live-transcript-summary

live-transcript-summary is a skill for Claude Code from wpsnote/wpsnote-skills. It costs 147 tokens per session (5,579 once invoked), scanned A, original, MIT.

A real-time note-taking skill that watches audio transcription in the current WPS note and periodically organizes it. WPS is an office and note-taking application.

In plain words
What is it for?
It is for turning ongoing speech into organized notes using a suitable template and writing the results back into the note.
Why use it?
It reduces the need to take structured notes while recording a meeting, class, podcast, or interview.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the capture-skills plugin — 6 skills shipped together

Good fit It is for turning ongoing speech into organized notes using a suitable template and writing the results back into the note.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wpsnote/wpsnote-skills/live-transcript-summary
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 wpsnote/wpsnote-skills --skill live-transcript-summary
Clone the repo
git clone --depth 1 https://github.com/wpsnote/wpsnote-skills

Made for: Claude Code.

Or install capture-skills, the plugin that ships this one along with the rest of its 6 skills.

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.

agentmods badge for live-transcript-summary

README.md
[![agentmods](https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/live-transcript-summary/github.svg)](https://agentmods.dev/skills/wpsnote/wpsnote-skills/live-transcript-summary)
Your own site
<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/live-transcript-summary"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/live-transcript-summary/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for live-transcript-summary

Your own site · 80×15
<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/live-transcript-summary"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/live-transcript-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,579 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00147 $0.05579
Opus 5.5 $0.00059 $0.02232
Sonnet 5.5 $0.00029 $0.01116
Haiku 4.5 $0.00015 $0.00558

Measured 1mo ago against content hash e19cb19d8c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

live-transcript-summary 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 1mo 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/live-transcript-summary/SKILL.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

边听边总结 Skill

实时监听当前 WPS 笔记中的音频录音转写,每 60 秒轮询一次,只处理新增句子(增量模式),根据场景自动选择模板整理内容并写回笔记。


工具优先级

优先使用 wpsnote-cli(CLI),不支持时才退回 MCP 工具调用。

操作 CLI 命令 MCP 工具
获取当前笔记 wpsnote-cli current --json get_current_note()
获取大纲 wpsnote-cli outline --note_id ID --json get_note_outline()
获取转写 wpsnote-cli audio --shorthand_id ID --json get_audio_transcript()
搜索笔记 wpsnote-cli find --keyword KW --json search_notes()
搜索笔记内内容 wpsnote-cli search --note_id ID --query Q --json search_note_content()
插入内容 wpsnote-cli edit --json-args '...' edit_block(op="insert")
替换内容 wpsnote-cli edit --json-args '...' edit_block(op="replace")
批量编辑 wpsnote-cli batch-edit --json-args '...' batch_edit()

CLI 中 XML 含尖括号时,统一用 --json-args 传 JSON 对象,避免 shell 转义问题。


⚠️ 写入笔记时的强制规则

content 参数必须是 XML 字符串,绝不能是数组或对象。

// ✅ 正确
{ "content": "<h2>标题</h2><p>内容</p>" }

// ❌ 禁止——数组
{ "content": [{"type": "text", "text": "<h2>标题</h2>"}] }

// ❌ 禁止——对象
{ "content": {"type": "text", "text": "<h2>标题</h2>"} }

遇到 BLOCK_NOT_FOUND 或写入反复失败时,第一步检查 content 是否为字符串,再用 outline 刷新 block_id 后重试。


核心工作流

启动(仅一次):
  1. 检查 CLI 可用性
  2. 获取当前笔记 note_id
  3. 风格学习(搜索 3-5 篇历史同类笔记)
  4. 初始化状态文件
  5. 输出启动告知

loop(每 60 秒):
  1. 扫描笔记大纲,找 NoteAudioCard
  2. 全量拉取转写,过滤新增句子(start_time > last_end_time)
  3. 若无新增 → 检测临时区用户输入 → 更新状态 → sleep 60 → continue
  4. 首轮:场景识别 + 发言人推断
  5. 人名联动:提取人名 → 搜索笔记库 → 注入背景上下文
  6. 首轮:先输出内容地图,再开始写入
  7. 用新增句子生成摘要 XML
  8. 写回笔记(首轮在末尾插入;后续追加到 summary_anchor 之后,始终在临时区之前)
  9. 回扫大纲:核查新内容是否落在正确章节,发现位置错误立即修正
 10. 首轮:在笔记末尾创建临时区(hr + 提示块)
 11. 检测临时区用户输入 → 合并到正文 → 清空用户 block
 12. 检测 *** 补全请求
 13. 更新状态文件(last_end_time、summary_anchor_id、temp_zone_anchor_id 等)
 14. 输出本轮简报 → sleep 60 → loop

启动阶段

Step 1:检查 CLI 可用性

wpsnote-cli status
# 输出包含"连接中... 成功" → CLI 可用,否则退回 MCP 模式

Step 2:获取当前笔记

NOTE=$(wpsnote-cli current --json)
NOTE_ID=$(echo $NOTE | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['data']['note_id'])")

Read the full file on GitHub · 521 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 1mo ago First seen · 521 lines · 147 tokens per session scan A e19cb19d8c12

Subscribe to this mod's changes

live-transcript-summary is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 5,579 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.