OpenClaw / ClawLite Self-Improvement

Use this skill to turn mistakes, corrections, blockers, and better approaches into durable operating knowledge.

What problem this solves

• - log failures and learnings
• separate errors from feature requests
• run small eval-driven experiments on repeated failures
• promote important patterns into AGENTS.md / TOOLS.md / SOUL.md
• write operator notes into Obsidian vault
• support stricter acceptance via Karen / Mission Control

When to use

• - "make the agent improve itself"
• "capture learnings"
• "log mistakes so we do not repeat them"
• "record blockers / corrections / feature gaps"
• "build a self-improving OpenClaw workflow"
• "operationalize lessons learned"
• "test whether this new rule actually helps"
• "run an eval loop on this workflow/skill/SOP"
• "should we keep this new guardrail or discard it"

Files this skill uses

• - INLINECODE0
• INLINECODE1
• INLINECODE2
• INLINECODE3
• Obsidian vault note under INLINECODE4

Command examples

Categories

learning

• - user corrections
• better recurring workflows
• tool gotchas
• operational lessons

error

• - command failures
• integration failures
• runtime blockers
• broken release / deploy behavior

feature

• - missing capability requests
• operator workflow gaps
• recurring requests that deserve a build item

experiment

• - repeated failures that need a tested guardrail
• checklist/SOP/schema changes that should be validated before broad promotion
• keep/discard decisions on new operating rules
• binary eval loops for skills, workflows, receipts, summaries, or deploy closeout rules

Promotion targets

• - AGENTS.md → workflow / delegation / execution rules
• INLINECODE6 → tool gotchas, secrets locations, environment routing rules
• INLINECODE7 → behavior / communication / non-negotiable principles
• Obsidian vault → reusable operator log and content proof asset

Karen / Mission Control compatibility

• - Karen can reference learnings when repeated failures happen
• Mission Control can treat promoted learnings as new operating rules
• recurring blockers can be elevated from chat into tracked operational knowledge
• experiments can test whether a new summary contract, receipt rule, or deploy closeout guardrail actually reduced the failure pattern

Eval loop rule

1. 1. define 3-5 binary evals
2. record the baseline failure state
3. change one thing at a time
4. re-check the same evals
5. classify the change as keep / discard / partial_keep

Use {baseDir}/references/eval-loop.md for the experiment format and examples.

Output goal

• - a durable learning entry
• a durable error entry
• a durable feature request entry
• a durable experiment entry with binary evals
• a promoted rule in AGENTS.md / TOOLS.md / SOUL.md
• an Obsidian vault operations note

Important limits

• - Logging is not the same as fixing.
• Do not treat a learning entry as closure for a broken deliverable.
• Use this skill to reduce repeated mistakes, not to excuse them.
• This skill is local-only: it does not read credentials, does not modify system services, and does not make network requests.
• Promotion writes are limited to workspace files (AGENTS.md, TOOLS.md, SOUL.md) unless OBSIDIAN_LEARNINGS_DIR is explicitly set.

References

• - INLINECODE13
• INLINECODE14
• INLINECODE15
• INLINECODE16
• INLINECODE17

• - INLINECODE18
• INLINECODE19