44 skills · sorted by relevance
Design loops that improve an agent’s own prompts, workflows, or execution code from failure records. Define bounded edits, preserve candidate histories, and accept changes through independent tests that check improvements and regressions.
Access the equivalent of Claude Code's /pua:pro command from Codex CLI. The alias invokes the pro protocol for self-improvement, KPI performance measures, and configuration commands, with all processing kept local.
Run the repository self-improvement scrub only from its scheduler or an explicit request for that scrub.
The English summary is being prepared. Showing the original description.
[omh] Missed route or run lessons to record: classify and review self-improvement store routes as an auxiliary review lane before durable writes, then record workflow attempts as metadata-only traces, evals, review queues, patch proposals, regression cases, audits, indexes, and exports. Use when the user says: workflow-learning, workflow learning, route-signal, self-improvement store routing, store route review, memory skill wiki routing, learning trace, learning audit.
The English summary is being prepared. Showing the original description.
Start, inspect, or continue a persistent SIPS self-improvement loop. Use when the user asks for /selfloop, wants the agent to iteratively improve itself, or wants a goal dedicated only to SIPS and agent capability.
The English summary is being prepared. Showing the original description.
Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.
The English summary is being prepared. Showing the original description.
Configures AI agents (GitHub Copilot, Claude Code, Cursor, Codex) to understand a codebase and self-improve as the project evolves. Use when setting up a new project for AI-assisted development, onboarding AI agents to an existing repo, creating AGENTS.md, configuring MCP servers for code navigation, packaging project workflows as agent skills, or establishing self-improvement feedback loops. Covers AGENTS.md authoring, skill packaging, MCP configuration, context management, and living-documentation strategies.
The English summary is being prepared. Showing the original description.
Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.
Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.
Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.
Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.
The English summary is being prepared. Showing the original description.
Code intelligence over repositories Guaardvark has indexed: semantic code search, exact-text search, file listing, PageRank repository map, import dependency graph, reading one class or function, analysis and generated rewrites, plus the System Mapper and self-improvement status. Use when the user asks where something is implemented, how modules depend on each other, or wants an architecture map of an indexed repo.
The English summary is being prepared. Showing the original description.
Continuous self-improvement system for Hermes Agent. Analyzes your past sessions to find recurring failures and skill gaps, then automatically creates or patches skills and runs self-evolution to fix them. Set it to run overnight and wake up to a better agent. Use /dojo to start.
The English summary is being prepared. Showing the original description.
Iterative rubric-based evaluation and self-improvement loop. Builds a scoring rubric interactively, evaluates an artifact with multiple models in parallel (Codex, Gemini, Claude), then autonomously improves the artifact one criterion at a time until a score threshold is met or circuit breaker fires. "/rulph", "rubric evaluate", "rubric score", "multi-model evaluate", "score and improve", "evaluate and iterate", "grade this", "루브릭 루프", "채점 루프", "자율 개선", "개선 루프", "루브릭 평가"
The English summary is being prepared. Showing the original description.
Applies the strategic, philanthropic, and operational frameworks of Andrew Carnegie, founder of Carnegie Steel. Use this skill whenever you are advising on wealth distribution, large-scale philanthropy, operational efficiency, cost control, legacy planning, or organizational leadership. Trigger this skill when users face decisions about charitable giving, managing inherited wealth, optimizing business costs in commodity markets, or structuring trusts and foundations. Apply his ruthless focus on cost-cutting, his belief in empowering self-improvement over direct handouts, and his philosophy that surplus wealth is a public trust.
The English summary is being prepared. Showing the original description.
The single config quality skill. Two modes: (1) Default — review/wire pending self-improvement proposals. (2) Audit — analyzes skills, rules, CLAUDE.md, project refs, hooks, and agents against the actual codebase to find inaccuracies, trigger overlaps, stale references, and weak rules, then fixes them. Trigger on 'self-evolve', 'evolve', 'config health check', 'audit config', 'check claude setup', 'apply this rule', 'reorganize rules', 'ok' (when proposals are pending). NOT for improving individual skills (use skill-creator), diagnosing code bugs (use diagnose), or fixing broken code (use fix).
The English summary is being prepared. Showing the original description.
Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a fix, a refactor) or asks the agent to "evolve", "learn from this", or "remember how this went".
The English summary is being prepared. Showing the original description.
Self-improvement loop for multi-agent workflows. Diagnose failures, improve tool descriptions, and learn from success/failure patterns.
The English summary is being prepared. Showing the original description.
Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".
The English summary is being prepared. Showing the original description.
Радар фундаментальных публикаций про автономных AI-агентов в блогах AI-лабораторий и продуктовых команд (Anthropic, Claude, OpenAI, Cursor, LangChain, Amp, Cognition). Собирает ленты и HTML-индексы за окно дат, отсеивает продуктовые анонсы и релизы моделей, оставляет глубокие посты про архитектуру агентов: память и контекст, long-running циклы, self-improvement, оркестрация, экономика прогона, эвалы, риски длинных горизонтов. Отдаёт дайджест со ссылками, сутью каждого поста и тем, что забрать в свою работу. Use when (используй когда): пользователь хочет узнать, что нового вышло в блогах про AI-агентов, собрать дайджест за неделю или период, отследить исследования про агентную память. Триггерится на: "радар", "дайджест", "что нового в блогах", "публикации про агентов", "agent research", "что вышло за неделю", "блог Anthropic", "cursor blog", "langchain blog", "long-running agents", "research digest". Do NOT use for (не для): корпоративные вики и трекеры; arXiv; доставка сообщений.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Fix a specific bug or problem in a {{engine_name}} project. Supports two modes — immediate fix or plan-first. Without arguments executes existing .unikit/code/FIX_PLAN.md. Checks {{engine_name}} compilation, suggests test coverage, and creates self-improvement patches. Use when user says "fix bug", "debug this", "something is broken", "fix the tests", "fix the errors in the tests", "read the errors in the {{engine_name}} console logs and fix the problems", or pastes an error message or {{engine_name}} console log. Also trigger when user shares a NullReferenceException, MissingReferenceException, compilation error, or any {{engine_name}}-specific error.
The English summary is being prepared. Showing the original description.
Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system
The English summary is being prepared. Showing the original description.
Run one safe self-improvement cycle: hypothesize → experiment → record → (maybe) federate.
The English summary is being prepared. Showing the original description.