Loading...
Loading...
Found 1,076 Skills
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.
DevOps and IT Ops automation - CI/CD, monitoring, incident management, and infrastructure workflows
Evolve APIs safely using versioned DTOs/transformers, deprecations, and compatibility tests
Deploy and configure MetaClaw — an agent that meta-learns and evolves from live conversations using skills injection, RL training, and smart scheduling.
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after idea-tournament), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing idea tournaments or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use idea-tournament).
Convert an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting the relevant code, adding evolve blocks, and generating `evaluate.py` plus Shinka runner/config files. Use when the user wants to optimize existing code with Shinka instead of creating a brand-new task from a natural-language description.
Use this skill for ANY task involving jj or jujutsu version control. ALWAYS trigger when the user mentions jj, jujutsu, revsets, change IDs, bookmarks, or oplog. Also trigger when the user wants to squash, split, or reorder commits in a stack, write a revset query, absorb fixup changes, undo or restore a previous operation, resolve conflicts after rebasing, recover from force-pushes, rewrite protected/immutable commits, view change evolution (evolog), or try parallel approaches. Trigger even if "jj" is not explicitly said — "changes" instead of "commits", "stack" instead of "branch", "absorb", "squash into the right commit", "undo my last operation", "conflict after rebase", or "compare approaches in parallel" are strong jj signals. This skill contains critical non-obvious rules (like always using -m flags) that prevent broken workflows.
Guide for creating evolving skills - detailed workflow plans that capture what you'll do, what tools you'll create, and learnings from execution. Use this when starting a new task that could benefit from a reusable workflow.
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing applications, managing infrastructure as code, deploying to Kubernetes clusters, configuring cloud platforms, automating releases, or responding to production incidents. Invoke for pipelines, Docker, Kubernetes, GitOps, Terraform, GitHub Actions, on-call, or platform engineering.
Internal protocol for evo optimization subagents. Not user-invocable -- read by subagents spawned from /optimize.
Run the evo optimization loop with parallel subagents until interrupted.
Governs the evolution of public APIs. Detects breaking changes, manages deprecation cycles, and generates migration guides for clients.