AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Docx Editor

skill-firstp1ck-pi-coding-agent-forge-docx-editor · by Firstp1ck

Safely inspect, search, render, edit, diff, validate, and commit Microsoft Word DOCX files with the dedicated docx_* tools. Use for DOCX/DOTX/DOCM/DOTM document work; enforces dry-run-first edits, active-content refusal, preservation checks, and save-as by default.

↗ Repository
— No reviews yet
0 installs
32 views
0.0% view→install

Install

$ agentstack add skill-firstp1ck-pi-coding-agent-forge-docx-editor

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-firstp1ck-pi-coding-agent-forge-docx-editor)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Docx Editor? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

DOCX editor

Required workflow

  1. Call docx_inspect before editing an unfamiliar document. Keep sourceSha256, feature/security inventory, and capability report.
  2. Call docx_read for only the relevant stories/blocks. Use returned paragraph IDs, paths, hashes, bookmarks, controls, or strict text anchors.
  3. Call docx_render when pagination, layout, tables, images, headers/footers, or formatting matter. Keep page selections small.
  4. Call docx_edit with dryRun: true; use exact preconditions and expected counts. Resolve ambiguity rather than broadening an edit.
  5. Call docx_edit with dryRun: false and expectedSourceSha256 to create a staged revision. This tool must not receive a destination.
  6. Call docx_validate and docx_diff against source and staged paths. Render focused before/after pages for visually sensitive operations.
  7. Call docx_commit to a new .docx path by default.
  8. Overwrite the source only when the user explicitly asked, hashes still agree, every gate passes, and interactive confirmation is available. Require a recovery path in the result.

Safety rules

  • Never use built-in text edit or write on DOCX/DOCM/DOTX/DOTM.
  • Never execute macros, OLE, fields, links, DDE, or attached templates. Never claim they were executed or refreshed.
  • Treat .docm/.dotm, active content, and signatures as read/render only. Do not bypass SIGNED_DOCUMENT or ACTIVE_CONTENT_BLOCKED.
  • Do not mutate raw XML, XPath, arbitrary ZIP parts, or page-number selectors.
  • Do not silently convert formats. Legacy/template conversion must create a new .docx and report losses.
  • Stop on LOSSY_OPERATION, protected-part changes, unavailable mandatory engines, validation failures, source/destination conflicts, or ambiguous selectors.
  • Keep hidden/deleted metadata out of model-visible output unless the user explicitly asks to inspect it.

Verification

A successful tool return is not enough. Confirm source and staged/output hashes, declared changed parts, protected-part stability, Open XML validation, independent reopen, semantic diff, and required render checks. Report renderer/font warnings and any host gate that was not run.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Developer Tools