Loading...
Loading...
Found 1,076 Skills
Run existing ShinkaEvolve tasks with the `shinka_run` CLI from a task directory (`evaluate.py` + `initial.<ext>`). Use when an agent needs to launch async evolution runs quickly with required `--results_dir`, generation count, and strict namespaced keyword overrides.
Create ShinkaEvolve task scaffolds from a target directory and task description, producing `evaluate.py` and `initial.<ext>` (multi-language). Use when asked to set up new ShinkaEvolve tasks, evaluation harnesses, or baseline programs for ShinkaEvolve.
Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.
Use when extracting requirements from Azure DevOps work items using dxs devops commands: fetching work items, reviewing relations, downloading attachments, compiling raw requirements. This is a utility skill — it extracts and structures work item content but does not build reports, datasources, or other artifacts.
Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment. Use when the user invokes /evo:discover, mentions setting up evo, wants to instrument a codebase for autonomous optimization, or asks to start a new evo run on a project.
Audit Claude Code configuration against latest features and best practices. Use when user says "evolve", "self-improve", "audit config", "what's new in claude code", "upgrade configuration", "check for improvements", "are we up to date".
Use when building revenue analytics on HubSpot — SQL warehouse queries, API enrichment pipelines, lead scoring models, pipeline forecasting, competitive intelligence. Triggers on "hubspot analytics", "revops dashboard", "lead scoring", "pipeline forecast", "ICP analysis", "hubspot SQL".
Professional DevOps engineering skill for creating CI/CD pipelines, implementing infrastructure as code, managing environments, and establishing monitoring and observability across all deployment stages.
Goal-driven fitness-scored improvement loop. Measures goals, picks worst gap, runs /rpi, compounds via knowledge flywheel.
Update specifications with discoveries made during development. Use when implementation reveals new requirements, constraints, or design changes.
Comprehensive mobile DevOps workflow that orchestrates mobile application development, CI/CD for mobile, app store deployment, and mobile device testing. Handles everything from mobile app build automation and testing to app store submission, monitoring, and mobile-specific DevOps practices.
Knowledge Blacksmith: Used to non-destructively merge and append new practical experience (new pitfalls encountered, new boundaries discovered, better solutions) into existing knowledge cards. The core principle is "extremely conservative minimally invasive surgery" - strictly prohibited from deleting or over-simplifying high-value experience (pain points, mistake records) in the original assets, and only upgrade old assets through Append and structured Merge. Trigger signals: `/asset-evolve`, `/asset-update`