What is doc-finalise?

A finishing process for Word documents that checks the file, embeds visuals, standardises styles, regenerates a PDF, and prepares a commit summary.

Use it to finish status reports, board packs, sprint retrospectives, RFCs, and compliance documents in .docx format.

It catches formatting, image, conversion, and factual-consistency problems before a document is delivered.

doc-finalise — Skill for Claude Code by ao92265

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ao92265/claude-code-playbook --skill doc-finalise

Clone the repo

git clone --depth 1 https://github.com/ao92265/claude-code-playbook

Made for: Claude Code.

Or install playbook, the plugin that ships this one along with the rest of its 48 skills, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/doc-finalise.svg)](https://agentmods.dev/skills/ao92265/claude-code-playbook/doc-finalise)

Your own site

<a href="https://agentmods.dev/skills/ao92265/claude-code-playbook/doc-finalise"><img src="https://agentmods.dev/badge/skills/ao92265/claude-code-playbook/doc-finalise.svg" alt="Measured on agentmods" height="20"></a>

Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,549 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00117	$0.01549
Opus 5	$0.00059	$0.00775
Sonnet 5	$0.00023	$0.00310
Haiku 4.5	$0.00012	$0.00155

Measured 8d ago against content hash acd668575e86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

doc-finalise scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/doc-finalise/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Finalisation

Structured workflow for finishing a .docx deliverable: programmatic integrity check, embedded visuals, style normalisation, PDF regeneration, and a Closeout Trio summary. Built for the case where a reviewer will spot every wandering em-dash and every rounding drift.

When to Use

Executive status reports where rounded numbers must be replaced with exact ones.
Board packs and compliance documents with claim-level provenance requirements.
Any second-pass edit where "tighten this up" has historically rephrased a number into an inaccuracy.
Documents where visuals must survive the .docx → PDF conversion unchanged.

When Not to Use

Drafting the document from scratch — use a writer skill, then finalise with this one.
Slide decks (.pptx) — different library, different gotchas.
Plain markdown deliverables — style inheritance and PDF rendering are not in scope.

Steps

Read the docx toolchain reference before touching the file. Load the Anthropic bundled docx skill (if available) or your project's python-docx reference. Do not skip this even if the model thinks it knows the API — the style-map and image-anchor details are where real documents break.

Inventory the source document programmatically. Capture a baseline so any later claim of "I only changed X" is verifiable.

Check	What to capture
Structure	Paragraph count, table count, section count, page count
Styles	Full style map, every explicit style override on every run
Typography	Em-dash (`—`) and en-dash (`–`) counts across `document.xml`, `header.xml`, `footer.xml`
Assets	Every embedded image (id, size, anchor paragraph text)
Theme	Font references — `majorFont` / `minorFont` — and any theme fallback

Embed visuals as PNG, not linked images. Linked images break on email handoff and PDF conversion.
- Use doc.add_picture() inside a centred paragraph, not floating anchors.
- Insert at named text anchors — "before the paragraph starting with Quarterly summary" — not "around the end of section 3". Paragraph indices shift; sentence fragments do not.
- Render charts with matplotlib at the target font size, save to PNG at 150 DPI minimum, embed from memory.

Read the full file on GitHub · 109 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 109 lines · 117 tokens per session scan A acd668575e86

Subscribe to this mod's changes

doc-finalise is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 21d ago), licensed MIT. It adds 117 tokens to every session and 1,549 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents PDF Writing and docs

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

doc-finalise