Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
code.deepline.com avatar

Deepline Feedback

  • 18.6k installs
  • code.deepline.com

A CLI skill that submits user feedback and bug reports to Deepline with automatic session transcript and environment context attachment.

About

Deepline Feedback is a CLI-based feedback submission tool that captures user-reported bugs or product suggestions along with environment metadata and current session transcripts. Developers use it within Claude or Cowork sessions to send actionable reports directly to the Deepline team without manual log gathering. The workflow prompts for feedback text, confirms what will be sent (feedback, environment info, session data), then executes two commands: one to send the feedback payload and another to attach the current or most recent session transcript, with fallback logic for Cowork-mounted project directories.

  • Collects feedback text from user or command argument
  • Auto-includes environment info and session transcript in reports
  • Supports both standard Claude sessions and Cowork mounted transcripts with bridging logic
  • Confirmation step shows exactly what data will be sent before submission
  • Sends via deepline CLI commands with JSON output for reliability

Deepline Feedback by the numbers

  • 18,577 all-time installs (skills.sh)
  • +2,071 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #80 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
At a glance

deepline-feedback capabilities & compatibility

Capabilities
collect user feedback via argument or prompt · confirm data payload before submission · send feedback via deepline cli · retrieve and send current or fallback session tr · bridge cowork mounted directories to standard cl
Platforms
macOS · Linux · WSL
Runs
Runs locally
Pricing
Free
From the docs

What deepline-feedback says it does

Send feedback or a bug report to the Deepline team.
skill:code.deepline.com#deepline-feedback (description)
npx skills add https://github.com/code.deepline.com --skill deepline-feedback

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs18.6k
Security audit1 / 1 scanners passed
Repositorycode.deepline.com

What it does

Submit bug reports and product feedback to Deepline with session transcript and environment context automatically included.

Who is it for?

Reporting bugs, requesting features, and sharing session context during active development in Claude or Cowork.

Skip if: General support inquiries outside Claude sessions; feature requests without context.

When should I use this skill?

User asks to report a bug, send feedback, or share session with Deepline support.

What you get

User submits feedback with full session and environment context; Deepline team receives actionable report with transcript for debugging.

  • Submitted feedback payload
  • Attached session transcript
  • Confirmation message to user

By the numbers

  • Supports two transcript sources: standard Claude sessions and Cowork-mounted directories
  • Two sequential CLI commands: one for feedback, one for session data

Files

SKILL.mdMarkdownGitHub ↗

Deepline Feedback

Send feedback or a bug report to the Deepline team.

Steps

1. Get feedback text. Use the argument if provided (e.g. /deepline-feedback the waterfall broke). Otherwise ask the user.

2. Confirm. Use AskUserQuestion with a question like:

This report will include:

>

- Your feedback: {feedback text}
- Environment info (auto-collected)
- Current session transcript

>

Send this feedback?

Options: "Send it" / "Cancel".

3. If confirmed, send the feedback text first:

   deepline feedback send "{feedback text}" --json

4. Send the session transcript. Try the normal Claude transcript location first:

   deepline sessions send --current-session --json

If that reports no session files and ~/mnt/.claude/projects exists, the run is likely in Cowork. Bridge the mounted transcript directory, then retry. If --current-session still cannot resolve a session, send the newest mounted transcript directly:

   if [ -d "$HOME/mnt/.claude/projects" ]; then
     mkdir -p "$HOME/.claude"
     ln -sfn "$HOME/mnt/.claude/projects" "$HOME/.claude/projects" 2>/dev/null || true
     deepline sessions send --current-session --json || deepline sessions send --file "$(ls -t "$HOME"/mnt/.claude/projects/*/*.jsonl | head -1)" --json
   fi

Use the plural sessions send command, not the old singular session form.

5. Tell the user it was sent. If cancelled, do nothing.

Related skills

FAQ

What data is included in my feedback submission?

Feedback text, auto-collected environment info, and the current session transcript (or newest Cowork-mounted transcript if standard session unavailable).

What happens if there is no current session?

The skill checks for Cowork mounted transcripts at ~/mnt/.claude/projects and sends the newest .jsonl file found; if none exist, feedback is sent without transcript.

Is Deepline Feedback safe to install?

skills.sh reports 1 of 1 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.