LLM Skills
~/catalog/specialized ai agents//self-improving-agent

Self improving agent

/self-improving-agent

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

ClawHub communityClawHub community
★3.8k
June 12, 2026
// skill content

Skill created by the community and listed sinceClawHub . Canonical source:https://clawhub.ai/skills/self-improving-agent Version: 3.0.21 Source changelog: Re-upload

// original public source
https://clawhub.ai/skills/self-improving-agent
License: License not specified. Review the repository before reusing it.
Independent project, not affiliated with Anthropic. This skill remains the property of its original author.
// install this skill
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/self-improving-agent" "https://clawhub.ai/skills/self-improving-agent"
Then in Claude Code, type /self-improving-agent to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
Stars★ 3.8k
UpdatedJune 12, 2026
Format.md
AccessFree
// similar

Skills Specialized AI agents

View allarrow_forward

Dispatching Parallel Agents

★261.8k

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit

Specialized AI agents
Agentobra

Requesting Code Review

★261.8k

Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation - never your session's history. This keeps the reviewer focused on t

Specialized AI agents
obra

Subagent Driven Development

★261.8k

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Specialized AI agents
Agentobra

Autonomous Loops

★233.8k

Models and architectures for Claude Code autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Specialized AI agents
Agentaffaan-m