跳到正文
cccskills
免费在 GitHub 公开

feishu-notify

Send experiment results, review scores, and requests for input to Feishu/Lark. Use it manually or from other skills, with one-way notifications or an optional connection that returns approvals, rejections, and written replies.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.

查看安装方法

适用场景

  • Receive experiment completion notifications
  • Check review scores on Feishu/Lark
  • Approve or reject requests from Feishu/Lark
  • Send a custom status message

包含的文件(1)

  • SKILL.md6.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Feishu/Lark Notification

Send a notification: $ARGUMENTS

Overview

This skill provides Feishu/Lark integration for ARIS. It is designed as an internal utility — other skills call it at key events (experiment done, review scored, checkpoint waiting). It can also be invoked manually.

Zero-impact guarantee: If no feishu.json config exists, this skill does nothing and returns silently. All existing workflows are completely unaffected.

Configuration

The skill reads ~/.claude/feishu.json. If this file does not exist, all Feishu functionality is disabled — skills behave exactly as before.

Config Format

{
  "mode": "push",
  "webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID",
  "interactive": {
    "bridge_url": "http://localhost:5000",
    "timeout_seconds": 300
  }
}

Modes

Mode"mode" valueWhat it doesRequires
Off"off" or file absentNothing. Pure CLI as-isNothing
Push only"push"Send webhook notifications at key events. Mobile push, no replyFeishu bot webhook URL
Interactive"interactive"Full bidirectional. Approve/reject from Feishu, reply to checkpointsfeishu-claude-code running

Workflow

Step 1: Read Config

cat ~/.claude/feishu.json 2>/dev/null
  • File not found → return silently, do nothing
  • "mode": "off" → return silently, do nothing
  • "mode": "push" → proceed to Step 2 (push)
  • "mode": "interactive" → proceed to Step 3 (interactive)

Step 2: Push Notification (webhook)

Send a rich card to the Feishu webhook:

curl -s -X POST "$WEBHOOK_URL" \
  -H "Content-Type: application/json" \
  -d '{
    "msg_type": "interactive",
    "card": {
      "header": {
        "title": {"tag": "plain_text", "content": "TITLE"},
        "template": "COLOR"
      },
      "elements": [
        {"tag": "markdown", "content": "BODY"}
      ]
    }
  }'

Card templates by event type:

EventTitleColorBody
experiment_doneExperiment CompletegreenResults table, delta vs baseline
review_scoredReview Round N: X/10blue (≥6) / orange (<6)Score, verdict, top 3 weaknesses
checkpointCheckpoint: Waiting for InputyellowQuestion, options, context
errorError: [type]redError message, what failed
pipeline_donePipeline CompletepurpleFinal summary, deliverables
customCustomblueFree-form message from $ARGUMENTS

Return immediately after curl — push mode never waits for a response.

Step 3: Interactive Notification (bidirectional)

Interactive mode uses feishu-claude-code as a bridge:

  1. Send message to the bridge:

    curl -s -X POST "$BRIDGE_URL/send" \
      -H "Content-Type: application/json" \
      -d '{"type": "EVENT_TYPE", "title": "TITLE", "body": "BODY", "options": ["approve", "reject", "custom"]}'
    
  2. Wait for reply (with timeout):

    curl -s "$BRIDGE_URL/poll?timeout=$TIMEOUT_SECONDS"
    

    Returns: {"reply": "approve"} or {"reply": "reject"} or {"reply": "user typed message"} or {"timeout": true}

  3. On timeout: Fall back to AUTO_PROCEED behavior (proceed with default option).

  4. Return the user's reply to the calling skill so it can act on it.

Step 4: Verify Delivery

  • Push mode: Check curl exit code. If non-zero, log warning but do NOT block the workflow.
  • Interactive mode: If bridge is unreachable, fall back to push mode (if webhook configured) or skip silently.

