AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Timeline Report (Journey Into…)

Turns your full claude-mem project timeline into a narrative "Journey Into [Project]" development-history report.

Data & AnalyticsIntermediate★ 90,139⑂ 7,846AI score 8/10Last updated: Aug 9, 2026

What it does

  • Resolves the claude-mem worker port (env → ~/.claude-mem/settings.json → per-UID default) and fetches the complete project timeline via /api/context/inject?full=true.
  • Estimates token cost up front and asks for confirmation when the timeline exceeds 100K tokens.
  • Spawns a subagent that writes a 3,000–6,000 word report with 10 required sections: genesis, architectural evolution, breakthroughs, work patterns, technical debt, debugging sagas, memory continuity, token economics/ROI, statistics, and lessons.
  • Runs ready-made SQL against ~/.claude-mem/claude-mem.db for quantitative metrics: top observations by discovery_tokens, monthly breakdown, explicit recall events.
  • Saves output to ./journey-into-PROJECT.md and reports date range, observation count, and token cost.
  • Detects git worktrees and switches to the parent repo name as the data source.

Who it's for

  • Developers already running claude-mem with a meaningful history of recorded sessions.
  • Tech leads who need retrospectives, onboarding docs, or release-note background material.
  • Anyone who wants hard numbers on the ROI of persistent AI memory.

Examples

  1. "Write a journey report for the tokyo project" → confirms ~34,722 observations (~718K tokens), then writes journey-into-tokyo.md.
  2. "Summarize the entire development history of this project" → uses the current directory basename (or parent repo in a worktree) to pull the timeline.
  3. Extract just the architectural-pivot and hard-bug sections into an internal wiki page for new hires.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/thedotmack/claude-mem/HEAD/plugin/skills/timeline-report/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the plugin/skills/timeline-report folder from the GitHub repo thedotmack/claude-mem into my ~/.claude/skills/timeline-report/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/thedotmack/claude-mem.git && mkdir -p ~/.claude/skills && cp -r claude-mem/plugin/skills/timeline-report ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Make sure claude-mem is installed and its worker is running — without recorded observations there is nothing to report on.
  2. Clone the repo: git clone https://github.com/thedotmack/claude-mem.git
  3. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r claude-mem/plugin/skills/timeline-report ~/.claude/skills/
  4. Verify curl, node, and sqlite3 are available (e.g. sqlite3 --version).
  5. If you changed the default port, set CLAUDE_MEM_WORKER_PORT in ~/.claude-mem/settings.json or as an environment variable.
  6. Restart Claude Code and ask: "Write a timeline report" or "Journey into <project>".
  7. Review the token estimate before approving, then open the generated ./journey-into-<project>.md.
View source on GitHub ↗License: Apache-2.0