lark-docx-authoring
Skill1 starsChanged 3 months agoNo licenceView on GitHub
Author and surgically edit Feishu/Lark cloud documents (docx) with the lark-cli command line — both high-fidelity creation from scratch and, especially, incremental BLOCK-LEVEL patching of existing docs that already contain hand-added content (pasted screenshots, @mentions, embedded tables, diagrams) which must not be destroyed. Use this whenever you create, rewrite, or make targeted edits to a Lark/Feishu doc via lark-cli (docs +create / +fetch / +update / +media-insert): adding/replacing/deleting blocks, editing table cells or rows, inserting or swapping images, fixing heading numbering or ordered lists, or converting a Markdown/PRD into native Lark blocks. It encodes the traps that bite every time — whole-doc re-import wiping screenshots, broken image-token reuse, heading numbers that don't render, tables losing cell structure, block ids changing under you — and the verified way around each. Complements the stock lark-doc skill with the hard-won patch mechanics.
In this repository43 other files it gives its agents.
- alpha-labSkill
- binance-trader-scraperSkill
- chrome-cdpSkill
- codex-auditSkill
- comparison-dashboardSkill
- data-request-kitSkill
- decision-deckSkill
- demo-video-kitSkill
- dev-plannerSkill
- dify-workflow-architectSkill
- docsSkill
- docxSkill
- ealy-pitchSkill
- ego-messengerSkill
- exec-proposalSkill
- friction-playbookSkill
- git-cleanupSkill
- google-workspaceSkill
- group-sync-messengerSkill
- import-memorySkill
- jira-card-kitSkill
- mexc-daily-insightSkill
- mexc-infographicSkill
- morningSkill
- okr-reportSkill
- pdfSkill
- pm-interview-prepSkill
- polymarket-execution-auditSkill
- pptxSkill
- prd-authoring-kitSkill
- prd-kit-releaseSkill
- prd-reviewerSkill
- prd-writerSkill
- proposal-deckSkill
- proposal-playbookSkill
- pvp-team-designerSkill
- quant-code-reviewSkill
- session-memorySkill
- showcase-demoSkill
- skill-creatorSkill
- user-research-reportSkill
- video-makingSkill
- xlsxSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.