Send messages, images, and files to Feishu groups or individuals.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionsend-feishuExecute the skills CLI command in your project's root directory to begin installation:
Fetches send-feishu from jssfy/k-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate send-feishu. Access via /send-feishu in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
2
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
2
stars
Send messages, images, and files to Feishu groups or individuals.
| Variable | Purpose | Required |
|---|---|---|
FEISHU_WEBHOOK |
Group Webhook URL | For text/card/image to group |
FEISHU_APP_ID |
App credential | For image/file upload & API send |
FEISHU_APP_SECRET |
App credential | For image/file upload & API send |
FEISHU_CHAT_ID |
Group chat ID (oc_xxx) |
For API send to group |
FEISHU_USER_OPEN_ID |
Personal open_id (ou_xxx) |
For send to individual |
FEISHU_WEBHOOK_SECRET |
Webhook signing secret | Only when group webhook has signature enabled |
ALWAYS follow this order — never skip Step 0:
Step 0 — Run Variable Resolution (mandatory bash, no exceptions):
FEISHU_APP_ID="${FEISHU_APP_ID:-${CTI_FEISHU_APP_ID:-}}"
FEISHU_APP_SECRET="${FEISHU_APP_SECRET:-${CTI_FEISHU_APP_SECRET:-}}"
FEISHU_CHAT_ID="${FEISHU_CHAT_ID:-${CTI_FEISHU_CHAT_ID:-}}"
FEISHU_WEBHOOK="${FEISHU_WEBHOOK:-${CTI_FEISHU_WEBHOOK:-}}"
echo "resolved: APP_ID=${FEISHU_APP_ID:0:8} CHAT_ID=${FEISHU_CHAT_ID} WEBHOOK=${FEISHU_WEBHOOK:0:20}"
Step 1 — Based on what's now available, choose method:
File/Image + FEISHU_CHAT_ID set → Get token → Upload → API send to chat_id ✅ preferred for groups
File/Image + FEISHU_APP_ID set → Get token → Upload → API send to chat_id (if user implied group)
Text/Card + FEISHU_WEBHOOK set → Webhook send
Text/Card + FEISHU_CHAT_ID set → Get token → API send to chat_id
Any + open_id known → Get token → API send to open_id
Nothing set after resolution → Ask user for missing vars
Use text — simple one-liner (status update, quick note).
Use card — content has title + body, structured data, summary, or report.
Use image — user explicitly asks to send an image file, screenshot, or chart.
Use file — user asks to send .html/.md/.pdf/.doc/.xls etc., or content is too long for card display.
Send to individual — user says "发给我", "私发", "发到我的飞书", or specifies a person.
Required for image upload, file upload, and API message sending. Skip this step if only sending text/card via Webhook.
curl -s -X POST 'https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal' \
-H 'Content-Type: application/json' \
-d '{"app_id":"'"$FEISHU_APP_ID"'","app_secret":"'"$FEISHU_APP_SECRET"'"}'
Response: {"code":0,"msg":"ok","tenant_access_token":"t-xxx","expire":7200}
Extract the token and store in a variable for subsequent steps.
Required when sending an image. Supports JPEG/PNG/WEBP/GIF/TIFF/BMP/ICO, max 10MB.
curl -s -X POST 'https://open.feishu.cn/open-apis/im/v1/images' \
-H "Authorization: Bearer $TOKEN" \
-F 'image_type="message"' \
-F 'image=@"/path/to/image.png"'
Response: {"code":0,"data":{"image_key":"img_xxx"}}
Required when sending a file. Max 30MB.
curl -s -X POST 'https://open.feishu.cn/open-apis/im/v1/files' \
-H "Authorization: Bearer $TOKEN" \
-F 'file_type="stream"' \
-F 'file_name="report.md"' \
-F 'file=@"/path/to/file"'
file_type values: opus (audio), mp4 (video), pdf, doc, xls, ppt, stream (binary, use as default).
