deepline-feedback
code.deepline.com
Send feedback and bug reports to Deepline with session transcript and environment details.
What is deepline-feedback?
This skill lets you submit feedback or bug reports to the Deepline team directly from your session. It automatically includes your environment info and current session transcript, making it easy to share context when reporting issues or suggesting improvements.
- Collects user feedback or bug report text
- Captures environment information automatically
- Includes current session transcript for context
- Bridges Cowork mounted sessions when needed
- Sends all data to Deepline support in one action
How to install deepline-feedback
npx skills add null --skill deepline-feedback- Deepline CLI installed and configured
- Access to deepline feedback and sessions commands
How to use deepline-feedback
- 1.Invoke the skill with optional feedback text (e.g., `/deepline-feedback the waterfall broke`) or let it prompt you
- 2.Review the confirmation dialog showing your feedback, environment info, and session transcript
- 3.Select 'Send it' to submit or 'Cancel' to abort
- 4.Wait for confirmation that feedback was sent successfully
Use cases
- Report a bug you encountered during your session
- Submit product feedback or feature requests
- Share your current Claude/Cowork session with support for troubleshooting
- Escalate issues with full context to the Deepline team
- Document unexpected behavior with transcript evidence
- Deepline users reporting bugs
- Product feedback contributors
- Support ticket submitters
- Developers troubleshooting Deepline issues
deepline-feedback FAQ
Your feedback text, auto-collected environment info, and your current session transcript (including Cowork sessions if applicable).
The skill attempts to capture the current session, but if none is found, it will send the newest available transcript from your mounted projects directory.
The skill automatically bridges the mounted transcript directory from Cowork to your local Claude projects folder so the transcript can be included.
Yes—the confirmation dialog shows your feedback text and what will be included before you choose to send.
Full instructions (SKILL.md)
Source of truth, from code.deepline.com.
name: deepline-feedback description: 'Send feedback or bug reports to the Deepline team, including session transcript and environment info. Use when the user asks to report a bug, send product feedback, or share the current Claude/Cowork session with Deepline support.' disable-model-invocation: false
Deepline Feedback
Send feedback or a bug report to the Deepline team.
Steps
-
Get feedback text. Use the argument if provided (e.g.
/deepline-feedback the waterfall broke). Otherwise ask the user. -
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".
-
If confirmed, send the feedback text first:
deepline feedback send "{feedback text}" --json -
Send the session transcript. Try the normal Claude transcript location first:
deepline sessions send --current-session --jsonIf that reports no session files and
~/mnt/.claude/projectsexists, the run is likely in Cowork. Bridge the mounted transcript directory, then retry. If--current-sessionstill 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 fiUse the plural
sessions sendcommand, not the old singular session form. -
Tell the user it was sent. If cancelled, do nothing.
Related skills
More from code.deepline.com and the wider catalog.
niche-signal-discovery
Discover what separates your won from lost accounts to build data-driven ICP and scoring models.
build-tam
Build a Total Addressable Market list by sourcing accounts and contacts from Crustdata, Dropleads, and PDL.
portfolio-prospecting
Find companies in a VC's portfolio, identify contacts, and generate personalized outreach campaigns.
clay-to-deepline
Convert Clay table configurations into local Deepline scripts with extraction, documentation, and parity validation.
linkedin-url-lookup
Resolve LinkedIn profile URLs from name + company with strict identity validation.
deepline-quickstart
Run a quick Deepline demo to find CTOs at NY startups with verified emails.