$ loading_
Design, evaluate, refine, and package AI skills with an architecture-first workflow.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "skill-conductor" yet — see the docs or source repo.
Use CREATE mode to design a customer support ticket classification AI skill. Output the goal, architecture pattern, input/output spec, key constraints, testing baseline, and evaluation metrics.
A structured skill design plan with architecture, interface specs, testing baselines, and evaluation criteria.
Use EVAL mode to compare two versions of an email summarization skill. Design a blind A/B test, scoring dimensions, benchmark samples, and provide strengths, weaknesses, and a recommendation.
An evaluation report with scores, comparative analysis, issue diagnosis, and a recommended version.
Use PACKAGE mode to prepare a reviewed market research assistant skill for release. Generate the release materials, including capability summary, usage instructions, sample prompts, limitations, and version notes.
A release-ready skill package with documentation for distribution, reuse, and maintenance.
Create professional prompts for image and video generation models.
Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 32 признака AI-генерации из русского текста - канцелярит, штампы ChatGPT, слоп | Russian AI-text humanizer skill for coding agents
mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insights-style HTML report on how you work: what you build, where you lose time, and concrete fixes. An agent skill for Claude Code, Codex, and any skills-capable agent.
Design, review, and package reusable Agent Skills and SKILL.md files.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Generate test scenarios and measure how well agents follow skills and rules.
Turn a repeated workflow into a reusable skill file from the current session.