AI Log — AI skill for Claude Code
Write a brief activity log entry for the current session.
How to install AI Log
Installs to ~/.claude/commands/jennydove-self-improving-claude-ai-log.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/jennydove/self-improving-claude/HEAD/.claude/commands/ai-log.md -o ~/.claude/commands/jennydove-self-improving-claude-ai-log.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Log does
Write a brief activity log entry for the current session.
Run at the end of every session via `/done`. Skip only if the session was a single quick question with no changes made.
Process
**Review the session** and draft a log entry covering:
- What was built or changed (3–5 bullet points)
- Key decisions made and why
- Follow-ups identified (anything started but not finished)
**Write the entry** to `ai-log/YYYY-MM-DD — [Short description].md`
- Create the
ai-log/direct
- Create the
Alternatives in AI
- Upstream Watch — Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict 361 ★
- Skillz macOS — Browse and manage local AI skills, MCP configs, plugins, and agent activity on macOS 14+ 133 ★
- Aar Loop — Run an After Action Review after any AI session and write concrete lessons so your agent stops repeating mista 78 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Sth Log
Record a changelog entry. AI auto-infers change type (Feature / Fix / Refactor / Docs / Breaking) and computes
Log Failure
Record an AI mistake in the fixed format — in the current ticket's plan and, if it generalises, in the repo-wi
Journal Recorder Agent
Auto-journal for Claude Code & Codex — every AI coding session becomes a rich markdown journal entry: per proj
Work Init
Set up, repair, or upgrade the work-management model in this repository — write the manifest, scaffold the wor
Goal Monitor
Enforces Law 2 (Plan Is Sacred) of the 7 Laws of AI Agent Discipline. Detects when a session has drifted away
Asynq Agentd
An open-source daemon that keeps your AI coding agents (Claude Code, Codex, OpenCode) running 24/7 on any alwa
Related Agents
Session Reflector
Generate an end-of-session reflection by reviewing what happened — ops log, thread changes, new observations —
Sdlc Handoff
Closes out the current session — reads every artifact touched, appends a PROGRESS.md entry, prints a recap. St
Stage Session
A lifecycle stage session dispatched by the iteration lead (lifecycle-kit/templates/lead.md). Runs exactly one