ClawHub

Agent Chronicle

v0.7.2

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archae...

⭐ 4· 4.3k·9 current·9 all-time
byRobby@robbyczgw-cla
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (agent diary, analytics, export) align with the shipped scripts and templates: generation, analysis, digest, and export scripts operate on a local diary directory. Required binary (python3) and file operations are proportional to the stated purpose.
✓
Instruction Scope
SKILL.md and the scripts confine actions to generating, analyzing, exporting, and storing diary markdown files under a workspace 'memory/diary' path. The recommended sub-agent pattern (sessions_spawn) and CLI flows are explicit and scoped to generating diary text. The code does read/write local diary and related index files (quotes.md, curiosity.md, etc.), which is expected for a journaling skill.
✓
Install Mechanism
There is no remote install step or downloader in the manifest; this is distributed as code files that run under python3. Dependencies for optional export features (pandoc, weasyprint, Python markdown) are called at runtime and documented; that is normal for local tooling and not unexpected here.
ℹ
Credentials
The skill requires no secret environment variables or credentials. It will read OPENCLAW_WORKSPACE or AGENT_WORKSPACE environment variables (if present) to locate the workspace; these are platform/environment variables rather than secrets and are reasonable for locating agent memory. No unrelated cloud keys or tokens are requested. Users should note that memory integration can be enabled to automatically append summaries into the agent's daily memory files—this increases how much agent data the skill writes.
✓
Persistence & Privilege
always is false; skill runs only when invoked. It writes diary files under a workspace-local memory directory and can be configured for cron auto-generation, which is within scope for a diary tool. It does not alter other skills' configs or request permanent elevated platform privileges.
Assessment
This skill appears to do what it says: generate and manage agent diary entries locally. Before installing, consider: 1) Privacy: diary entries are stored under memory/diary/ and (optionally) appended into the agent's main daily memory — if you don't want persistent logs, set privacy_level to 'private' and disable memory_integration/auto_generate. 2) Exports: PDF/HTML export requires external tools (pandoc, texlive/xelatex) or Python libraries (weasyprint, markdown); these run subprocesses and may fetch remote CSS when exporting HTML (the export script references a CDN CSS URL). 3) Sub-agent workflow: generation uses sessions_spawn (OpenClaw sub-agents) — review that integration if you want to restrict autonomous spawning. 4) Review config.json and run setup interactively to choose storage paths and features. If you need any of the above behaviors restricted (auto-generation, memory appending, remote asset fetching), adjust config.json or disable optional features before use.

Like a lobster shell, security has layers — review code before you run it.

latestvk974aevm4nwaasb48gmnhxjycn83qw6c

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

Binspython3

Comments