← Back to Skills Marketplace
Willow System Health
by
Sean Campbell
· GitHub ↗
· v1.0.0
· MIT-0
70
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install willow-system-health
Description
Audit the Willow local AI stack for subsystem failures, drift, and resource bloat. Use when a user asks to check Willow health, diagnose a slow or broken Wil...
Usage Guidance
This skill appears to do exactly what it says: local health checks and guided cleanup for a Willow stack. Before installing or running it, note that it will: (1) probe local TCP ports and make HTTP requests to localhost (Ollama/MCP), (2) attempt Postgres connections using the default Willow DSN and may call pg_isready or import psycopg2, (3) run local commands like git and `python -m willow.cli`, and (4) can append entries to your agent memory if you have memory writes enabled. None of these actions contact remote endpoints outside the host, and destructive operations (git worktree remove, ollama rm, VACUUM) are gated by explicit confirmation in the SKILL.md. If you plan to run this skill, review the script (scripts/system_health.py), ensure you trust the local environment, and confirm any cleanup actions before proceeding.
Capability Analysis
Type: OpenClaw Skill
Name: willow-system-health
Version: 1.0.0
The willow-system-health skill is a diagnostic utility designed to audit a local AI stack. The Python script (system_health.py) performs read-only checks on local services (Postgres, Ollama, MCP), git worktrees, and file-based session stores to report on system drift and resource usage. While it uses subprocess calls and local network requests, all actions are scoped to the application's default local paths and ports (e.g., 127.0.0.1:11434), and the instructions in SKILL.md explicitly require user confirmation before any cleanup actions are performed.
Capability Assessment
Purpose & Capability
Name and description claim a local Willow system audit; the included script explicitly checks Postgres, Ollama, the MCP server, git worktrees, Willow CLI tasks, and store sizes — all directly relevant to the stated purpose. No unrelated cloud credentials or remote service keys are requested.
Instruction Scope
SKILL.md instructs the agent to run the included Python script and, optionally, append an entry to the user's memory. The script performs network probes to localhost services, runs local subprocesses (git, pg_isready, python -m willow.cli, psycopg2 via python -c), and reads repository and Willow store paths (default ~/.willow and ~/github/willow-1.9). These actions are within the audit scope but do access local files, sockets, and run commands with potentially elevated read access to local data; the SKILL.md requires explicit user confirmation before destructive actions.
Install Mechanism
No install spec is present; the skill is instruction-only with an included script. Nothing is downloaded from external URLs and no archives are extracted. This lowers install-time risk.
Credentials
The skill declares no required environment variables or credentials which is appropriate. The script uses an embedded default Postgres DSN (postgresql://willow:willow@localhost:5432/willow) and attempts to import/use psycopg2 and system binaries (git, pg_isready, willow CLI) if present. That is proportionate for a local Willow health check, but it does assume access to local DB credentials and filesystem paths (~/github/willow-1.9, ~/.willow) — users should be aware it will probe those locations.
Persistence & Privilege
always is false and model invocation is allowed (normal). SKILL.md says memory writes are conditional on the user's memory opt-in and are append-only to memory/YYYY-MM-DD.md. The skill does not request permanent always-on privilege or modification of other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install willow-system-health - After installation, invoke the skill by name or use
/willow-system-health - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of willow-system-health for auditing Willow's local AI stack:
- Audits Willow system health across boot, daily, and weekly tiers, reporting HEALTHY / WARN / CRITICAL status for each subsystem.
- Identifies issues with core services (Postgres, Ollama, MCP), orphaned forks, open tasks, store bloat, and more.
- Provides actionable recommendations and next steps for any WARN or CRITICAL flags detected.
- Supports user-triggered checks and tier selection (quick, daily, weekly, or all).
- Offers interactive cleanup actions (e.g., merge/delete orphaned forks, remove dead models) with user confirmation.
- Optionally appends summary results to memory logs when enabled.
Metadata
Frequently Asked Questions
What is Willow System Health?
Audit the Willow local AI stack for subsystem failures, drift, and resource bloat. Use when a user asks to check Willow health, diagnose a slow or broken Wil... It is an AI Agent Skill for Claude Code / OpenClaw, with 70 downloads so far.
How do I install Willow System Health?
Run "/install willow-system-health" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Willow System Health free?
Yes, Willow System Health is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Willow System Health support?
Willow System Health is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin).
Who created Willow System Health?
It is built and maintained by Sean Campbell (@rudi193-cmd); the current version is v1.0.0.
More Skills