archibate/dotfiles-opencode / optional-skills/cc-connect
cc-connect
VerifiedThis skill should be used when sending images, files, or notifications back to the user via messaging platforms (Discord, Feishu, Telegram, etc.) through cc-connect. TRIGGER when agent generates a plot/chart/screenshot and wants to show the user; agent creates a report/PDF/file the user should receive; agent needs to proactively notify the user (e.g. task completed, alert, reminder); user asks to "send image", "show me the chart", "notify me", "send the file", "send to Telegram", "show plot in Discord".
cc-connect: Send Images, Files, and Notifications
Purpose
Claude Code cannot send images or files back to users. The terminal output
is text-only. cc-connect bridges this gap by providing a send command
that delivers images, files, and text notifications directly through
messaging platforms (Discord, Feishu, Telegram, etc.).
When to use
- Send generated charts/plots — matplotlib, plotly, seaborn, etc.
- Send screenshots — captured via agent-browser or other tools
- Send reports/files — PDFs, CSVs, logs, any artifact to transfer
- Proactive notifications — task completed, long job done, alerts
- Send links — share URL links to user (easier to click)
When NOT to use
- Short text report — response directly
- Service not available — skip this skill if cc-connect daemon not running
Commands
All commands use cc-connect send with different flags.
Send an Image
cc-connect send --image /absolute/path/to/image.png -p <project> -m "Description"
- Repeat
--imagefor multiple images in one message. - Supported formats: PNG, JPG, JPEG, GIF.
- Always use absolute paths.
Send a File
cc-connect send --file /absolute/path/to/report.pdf -p <project> -m "Description"
- Repeat
--filefor multiple files. - Works with any file type: PDF, CSV, ZIP, etc.
Send a Text Notification
cc-connect send -m "Task completed successfully" -p <project>
- For long or multi-line messages, use heredoc:
cc-connect send --stdin -p <project> <<'EOF'
Build completed!
- Tests: PASS
- Coverage: 87%
EOF
Combine Image + File + Message
cc-connect send --image /path/to/chart.png --file /path/to/data.csv -p <project> -m "Results attached"
Common Options
| Flag | Description |
|---|---|
-p, --project <name> | Target project name (required when multiple projects exist) |
-s, --session <key> | Target specific session key (optional, defaults to first active) |
-m, --message <text> | Text message to accompany the attachment |
--image <path> | Image file to send (repeatable) |
--file <path> | File to send (repeatable) |
--stdin | Read message body from stdin |
Project Names
Project names come from ~/.cc-connect/config.toml. Check the config to find
available project names:
grep -A1 'name = ' ~/.cc-connect/config.toml
If only one project is configured, -p can be omitted.
Workflow Patterns
Pattern 1: Generate and Send a Chart
After generating a plot with matplotlib, save it to disk and send:
import matplotlib.pyplot as plt
plt.savefig("/tmp/chart.png", dpi=150, bbox_inches="tight")
plt.close()
Then:
cc-connect send --image /tmp/chart.png -p <project> -m "Here is the chart"
Pattern 2: Notify After Long Task
When a long-running task completes (training, backtest, build), notify the user even if they are away from the screen:
cc-connect send -m "Training complete! Loss: 0.023, Accuracy: 97.2%" -p <project>
Pattern 3: Send Report with Multiple Files
cc-connect send \
--file /tmp/report.pdf \
--file /tmp/data.csv \
--image /tmp/summary_chart.png \
-p <project> \
-m "Weekly report attached"
Troubleshooting
"no active session found"
Try specifying the full session key found in daemon logs:
journalctl --user -u cc-connect -n 20 --no-pager | grep session_key
If not found: The user has not started a chat session yet. The user must send at least one message on the platform before
cc-connect sendcan deliver to them.
Then use the session key:
cc-connect send --image /path/to/img.png -p <project> -s "discord:xxx:xxx" -m "Image"
"project not found"
Check available projects with grep 'name = ' ~/.cc-connect/config.toml and
use the exact project name with -p.
Beta Version Required
The --image and --file flags require cc-connect >= v1.2.2-beta. Install
via:
npm install -g cc-connect@beta
Stable versions (v1.2.1 and below) only support text messages (-m, --stdin).
Requirements
- cc-connect daemon must be running:
cc-connect daemon status attachment_send = "on"in~/.cc-connect/config.toml(global or per-project)- For image/file sending: cc-connect >= v1.2.2-beta (
cc-connect --version)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |