OpenClaw Memory Doctor
v1.0.1Diagnose and fix OpenClaw memory problems fast, including missing recall, Dreaming not running, embedding provider errors, index drift, and promotion issues....
⭐ 0· 99·0 current·0 all-time
byVasiliy@vassiliylakhonin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description match the instructions: all steps focus on diagnosing and repairing OpenClaw memory/dreaming/indexing issues. One minor mismatch: the SKILL.md repeatedly runs the 'openclaw' CLI (and a '/dreaming status' command) but the registry metadata lists no required binaries — the skill assumes the platform has the OpenClaw CLI and repo files available but does not declare that dependency.
Instruction Scope
All runtime instructions stay within the memory/dreaming domain: run OpenClaw status/doctor/memory commands, inspect memory files (MEMORY.md, DREAMS.md), check agent config keys and schedules, run cautious fixes with verification. The instructions avoid broad, unrelated data collection and explicitly recommend read-only checks and confirmation before broad rewrites.
Install Mechanism
No install spec and no code files — lowest-risk model. The skill is instruction-only, so nothing will be downloaded or written by an installer.
Credentials
The skill requests no environment variables or credentials. SKILL.md notes checking 'API key/dependency readiness' (i.e., verify existing provider keys) but does not request or attempt to collect secrets — this is proportionate to its purpose.
Persistence & Privilege
always is false and there are no install-side persistence actions. The skill does not request to modify other skills or system-wide agent settings beyond performing diagnostic/fix commands described in its instructions.
Assessment
This is an instruction-only diagnostics skill and appears to do what it says. Before using it: ensure the OpenClaw CLI and relevant repository files (MEMORY.md, DREAMS.md, agent config) are present on the host where commands will run; review and approve any configuration-change commands the skill proposes (it says it will ask, but confirm interactively); avoid giving it direct access to secrets — it will check for API key readiness but does not need you to paste keys into the skill. If you plan to allow autonomous invocation, be comfortable with the agent running OpenClaw commands on your environment; otherwise run it manually or require explicit confirmations.Like a lobster shell, security has layers — review code before you run it.
dreaming-fixvk9701n4zjh0205zgdy1zjnp12x84j20xlatestvk973bdv3n44gmxqggd39m078pn84kwhpmemory-diagnosticsvk9701n4zjh0205zgdy1zjnp12x84j20xmemory-doctorvk9701n4zjh0205zgdy1zjnp12x84j20xmust-havevk9701n4zjh0205zgdy1zjnp12x84j20x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.