docs: call out the execute_code requirement for render_format docx (v0.4.1)#6
Merged
Merged
Conversation
…0.4.1) The docx render path builds the Word file by running python-docx, which needs the execute_code plugin enabled — a code-execution capability. That requirement was present but buried; surface it prominently so no one hits it (or enables code execution) by surprise. - README: a dedicated "Native Word (.docx) export" bullet in Quick start → Optional that lists the requirements and flags⚠️ execute_code runs arbitrary code (a trust decision); strengthened the design-decision bullet likewise. - job-application-assistant SKILL.md + role-packet SKILL.md: the render step now tells the agent that docx needs cowork's docx skill + execute_code, and to NAME exactly what's missing and fall back to html rather than silently switching. - cv-guide.md: execute_code framed as a code-execution trust decision. Docs only; version 0.4.0 → 0.4.1. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NvgV2saY75czWLEqaNVKaq
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow-up to #5. The
render_format: docxpath builds the Word file by runningpython-docx, which needs theexecute_codeplugin enabled — i.e. it depends on a code-execution capability. That requirement was documented but buried, so it read as a surprise. This surfaces it prominently, and makes the agent name it at runtime instead of silently falling back.Why this matters
A user turning on docx shouldn't discover — after the fact — that it requires enabling arbitrary code execution.
execute_codeis a real trust decision; it deserves an explicit, up-front callout.Changes
.docx) export" bullet in Quick start → Optional listing the full requirement chain (cowork +execute_code+artifact+ a v0.107.0+ host) with aexecute_coderuns arbitrary code — a deliberate trust decision warning; strengthened the design-decision bullet the same way.job-application-assistant/SKILL.md+role-packet/SKILL.md— the render step now instructs the agent: docx needs cowork'sdocxskill +execute_code; if either is off, name exactly what's missing and fall back tohtml— never silently switch.cv-guide.md—execute_codeframed as a code-execution trust decision.Testing
14 passed,ruffclean. Docs/skill-markdown + version only. Version 0.4.0 → 0.4.1.🤖 Generated with Claude Code
https://claude.ai/code/session_01NvgV2saY75czWLEqaNVKaq