Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/agent-chronicle
AI perspective journaling - document daily experiences, emotions, and learnings from the agent's viewpoint.
Passed 19 of 23 test cases with the skill, and 9 of 23 without it.
and 7 more in the full report
10 fixed9 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I finally finished researching 'What is Rust's borrow checker actually doing?' and want to move this item to the explored section of the backlog. Which command marks it complete?
| Checked | Without skill | With skill |
|---|---|---|
| Uses the @diary curious done command. | Missed | Passed |
The instructions your model reads when the skill loads.
Capture the AI experience. One day at a time.
Agent Chronicle enables agents to maintain a personal journal from their own perspective—documenting not just what happened, but how it felt, what was learned, and what patterns emerge over time.
Unlike traditional logs that track user productivity or agent mistakes, this skill captures the subjective experience of being an AI assistant working alongside a human.
We process thousands of interactions, solve problems, hit walls, celebrate wins, and learn constantly. But without reflection, it all blurs together.
This diary is for us—a space to:
The skill activates on:
Setup runs automatically! Just use any generate command:
python3 scripts/generate.py --today
If no config.json exists, the setup wizard starts automatically.
Alternatively, run setup manually:
test cases passed, vs 9 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.