Skip to main content
skill CX Codex

self-improving-agent · borghei — Claude Code skill: what it does, how to install

self-improving-agent — a skill for Claude Code, Codex, and Cursor that curates long-term agent memory. Converts repeated task outcomes into reviewed project rules.

LicenseRef-MIT-Commons-Clause 244 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill self-improving-agent -a claude-code
Open on GitHub

What self-improving-agent does

Runs across Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It monitors outcomes across development sessions, structures takeaways, and detects repeated patterns via pattern_extractor.py and feedback_analyzer.py.

The improvement cycle separates recording learnings, isolating recurring patterns, proposing rule updates, and auditing memory hygiene. Promoting an entry into CLAUDE.md or .claude/rules/ is strictly gated: rule_promoter.py tests recurrence criteria and waits for manual user approval before altering configuration.

Running the included tools requires Python 3. The rule_promoter.py script applies automated edits exclusively to section-based MEMORY.md files; index-based layouts pointing to standalone topic files require manual promotion.

What it helps with

  • detect broken topic pointers and line bloat in MEMORY.md
  • isolate recurring failure patterns from session logs
  • stage verified guidelines before editing CLAUDE.md
  • measure performance drops after updating rules

Example prompts for the agent

  • Run a health audit on ./MEMORY.md
  • Extract recurring error patterns from sessions.jsonl
  • Review promotion candidates for project rules

How to install self-improving-agent

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill self-improving-agent -a claude-code

2Manually: put the files in place

~/.claude/skills/self-improving-agent/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/self-improving-agent/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about self-improving-agent

How to install self-improving-agent in Claude Code?

Run npx skills add borghei/Claude-Skills --skill self-improving-agent -a claude-code in your terminal.

What does self-improving-agent do?

It reviews agent memory health, extracts repetitive lessons from logs, and guides promotion of proven behaviors into permanent instructions.

Can it promote rules without human review?

No, rules impact all future runs, so the promoter prints dry-run diffs and requires explicit confirmation before applying changes.

Similar skills

All skills for Agent setup: memory, context, orchestration →

self-improving-agent by other authors comes first.

self-improving-agent Alireza Rezvani self-improving-agent — a Claude Code skill that curates the agent's auto-memory into project rules. Reviews MEMORY.md, promotes proven patterns into CLAUDE.md or .claude/rules/, and turns recurring fixes into skills. CX Codex +1 1,078installs self-improving-agent zhaono1 self-improving-agent turns workflow failures, corrections, and workarounds into auditable rules for agents. Prevents blind instruction rewrites by requiring executable proof first. CX Codex +1 35,900installs self-improving-agent pskoett The self-improving-agent skill keeps a markdown log of agent errors, corrections and findings so useful fixes survive between sessions. CX Codex +1 408installs self-improving-agent Grail-Computer self-improving-agent teaches an agent to diagnose friction, update project guardrails in AGENTS.md, and turn repeated multi-step workflows into standalone skills. CX Codex +1 520installs self-improving-agent jdrhyne self-improving-agent keeps a small journal in .learnings/ with failures, user corrections and missing-capability requests, then reads it back before big jobs. CX Codex +1 ★ 239repo stars evo-memory EvoScientist evo-memory keeps what you learned between research cycles: which directions paid off, which failed, and which training strategies are worth reusing. CX Codex +1 401installs self-improvement pskoett self-improvement keeps your corrections, failed commands and feature asks in markdown files so the agent can turn repeated lessons into project rules. CX Codex +1 2,100installs self-learning kulaxyz self-learning is a Claude Code skill that captures a working route from the current session as a reusable skill, so the next session already knows it. CX Codex +1 889installs self-reflection sundial-org self-reflection stores mistakes and operational lessons in local markdown memory so the agent avoids repeated failures. CX Codex +1 162installs claude-self-reflect ramakay claude-self-reflect stores Claude Code conversation history locally and retrieves past context with sub-millisecond vector search. Keeps your decisions and task state across multiple sessions. ★ 231repo stars thinking-systems tjboudreaux thinking-systems — a skill for problems that resist local fixes: it maps the system, finds feedback loops and delays, then ranks interventions by leverage. CX Codex +1 708installs

From the same set120

The whole set →
design-system-lead design-system-lead guides agents through building multi-tier design tokens, component architecture, and cross-platform export pipelines. CX Codex +1 262installs cmo-advisor cmo-advisor guides marketing strategy, demand generation, lead scoring, and revenue alignment. Use it when a plan needs clear inputs, channels, and metrics. CX Codex +1 261installs program-manager program-manager — a skill for Claude Code coordinates programs spanning multiple projects. It builds charters, maps dependencies, tracks benefits, and prepares steering updates. CX Codex +1 259installs senior-architect senior-architect — a skill for designing systems and documenting architecture decisions as ADRs. Analyzes code coupling, generates diagrams, and guides choices between patterns, databases, and monolith versus microservices. CX Codex +1 244installs seo-specialist The seo-specialist skill guides technical SEO audits, keyword research, and on-page improvements. Use it to investigate a site or review organic search performance. CX Codex +1 244installs senior-prompt-engineer senior-prompt-engineer — a skill for Claude Code that reviews prompt architecture, scores RAG quality, and diagrams agent workflows. Flags redundant instructions and missing output contracts during prompt tuning. CX Codex +1 239installs senior-qa senior-qa — a skill for Claude Code and five other platforms that structures test suites for React and Next.js apps. Scaffolds Jest unit tests, Playwright specs, and inspects coverage reports. CX Codex +1 232installs senior-devops senior-devops is a Claude Code skill that generates CI/CD pipelines, Docker images, and Terraform infrastructure, selects deployment strategies, and orchestrates rollbacks. CX Codex +1 209installs

Project sponsors

Companies that keep this analytics open