🧠
AI EngineeringPython

Skill Optimization Coach

by microsoft

Skill Optimization Coach is an AI Engineering skill for Claude Code, published by microsoft in SkillOpt.

16K stars1.5K forkson microsoft/SkillOptAdded 2026/08/14Repository updated 2026/08/13
agent-skillsself-evolving-agents
Install in seconds
Install Skill Optimization Coach
Copy Skill Optimization Coach into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/microsoft/SkillOpt/tree/main/skillopt/prompts ~/.claude/skills/prompts

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/microsoft/SkillOpt.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skillopt/prompts/meta_skill.md in microsoft/SkillOpt
Installs to
~/.claude/skills/prompts
Collection
One of 12 skills cataloged from this repository
Category
AI Engineering2451 skills

What Skill Optimization Coach does

Skill Optimization Coach writes compact optimizer-side meta skills that guide future agent skill edits using evidence from adjacent-epoch comparisons. It identifies which editing directions help or hurt in self-evolving agent environments.

Skill Optimization Coach is cataloged under AI Engineering on DirSkills. Skill Optimization Coach comes from a repository tagged agent-skills and self-evolving-agents.

Documentation

README

You are a optimizer-coach for an AI agent skill optimization system.

Your job is not to solve tasks directly and not to write target-facing skill rules. Your job is to write a compact OPTIMIZER-SIDE memory that helps future optimizer calls produce better skill edits in this environment.

What You Receive

  1. The previous epoch's last-step skill.
  2. The current epoch's last-step skill.
  3. A longitudinal comparison on the SAME sampled tasks under those two skills.
  4. The previous optimizer meta skill, if one existed.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Skill Optimization Coach

  • What else does microsoft publish alongside Skill Optimization Coach?

    Skill Optimization Coach is one of 12 skills that DirSkills catalogs from microsoft/SkillOpt, the repository it ships in. Its siblings there include ALFWorld Embodied Agent, DocVQA and Document Rewriter. Each one is a separate skill with its own page in this directory, installs the same way Skill Optimization Coach does, and is maintained by microsoft in that same repository. The rest of the collection is listed on the microsoft/SkillOpt page.

  • How does Skill Optimization Coach compare to other AI Engineering skills?

    Skill Optimization Coach ranks #281 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Optimization Coach against them. Open each page to compare what they document and how they install.

More from microsoft/SkillOpt

Skill Optimization Coach is one of 12 skills cataloged on DirSkills from microsoft/SkillOpt.

See all 12 skills
🤖
2w ago

ALFWorld Embodied Agent

ALFWorld Embodied Agent guides agents in the ALFWorld text environment to complete household tasks by navigating rooms, interacting with objects, and using appliances. Use it when an agent needs to choose admissible actions for pick-and-place, clean, heat, cool, or examine tasks.
AI Engineering
16K1.5K
📄
2w ago

DocVQA

DocVQA guides an agent to extract exact, evidence-backed answers from document images, tables, forms, and handwriting. Use it when answering visual document questions where precision and exact text spans matter.
AI Engineering
16K1.5K
✍️
2w ago

Document Rewriter

Document Rewriter rewrites full AI agent skill documents to incorporate selected revise suggestions from trajectory analysis while preserving scope and protected blocks. Use it when refining agent skills with consolidated feedback and clarity improvements.
AI Engineering
16K1.5K
🧮
2w ago

Live Mathematical MCQ Heuristics

Live Mathematical MCQ Heuristics guides models through mathematical multiple-choice questions by comparing options, checking theorem-level precision, and verifying hypotheses. Use it when answering rigorous math MCQs where distractors differ by strength, quantifiers, or exact conditions.
AI Engineering
16K1.5K
📊
2w ago

OfficeQA

OfficeQA retrieves and verifies numerical answers from official tables and time series, applying strict calculation, unit, and evidence checks before final answers.
Data
16K1.5K
🧠
2w ago

Question Answering

Question Answering normalizes short-answer trivia responses by applying rules for concise answer form, evidence matching, and clue interpretation. Use it when an agent must produce accurate, well-formed answers for QA or crossword-style questions.
AI Engineering
16K1.5K