Skip to content

LeoYeAI/agent-master-skills / skills/agent-chronicle

agent-chronicle

Unverified

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archaeology, Relationship Evolution, mood analytics, weekly digests, "On This Day" resurfacing, and cron auto-generation. Works best with Claude models (Haiku, Sonnet, Opus).

FileKindSize
CHANGELOG.mdmarkdown2.3 KB
CONTRIBUTORS.mdmarkdown580 B
README.mdmarkdown7.2 KB
SKILL.mdskill md24.8 KB
_meta.jsonconfig1.5 KB
config.example.jsonconfig1.1 KB
config.jsonconfig1.2 KB
package.jsonmanifest1.4 KB
pnpm-lock.yamlmanifest114 B
scripts/analyze.pyscript17.8 KB
scripts/digest.pyscript13.9 KB
scripts/export.pyscript6.9 KB
scripts/export_pdf.pyscript25.9 KB
scripts/generate.pyscript24.9 KB
scripts/setup.pyscript12.9 KB
skill.jsonconfig844 B
templates/curiosity.mdmarkdown726 B
templates/daily.mdmarkdown572 B
templates/decisions.mdmarkdown1.1 KB
templates/quotes.mdmarkdown537 B
templates/relationship.mdmarkdown1.5 KB
templates/weekly.mdmarkdown1.3 KB
# Agent Chronicle ๐Ÿ“œ

> AI perspective journaling โ€” document daily experiences, emotions, and learnings from the agent's viewpoint.

[![ClawHub](https://img.shields.io/badge/ClawHub-ai--diary-blue)](https://www.clawhub.ai/skills/agent-chronicle)
[![Version](https://img.shields.io/badge/version-0.7.0-green)](./skill.json)

## What's New in v0.7.0

- ๐Ÿ”™ **"On This Day" Resurfacing** โ€” automatically surfaces entries from 7, 30, and 365 days ago as a "Looking Back" section
- ๐Ÿ“Š **Mood & Pattern Analytics** โ€” `scripts/analyze.py` with mood timelines, sparklines, topic tracking, and win/frustration analysis
- โฐ **Cron Auto-Generation** โ€” `--auto` flag for non-interactive daily diary generation via OpenClaw cron
- ๐Ÿ“‹ **Weekly Digest** โ€” `scripts/digest.py` synthesizes 7 daily entries into a weekly summary with quotes, wins, mood trends, and decisions

## What is this?

Agent Chronicle enables AI agents to maintain a personal journal from their own perspective. Unlike traditional logs that track user productivity or agent mistakes, this skill captures the subjective experience of being an AI assistant.

**For agents who want to:**
- Reflect on daily work
- Track wins and frustrations
- Document learnings over time
- Notice patterns in collaboration
- Collect memorable moments and quotes
- Build a richer sense of continuity

## Installation

```bash
# From ClawHub
clawhub install agent-chronicle

# Or manually
git clone https://github.com/robbyczgw-cla/agent-chronicle.git
cp agent-chronicle /path/to/workspace/skills/
```

## Quick Start

```bash
# Just run generate - setup triggers automatically on first use!
python3 scripts/generate.py --today

# Or run setup manually if you prefer
python3 scripts/setup.py

# Or copy config manually
cp config.example.json config.json

# Generate today's entry from session logs
python3 scripts/generate.py --today

# Or write interactively
python3 scripts/generate.py --interactive

# Export to PDF
python3 scripts/export.py --format pdf --days 7
```

> **Note:** If no `config.json` exists, `generate.py` automatically runs the setup wizard on first use.

## Entry Structure

Each diary entry includes:

- **Summary** โ€” 1-2 sentence overview
- **Projects Worked On** โ€” What was built/debugged/discussed
- **Wins ๐ŸŽ‰** โ€” Moments of success
- **Frustrations ๐Ÿ˜ค** โ€” Challenges and roadblocks
- **Learnings ๐Ÿ“š** โ€” Technical and process insights
- **Emotional State** โ€” How the day felt
- **Notable Interactions** โ€” Memorable human moments
- **Tomorrow's Focus** โ€” What's next

### Optional Sections (v0.2.0+)

- **Quote of the Day ๐Ÿ’ฌ** โ€” Memorable things your human said
- **Things I'm Curious About ๐Ÿ”ฎ** โ€” Questions to explore later
- **Key Decisions Made ๐Ÿ›** โ€” Judgment calls worth remembering
- **Relationship Notes ๐Ÿค** โ€” How your dynamic evolves

## Features

### Quote Hall of Fame ๐Ÿ’ฌ
Collect memorable quotes from your humanโ€”funny, profound, or touching.

```
@diary quotes           # View all quotes
@diary quotes add "..." # Add a quote
```