Response: {"code":0,"data":{"file_key":"file_xxx"}}
If the webhook has signature verification enabled, generate timestamp and sign first, then include them in the webhook payload. If no secret is configured, use the unsigned examples below.
python3 - <<'PY'
import base64
import hashlib
import hmac
import json
import os
import time
secret = os.environ["FEISHU_WEBHOOK_SECRET"]
timestamp = str(int(time.time()))
string_to_sign = f"{timestamp}\n{secret}".encode("utf-8")
sign = base64.b64encode(hmac.new(string_to_sign, b"", digestmod=hashlib.sha256).digest()).decode("utf-8")
payload = {
"timestamp": timestamp,
"sign": sign,
"msg_type": "text",
"content": {"text": "MESSAGE_HERE"},
}
print(json.dumps(payload, ensure_ascii=False))
PY
将输出的 JSON 作为 curl -d 请求体发送到 $FEISHU_WEBHOOK。卡片、图片消息同理，只需替换 msg_type 和 content。
curl -s -X POST "$FEISHU_WEBHOOK" -H "Content-Type: application/json" \
-d '{"msg_type":"text","content":{"text":"MESSAGE_HERE"}}'
Pick header color by sentiment:
green — success, complete, doneorange — warning, attentionred — error, failureblue — info, neutral (default)purple — highlight, specialShort content (no special characters):
curl -s -X POST "$FEISHU_WEBHOOK" -H "Content-Type: application/json" \
-d '{
"msg_type":"interactive",
"card":{
"header":{"title":{"content":"TITLE","tag":"plain_text"},"template":"COLOR"},
"elements":[{"tag":"div","text":{"content":"BODY_LARK_MD","tag":"lark_md"}}]
}
}'
Long content or content with special characters ($, ", \n, etc.) — always use this pattern:
python3 - << 'EOF' | curl -s -X POST "$FEISHU_WEBHOOK" \
-H "Content-Type: application/json" -d @-
import json
card = {
"msg_type": "interactive",
"card": {
"header": {"title": {"content": "TITLE", "tag": "plain_text"}, "template": "COLOR"},
"elements": [
{"tag": "div", "text": {"content": "BODY LINE 1\nBODY LINE 2", "tag": "lark_md"}},
{"tag": "hr"},
{"tag": "div", "text": {"content": "SECTION 2 CONTENT", "tag": "lark_md"}}
]
}
}
print(json.dumps(card))
EOF
Card body supports lark_md: **bold**, *italic*, ~~strike~~, [link](url), \n for newlines.
After uploading image (Step B) to get image_key:
curl -s -X POST "$FEISHU_WEBHOOK" \
-H "Content-Type: application/json" \
-d '{"msg_type":"image","content":{"image_key":"img_xxx"}}'
Use API when sending files, or sending any content to an individual.
curl -s -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=chat_id" \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
-d '{"receive_id":"'"$FEISHU_CHAT_ID"'","msg_type":"MSG_TYPE","content":"CONTENT_JSON_STRING"}'
curl -s -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=open_id" \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json; charset=utf-8" \
-d '{"receive_id":"'"$FEISHU_USER_OPEN_ID"'","msg_type":"MSG_TYPE","content":"CONTENT_JSON_STRING"}'
The content field must be a JSON-encoded string (escaped JSON inside JSON).
Text:
{"receive_id":"ID","msg_type":"text","content":"{\"text\":\"Hello\"}"}
Image (after upload):
{"receive_id":"ID","msg_type":"image","content":"{\"image_key\":\"img_xxx\"}"}
File (after upload):
{"receive_id":"ID","msg_type":"file","content":"{\"file_key\":\"file_xxx\"}"}
Check the response JSON:
{"code":0,"msg":"success"} → success{"code":0,"msg":"success","data":{...}} → successcode != 0 → report the error:
printf '%s' or heredoc to safely pass message content to curl if it contains special charactersCTI_FEISHU_* may already provide themFEISHU_WEBHOOK_SECRET and include timestamp + signim:message:send_as_bot (send messages), im:resource (upload images and files)Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
send-feishu has been reliable in day-to-day use. Documentation quality is above average for community skills.
Keeps context tight: send-feishu is the kind of skill you can hand to a new teammate without a long onboarding doc.
send-feishu fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
send-feishu reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend send-feishu for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for send-feishu matched our evaluation — installs cleanly and behaves as described in the markdown.
send-feishu reduced setup friction for our internal harness; good balance of opinion and flexibility.
Useful defaults in send-feishu — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
We added send-feishu from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
send-feishu is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
showing 1-10 of 68