Loading...
Loading...
Found 31 Skills
Framework-agnostic persistent memory and self-improvement loops for AI agents. Scaffolds shared state, task queues, and learnings files that can be read/written by Claude, Gemini, and Antigravity. Use this to initialize an Agentic OS layer in any workspace and instruct agents on how to use it.
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.
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.
Audit recent work in a folder and produce a forward-looking self-improvement report. Reviews files modified in the past week, git activity, file-type distribution, and recurring task patterns; writes a 5-section weekly-setup-improvements.md with concrete updates for context files, ideas for new skills, workflow gaps to close, files to clean up, and what's working well enough to leave alone. Cross-platform; safe to schedule weekly via /schedule. Use when: 'weekly review', 'weekly self audit', 'improve my setup', 'what should I clean up', 'suggest new skills', 'self improvement loop', 'weekly setup improvements', or before a planning week.
Workflow orchestration for complex coding tasks. Use for ANY non-trivial task (3+ steps or architectural decisions) to enforce planning, subagent strategy, self-improvement, verification, elegance, and autonomous bug fixing. Triggers: multi-step implementation, bug fixes, refactoring, architectural changes, or any task requiring structured execution.
Scaffold and run a label's self-managing "music-company OS" inside its own git repo — the full label-intelligence workspace (folders, a self-managing CLAUDE.md mirrored to AGENTS.md, a read-only doctor + never-stale janitor, compound-learning and self-improvement loops, an in-place plugin) seeded with Recoup's conventions (top-level artists/{slug}/RECOUP.md identity files, releases/{slug}/RELEASE.md) and backed by the Recoup API as system of record. Use for "set up our label OS", "build the org workspace", "turn this repo into our label brain", or onboarding a new org/label repo. Pulls the real roster from the live account (auth via recoup-platform-connect-account), onboards artists API-first via recoup-roster-add-artist, and calls the other recoup-* skills (research/content/release/song/catalog) instead of reinventing them. The single workspace/OS builder — also covers the lightweight "just mirror my roster into folders" case.
HOWL v2 — Hunt, Optimize, Win, Learn. Nightly self-improvement loop for the WOLF autonomous trading strategy. Runs once per day (via cron) to review all trades from the last 24 hours, compute win rates, analyze signal quality correlation, evaluate DSL tier performance, identify missed opportunities, and produce concrete improvement suggestions for the wolf-strategy skill. v2 adds fee drag ratio (FDR) analysis, holding period bucketing, LONG vs SHORT regime detection, rotation cost tracking, cumulative drift detection, and gross vs net profit factor separation. Use when setting up daily trade review automation, analyzing trading performance, or improving an autonomous trading strategy through data-driven feedback loops. Requires Senpi MCP connection, mcporter CLI, and OpenClaw cron system.
Autonomously optimize an existing AI skill by running it repeatedly against binary evals, mutating one instruction at a time, and keeping only changes that improve pass rate. Based on Karpathy-style autoresearch, but applied to SKILL.md iteration instead of ML training. Use when optimizing a skill, benchmarking prompt quality, building evals for a skill, or running self-improvement loops on reusable agent instructions. Triggers on: skill-autoresearch, optimize this skill, improve this skill, benchmark this skill, eval my skill, run autoresearch on this skill, self-improve skill.
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
(Industry standard: Routing Agent / Orchestrator Pattern) Primary Use Case: Analyzing an ambiguous trigger and routing it to one of the specific specialized implementations. Routes triggers to the appropriate agent-loop pattern. Use when: assessing a task, research need, or work assignment and deciding whether to run a simple learning loop, red team review, dual-loop delegation, or parallel swarm. Manages shared closure (seal, persist, retrospective, self-improvement).
End-to-end benchmark suite for vercel-plugin. Runs realistic projects through skill injection, launches dev servers, verifies everything works, analyzes conversation logs, and produces an improvement report for overnight self-improvement loops.
Create, improve, and manage Droid skills. Use when the user wants to: - Create new skills from scratch or from session learnings - Improve existing skills based on user preferences - Analyze sessions to identify patterns worth codifying - Understand best practices for agentic skill design This is a meta-skill for self-improvement and continuous learning.