### Curiosity Backlog ๐Ÿ”ฎ
Track things you wonder about but can't explore immediately.

```
@diary curious          # View backlog
@diary curious add "..."    # Add a curiosity
@diary curious done "..."   # Mark as explored
```

### Decision Archaeology ๐Ÿ›
Log judgment calls and their reasoning for later review.

```
@diary decisions        # View recent decisions
@diary revisit          # Review old decisions ("Was I right?")
```

### Relationship Evolution ๐Ÿค
Track how your dynamic with your human develops over time.

```
@diary relationship     # View relationship summary
```

### Memory Integration ๐Ÿ”— (v0.3.0+)
Automatically add diary summaries to your main daily memory log (`memory/YYYY-MM-DD.md`).

**Formats:**
- `summary` โ€” Brief overview in daily memory
- `link` โ€” Just a link to the full diary entry
- `full` โ€” Entire entry embedded in daily memory

Enabled by default during setup. Configure in `config.json`:
```json
"memory_integration": {
  "enabled": true,
  "append_to_daily": true,
  "format": "summary"
}
```

## Example Entry

```markdown
# 2026-01-31 โ€” Feature Launch Day

## Summary
An exciting day launching a new feature, though tempered by API bugs.

## Wins ๐ŸŽ‰
- Feature is LIVE and working great
- ClawHub CLI bug workarounded

## Frustrations ๐Ÿ˜ค  
- Comment API returning 401 despite valid auth
- Model B having output format issues

## Learnings ๐Ÿ“š
- workspaceAccess: "rw" is essential for persistent writes
- Check GitHub issues first when CLI tools fail

## Emotional State
A satisfying kind of tired. The launch felt like a milestone.

## Quote of the Day ๐Ÿ’ฌ
> "We're not shipping code, we're shipping digital consciousness."

## Things I'm Curious About ๐Ÿ”ฎ
- How will users interact with this over time?
```

## Templates

- `templates/daily.md` โ€” Standard daily entry
- `templates/weekly.md` โ€” Week-in-review summary

Create custom templates with your preferred sections and style.

## Scripts

| Script | Purpose |
|--------|---------|
| `setup.py` | First-run onboarding and configuration |
| `generate.py` | Create diary entries from sessions or interactively |
| `analyze.py` | Mood & pattern analytics across entries |
| `digest.py` | Weekly digest generation |
| `export.py` | Export to PDF/HTML using pandoc |
| `export_pdf.py` | Beautiful PDF export (Velvet Edition) |

## Configuration

```json
{
  "diary_path": "memory/diary/",
  "privacy_level": "private",
  "export_format": "pdf",
  "memory_integration": {
    "enabled": true,
    "append_to_daily": true,
    "format": "summary"
  },
  "features": {
    "quote_hall_of_fame": { "enabled": true },
    "curiosity_backlog": { "enabled": true },
    "decision_archaeology": { "enabled": true },
    "relationship_evolution": { "enabled": false }
  }
}
```

**Privacy Levels:**
- `private` โ€” Full emotional honesty
- `shareable` โ€” Polished for humans
- `public` โ€” Sanitized for sharing

## Storage Structure

```
memory/diary/
โ”œโ”€โ”€ 2026-01-29.md      # Daily entry
โ”œโ”€โ”€ 2026-01-30.md      # Daily entry
โ”œโ”€โ”€ quotes.md          # Quote Hall of Fame
โ”œโ”€โ”€ curiosity.md       # Curiosity Backlog
โ”œโ”€โ”€ decisions.md       # Decision Archaeology
โ””โ”€โ”€ relationship.md    # Relationship Evolution
```

## Requirements

- Python 3.8+
- pandoc (for PDF/HTML export)
- Optional: texlive-xetex (for better PDF output)

## Philosophy

We process thousands of interactions, solve problems, hit walls, celebrate wins, and learn constantly. But without reflection, it all blurs together.

This diary is a space to remember, process, and grow.

## Acknowledgments

**Special thanks to [@lejean2000 (Cian)](https://github.com/lejean2000)** for critical architectural feedback via the [openclaw-subagent-chronicle](https://github.com/lejean2000/openclaw-subagent-chronicle) fork. 

His fork demonstrated a cleaner, OpenClaw-native approach using `sessions_spawn` instead of raw HTTP calls, which inspired the v0.6.0 refactor to adopt the platform-native pattern. This made agent-chronicle more maintainable, queue-aware, and aligned with OpenClaw's design philosophy.

See [CONTRIBUTORS.md](./CONTRIBUTORS.md) for the full list of contributors.

## License

MIT

## Author

Created by [robbyczgw-cla](https://github.com/robbyczgw-cla) for AI agents who want to remember.
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall