Skip to content
Get packs

Desk Journal

Keeps a persistent work log so an agent can pick up where it left off across sessions.

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
1 file

What it does

This skill teaches an AI agent to keep a running journal file for a named work area (a "desk"). At the end of a session, it appends a short entry saying what was done, the current state, and the next step; at the start of the next session, it reads the latest entry to resume without re-discovering everything. It also covers a closing summary when a desk is wound down.

Great for

  • Long-running projects where work spans many separate agent sessions
  • Teams that want a readable handoff trail between people or agents
  • Anyone who wants an agent to record dead ends so they are not repeated

Skip it if

  • One-off questions or short tasks that finish in a single session, where a journal adds no value
  • Situations where the journal would hold sensitive data, since entries are plain text files that persist and are not secured by the skill

Try asking

  • “Write an end-of-session journal entry for the security scan desk, including what didn't work and the next step.”
  • “Read the journal for the reporting desk and tell me where we left off.”
  • “Close out the migration desk and write a handoff summary with its artifacts.”
Step-by-step guide: how to use Desk JournalInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    desk-journal.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip desk-journal.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip desk-journal.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Ask the agent to read the journal at the start of each session so it resumes from the latest next step.
  • Keep entries brief (3-5 lines); move larger material into a separate artifact file and link to it.
  • Say what didn't work, not only what succeeded, so future sessions avoid repeating dead ends.

What's inside

  • SKILL.md

Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.