ClawHub

Autodream Claw

v1.0.0

Memory consolidation skill that replicates Anthropic's Auto Dream feature. Runs a 4-phase reflective pass over memory files: Orient → Gather → Merge → Prune....

⭐ 0· 26·0 current·0 all-time
by@brasco05
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 (Auto Dream memory consolidation) match the actions in SKILL.md: scanning memory/, gathering recent logs, merging/pruning memories and updating an index. Commands referenced (ls, cat, grep, git log, wc) are coherent with that purpose.
ℹ
Instruction Scope
Instructions explicitly tell the agent to read and modify memory files (INDEX, topic files) and run git log and simple shell commands. This is appropriate for consolidation but is potentially destructive (merge/delete/prune). The SKILL.md includes good rules (e.g., don't leak secrets, be idempotent) but does not enforce backups or require user confirmation before deletions—recommend adding explicit backup and review steps.
✓
Install Mechanism
This is instruction-only with no install spec or downloaded code. No binaries or external packages are pulled, so there is no installation risk.
✓
Credentials
No environment variables, credentials, or config paths are requested. The skill operates on local workspace files, which is proportionate to its stated function.
ℹ
Persistence & Privilege
always:false and no special privileges requested. However, the skill modifies user files and may be invoked automatically by daily-reflection per the README; automatic modification of memories warrants caution (backups, dry-run mode, or requiring confirmation). Autonomous invocation is allowed by default but is not excessive here.
Assessment
This skill appears to do what it says: read and consolidate your workspace memory files. Before installing, back up your memory/ directory (or ensure it's under git) and prefer running it manually the first few times to inspect its output. Ask the author or add a dry-run/confirm step to avoid unintended deletions. If you use daily-reflection automation, decide whether you want auto-pruning enabled or prefer manual approval.

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

latestvk97d4bb1rvn4x5hae0b67k7r2584ap99

License

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

Runtime requirements

🌙 Clawdis

Comments