optional-skills/cc-connect/SKILL.md
This 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".
npx skillsauth add archibate/dotfiles-opencode cc-connectInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.).
All commands use cc-connect send with different flags.
cc-connect send --image /absolute/path/to/image.png -p <project> -m "Description"
--image for multiple images in one message.cc-connect send --file /absolute/path/to/report.pdf -p <project> -m "Description"
--file for multiple files.cc-connect send -m "Task completed successfully" -p <project>
cc-connect send --stdin -p <project> <<'EOF'
Build completed!
- Tests: PASS
- Coverage: 87%
EOF
cc-connect send --image /path/to/chart.png --file /path/to/data.csv -p <project> -m "Results attached"
| 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 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.
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"
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>
cc-connect send \
--file /tmp/report.pdf \
--file /tmp/data.csv \
--image /tmp/summary_chart.png \
-p <project> \
-m "Weekly report attached"
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"
Check available projects with grep 'name = ' ~/.cc-connect/config.toml and
use the exact project name with -p.
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).
cc-connect daemon statusattachment_send = "on" in ~/.cc-connect/config.toml (global or per-project)cc-connect --version)development
Color theme palettes for UI/UX design and personal configurations (i3wm, dunst, etc.). Use when user asks to apply color themes like Tokyo Night, needs color palettes for frontend development, or wants to customize terminal/desktop colors.
development
This skill should be used when the user asks about "code complexity", "cyclomatic complexity", "cognitive complexity", "code metrics", "maintainability index", "code coverage", or when measuring code quality quantitatively. Provides metrics thresholds and measurement techniques.
tools
Implement CLI tools in Python, JS/TS, Bash, or Go following clig.dev standards. Use when writing or reviewing CLI code.
tools
Spec CLI surface area before implementation - command tree, flags, exit codes, I/O contract. Use when designing or planning a CLI interface.