79 tagged self-improvement, measured the same way as everything else here.
Browse within: self-improving-ai 35self-improving-agent 22self-learning 22meta 9core 6opencode 6opencode-ai 6opencode-skills 6powerhouse 6initialization 5recursive-self-improvement 5upgrade 5
Skill Claude CodeCodex
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.
Skill Claude CodeCodex
FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.
Skill Claude CodeCodex
Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does…
Skill Claude CodeCodex
Rigorous code review of all uncommitted changes. Analyzes architecture, code quality, security, and engineering best practices. Embeds questions and assumptions inline, then summarizes all proposed changes as a plan for user approval before any edits are made.
Skill Claude CodeCodex
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
Skill Claude CodeCodex
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
Skill Claude CodeCodex
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
Skill Claude CodeCodex
Use when preparing training data.
Skill Claude CodeCodex
Use when evaluating a model on the current benchmark(s).
Skill Claude CodeCodex
Use when appending an experiment log entry after a completed iteration.
Skill Claude CodeCodex
Learn from experience: self-reflection + self-criticism + self-learning + self-organizing memory + cross-session sync. Agent evaluates its own work, catches mistakes, and improves permanently. Compiles confirmed learnings to global config for automatic cross-session persistence. Use when (1) a command, tool, API, or…
Skill Claude CodeCodex
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
Skill Claude CodeCodex
A Chinese-language guide to AI research papers from paper.mulanai.com, including daily selections, weekly reports, topic categories, summaries, and reasons for recommendations. Its interfaces are anonymous and read-only, with no API key required.
Skill Claude CodeCodex
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes…
Skill Claude CodeCodex
Use when the user wants to create, improve, evaluate, inspect, run, schedule, automate, or export Skill RSI projects or Agent Skill improvement loops. In Codex desktop, every Skill RSI invocation must open the local Skill RSI web app/sidebar first.
Skill Claude CodeCodex
A tool for evaluating and improving other coding-agent skills through benchmarks, adversarial tests, and repeated improvement cycles.
bokan/claude-skill-self-improvement
Skill Claude CodeCodex
Analyze conversation history to find friction patterns and suggest CLAUDE.md/skill improvements. Use when user wants to review what went wrong across sessions and systematically improve. (user).
Skill Claude CodeCodex
Use after meaningful instruction changes; replay behavior, test controls, and independently verify improvement.
Skill Claude CodeCodex
A record of whether external command-line tools and services are currently available, along with the result of their latest check.
Skill Claude CodeCodex
A strategy for extracting readable content from web pages, including pages that need JavaScript to load or resist automated access.
Skill Claude CodeCodex
A set of instructions for searching the internet and choosing among available search methods. It covers direct web pages, built-in search, external search services, and a fallback search engine.
Skill Claude CodeCodex
Run a decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) that peer-review anonymously and synthesize a verdict. Trigger on 'council this', 'pressure-test this', 'war room this', or any high-stakes either/or choice. Skip for factual lookups, summaries, or simple…
Skill Claude CodeCodex
Convert multi-format documents (PDF, DOCX, PPTX, XLSX, images, audio, video, HTML, ZIP) into token-efficient Markdown using Microsoft MarkItDown for LLM ingestion and knowledge graph indexing.
Skill Claude CodeCodex
Browser automation, web testing, dynamic scraping, and visual verification using Playwright and agent-browser CLI. Supports DOM snapshots with @eN element references, form interactions, and screenshot validations.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: