AB mind-wander
Background reasoning agent that autonomously explores open questions using a local LLM (Qwen3.5-9B), a private knowledge graph for dead-end tracking, and Perplexity web search. Fires on a schedule, picks one unresolved question from ON_YOUR_MIND.md, runs sandbox experiments and web searches, and writes findings to MENTAL_EXPLORATION.md only when genuinely novel — mirroring hippocampal background consolidation. Uses a separate FalkorDB 'wander' graph so exploration history never pollutes the primary agent context. Use when: setting up autonomous background research for an OpenClaw agent, exploring research questions without consuming primary LLM token budget, building training data from exploratory reasoning sessions, or tracking dead ends to avoid re-exploration. Triggers on: "mind wander", "background reasoning", "autonomous research", "wander agent", "ON_YOUR_MIND", "MENTAL_EXPLORATION", "dead ends", "explore while I sleep".
As a process B 66/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 959 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 940: 120–800 characters recommended
- -35 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 8 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.