Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Timeline Report (Journey Into)

Turns your project's full claude-mem observation history into a narrative "Journey Into [Project]" report.

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

What it does

Pulls the complete observation timeline that the claude-mem persistent-memory plugin recorded for a project and turns it into a long-form technical narrative.

  • Resolves the claude-mem worker port automatically (env var → settings.json → per-UID default) and detects git worktrees so it reads the parent repo's data.
  • Fetches the full timeline, estimates token cost up front, and asks for confirmation above 100K tokens.
  • Dispatches a subagent that writes a 3,000–6,000 word report with 10 sections: genesis, architectural evolution, breakthroughs, work patterns, technical debt, debugging sagas, memory/continuity, token economics & memory ROI, statistics, and lessons.
  • Includes ready-made SQL against ~/.claude-mem/claude-mem.db for monthly token breakdowns and the top-5 most expensive memories.
  • Saves the result to ./journey-into-PROJECT.md and reports date range, observation count and token cost.

Who it's for

  • Developers already running claude-mem with months of accumulated observations.
  • Team leads who need retrospectives or end-of-sprint history documents.
  • Anyone onboarding new contributors who must explain why the codebase looks the way it does.
  • Users who want hard numbers on how much re-work persistent memory prevented.

Examples

  1. Quarterly retrospective: "Write a journey report for the tokyo project" → analyzes ~34K observations and highlights architectural pivots and the longest debugging sessions.
  2. Onboarding doc: generate a project-history brief that links early design decisions to their later consequences.
  3. Memory ROI report: query the SQLite DB directly to produce a monthly discovery-token table plus the five highest-value memories.

· · · Install guide · · ·

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 Claude 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 /tmp/claude-mem && mkdir -p ~/.claude/skills && cp -r /tmp/claude-mem/plugin/skills/timeline-report ~/.claude/skills/

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

  1. Make sure the claude-mem plugin is installed and its worker is running — this skill has no data source without it.
  2. Open a terminal and clone the repo: git clone https://github.com/thedotmack/claude-mem.git
  3. Copy the skill into your skills folder: mkdir -p ~/.claude/skills && cp -r claude-mem/plugin/skills/timeline-report ~/.claude/skills/
  4. Verify that ~/.claude/skills/timeline-report/SKILL.md exists.
  5. Install sqlite3 if missing (needed for the token-economics section): built in on macOS, sudo apt install sqlite3 on Ubuntu.
  6. Restart Claude Code and ask for "a timeline report" or "Journey into <project>".
  7. For large projects the input can reach hundreds of thousands of tokens — review the printed estimate before confirming.
View source on GitHub ↗License: Apache-2.0