Helper Function (for other skills)

Other skills should use this pattern to send notifications:

### Feishu Notification (if configured)

Check if `~/.claude/feishu.json` exists and mode is not "off":
- If **push** mode: send webhook notification with event summary
- If **interactive** mode: send notification and wait for user reply
- If **off** or file absent: skip entirely (no-op)

This check is always guarded. If the config file doesn't exist, the skill skips the notification block entirely — zero overhead, zero side effects.

Event Catalog

Skills send these events at these moments:

SkillEventWhen
/auto-review-loopreview_scoredAfter each round's review score
/auto-review-looppipeline_doneLoop complete (positive or max rounds)
/auto-paper-improvement-loopreview_scoredAfter each round's review score
/auto-paper-improvement-looppipeline_doneAll rounds complete
/run-experimentexperiment_doneScreen session finishes
/idea-discoverycheckpointBetween phases (if interactive)
/idea-discoverypipeline_doneFinal report ready
/monitor-experimentexperiment_doneResults collected
/research-pipelinecheckpointBetween workflow stages
/research-pipelinepipeline_doneFull pipeline complete

Key Rules

  • NEVER block a workflow because Feishu is unreachable. Always fail open.
  • NEVER require Feishu config — all skills must work without it.
  • Config file absent = mode off. No error, no warning, no log.
  • Push mode is fire-and-forget. Send curl, check exit code, move on.
  • Interactive timeout = auto-proceed. Don't hang forever waiting for a reply.
  • Respect AUTO_PROCEED: In interactive mode, if the user doesn't reply within timeout, use the same auto-proceed logic as the calling skill.
  • No secrets in notifications. Never include API keys, tokens, or passwords in Feishu messages.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Plan ablation studies, experiments that remove or replace parts of a machine learning method to test their contribution. Define reviewer questions, expected outcomes, priorities, execution order, and compute estimates, then implement experiments and record findings.

中文简介正在准备中。当前显示英语简介。

  • Testing the contribution of individual method components
  • Planning additional experiments before paper submission
  • Prioritizing experiments within a GPU budget
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月22日 更新

Plan and run ablation studies, experiments that remove or replace parts of a method to test their contribution. Organize reviewer questions, priorities, expected outcomes, and compute costs, then record results and findings.

中文简介正在准备中。当前显示英语简介。

  • Test how much each component contributes
  • Plan experiments that address reviewer questions
  • Prioritize comparisons within a compute budget
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月22日 更新

alphaxiv

免费

Understand a single arXiv paper through an AlphaXiv summary, with full text and LaTeX source available when needed. Use it to identify key findings or ask specific questions about methods, experiments, and equations.

中文简介正在准备中。当前显示英语简介。

  • Get a quick overview of a paper from its URL
  • Check a paper's methods and experimental results
  • Ask about equations, proofs, or appendix details
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月22日 更新

Compare machine learning experiment results from JSON or CSV files. Calculate improvements over a baseline, summarize variation across repeated runs, identify trends and unusual results, and suggest experiments to test possible explanations.

中文简介正在准备中。当前显示英语简介。

  • Compare model performance across experimental conditions
  • Check variation across runs with different random seeds
  • Identify trends as a parameter changes
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月22日 更新

arxiv

免费

Search arXiv papers by topic or paper ID, review authors and abstracts, and summarize contributions stated in the abstracts. Download selected papers or all search results as PDFs to build a local paper library.

中文简介正在准备中。当前显示英语简介。

  • Find arXiv papers on a research topic
  • Retrieve details for a known arXiv paper ID
  • Download all PDFs from a set of search results
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月22日 更新

Improve a compiled LaTeX paper through two rounds of Claude review, edits, and recompilation. The workflow addresses inconsistent reasoning, unsupported claims, unclear writing, and visual presentation, while keeping a cumulative log of changes.

中文简介正在准备中。当前显示英语简介。

  • Polish a generated paper before submission
  • Correct inconsistencies and unsupported claims
  • Improve figures, tables, and page layout
wanshuiyin/Auto-claude-code-research-in-sleep1.8万2026年10月22日 更新

查看 wanshuiyin 的全部技能

报告此技能的问题