← Back to Skills Marketplace
164
Downloads
0
Stars
17
Active Installs
1
Versions
Install in OpenClaw
/install self-improving-agent-3-0-5
Description
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Usage Guidance
This skill appears to do what it says: it provides templates, a lightweight activator reminder, an error detector that watches tool output, and a helper to scaffold extracted skills. Before installing or enabling hooks: 1) Review the scripts (activator.sh, error-detector.sh, extract-skill.sh) to confirm you’re comfortable with their behavior; they do not exfiltrate data but do read runtime tool output and may encourage logging of command outputs to .learnings. 2) Prefer project-level (per-repo) hook configuration rather than user-global (~/.claude or ~/.openclaw) if you want to avoid injecting reminders across all sessions. 3) Check file permissions and ensure .learnings doesn't inadvertently store sensitive output (secrets, full stack traces) — treat it like a log. 4) If you enable the hook, test in a sandbox project first (or use the scripts' --dry-run where available). 5) If you have privacy or compliance concerns about storing tool outputs, do not enable PostToolUse hooks that automatically examine CLAUDE_TOOL_OUTPUT.
Capability Analysis
Type: OpenClaw Skill
Name: self-improving-agent-3-0-5
Version: 1.0.0
The skill bundle implements a 'self-improvement' framework that allows an AI agent to log errors, user corrections, and new insights into a local `.learnings/` directory. It includes bash scripts (`activator.sh`, `error-detector.sh`) and OpenClaw hooks (`handler.js`) designed to inject reminders into the agent's context, encouraging it to document its performance. The `extract-skill.sh` utility provides a safe way to scaffold new skill templates with built-in protections against directory traversal. The logic is transparently aimed at improving agent reliability and project memory without any evidence of data exfiltration or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description (capture learnings, log errors, promote learnings) align with the included files: reminders, logging templates, hook handlers, activator and error-detection scripts, and a helper to extract skills. No environment variables, credentials, or binaries are requested that would be unrelated to logging and hook-based reminders.
Instruction Scope
Runtime instructions and scripts perform the expected scoped tasks: creating .learnings files, emitting reminder text, detecting error output, and scaffolding new skills. The error-detector script reads CLAUDE_TOOL_OUTPUT (a runtime-provided env var) to detect errors — that is proportionate to 'detect command failures', but you should be aware that learnings may reference command output and file paths. The hooks inject a virtual bootstrap file into session context; this is intended, but installing globally will surface the content across sessions.
Install Mechanism
No install spec (instruction-only plus included scripts). The SKILL.md suggests cloning from a GitHub repo or using clawdhub; there are no remote downloads or archive extracts in the package itself. The helper scripts are local and include safeguards (extract-skill.sh refuses absolute paths or '..').
Credentials
The skill declares no required env vars or credentials. The scripts rely on runtime context: CLAUDE_TOOL_OUTPUT (read-only) and event/session fields provided by OpenClaw hooks — these are relevant to error detection and hook handling. No unrelated secrets or broad environment access are requested.
Persistence & Privilege
always:false and model invocation is allowed (default). The skill offers optional hooks that the user must enable; enabling hooks and copying files to ~/.openclaw/hooks or ~/.openclaw/workspace gives it persistent presence across sessions (intentional for a workspace-level learning system). This is expected but you should opt for project-level configuration if you don't want global persistence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install self-improving-agent-3-0-5 - After installation, invoke the skill by name or use
/self-improving-agent-3-0-5 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the self-improving-agent skill for OpenClaw and other agent environments.
- Provides structured markdown logging for learnings, errors, and feature requests to enable continuous improvement.
- Includes detailed templates and workflow recommendations for capturing corrections, failures, knowledge gaps, and user feedback.
- Outlines promotion process for learnings to project memory files (e.g., CLAUDE.md, AGENTS.md, TOOLS.md).
- Compatible with OpenClaw: supports workspace setup, session sharing tools, and optional hooks.
- Offers generic guidance for integrating with other AI agents (Copilot, Claude Code, etc.).
- Defines standardized ID generation, resolution tracking, and status management for all learnings.
Metadata
Frequently Asked Questions
What is Self Improving Agent 3.0.5?
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau... It is an AI Agent Skill for Claude Code / OpenClaw, with 164 downloads so far.
How do I install Self Improving Agent 3.0.5?
Run "/install self-improving-agent-3-0-5" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Self Improving Agent 3.0.5 free?
Yes, Self Improving Agent 3.0.5 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Self Improving Agent 3.0.5 support?
Self Improving Agent 3.0.5 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Self Improving Agent 3.0.5?
It is built and maintained by mutsunico (@mutsunico); the current version is v1.0.0.
More Skills