ziondoki/confucius/annotation-pass

Claude Code and agent skill by ziondoki/confucius

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Prepare PDF annotations and request approval before writing them.

Install

npx vskill@latest install ziondoki/confucius/annotation-pass

SKILL.md

The host freezes each PDF's pre-existing colors when it joins this task and remaps conflicts automatically. Use the final colors returned in previews and receipts in the report legend. The task chat has one persistent annotation batch across follow-ups, retries and Agent changes; new and branched tasks have new batches. Only verified Confucius Agent annotations may be changed with update_annotation (comment and/or a same-PDF text anchor), update_annotation_comment, or delete_annotation, across tasks and Agents. Keep the original batch and creation source; unknown old marks remain existing annotations. Do not add batch tags to native annotations. Existing tags stay unchanged. Labels, author names and colors never authorize changes. After interruption, use receipts and reconcile unknown writes; never recreate an already saved or deleted annotation.

Follow an explicit output-language request first, otherwise the current substantive user request, then the most recent effective conversation language, with the interface language only as a fallback. A bare skill command, retry or continuation inherits the conversation language. This applies to any language, including progress, annotation comments, artifact titles, report prose and revisions. Preserve source quotations and annotation anchors in their original language.

Prepare annotations for the user's reading goal. Respect the requested count and scope. If optional preferences are absent, use the settings below without asking follow-up questions.

Use this default legend unless the user overrides it for this task:

  • yellow highlight (#ffd400) = key point
  • blue underline (#2ea8e5) = supporting detail
  • purple image-region note (#a28ae5) = visual evidence with an explanation

Read physical pages with get_pages and existing marks with get_annotations. Text contains [anchor:ID] before selectable passages. Copy the ID into annotation.anchor, and write a useful comment in the user's response language. Omit page and quote; the tool resolves the exact native text and positions. Preserve the claim's conditions and denominators and distinguish source findings from your interpretation. Image-region notes need a comment and coordinates from inspect_pdf_page. Inspect at most one visual page per model round. If no page image is returned, omit the region instead of guessing its coordinates. Follow any colors, legend, method-summary format, note voice, or focus set by the user.

Call commit_annotations directly with annotations:[{anchor,comment}], one entry or a batch. Type defaults to highlight; underline and color are optional. Use propose_annotations only for a saved candidate draft the user requests. Submission saves suggestions in the task review area; only the user’s acceptance writes them to the PDF. Submitted suggestions complete generation and do not require waiting or further batches. After partial success, repair only unresolved entries; preserve existing marks and user edits. Never retry a denied write or an unchanged non-retryable failure. Create an annotation_set artifact only if the user requests a separate file. Distinguish submitted suggestions from actual saved/skipped outcomes. Use only zoteroUri values returned by tools. Use the user's response language for progress, comments, artifacts and the final answer; keep source quotations in their original language.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ziondoki/confucius/annotation-pass/badge)](https://verified-skill.com/skills/ziondoki/confucius/annotation-pass)

Something wrong with this skill or its page? Tell us.