 / 100

   first audit · source 81994516a430

Questions about Draft Polisher

• github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.c — the audited source at commit 81994516a430 and every finding aboveObserved · 19 Oct 2026

Spotted something wrong? Report a correction · Methodology