Updated today
by microsoft
waza
CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness
1.4k GitHub stars (1,417)
+91 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | +1 |
| Sep 29 | +1 |
| Sep 30 | +2 |
| Oct 1 | +13 |
| Oct 2 | +21 |
| Oct 3 | +17 |
| Oct 4 | +6 |
| Oct 5 | +6 |
| Oct 6 | +5 |
| Oct 7 | +2 |
| Oct 8 | +3 |
| Oct 9 | +3 |
| Oct 10 | +2 |
| Oct 11 | +1 |
| Oct 12 | +4 |
| Oct 13 | −1 |
| Oct 14 | +1 |
| Oct 15 | +5 |
| Oct 16 | −1 |
- 24 skills (24 skills found in its SKILL.md files)
- 91 forks (91 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add microsoft/waza
Asks which skills and agents to install. Just one: npx skills add microsoft/waza --skill '{skill-name}' — add -g for every project.
Claude Code
git clone https://github.com/microsoft/wazacp -r "waza/.squad-templates" ~/.claude/skills/
Copies the {skill-name} skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add microsoft/waza
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 24 of 33 files.
-
{skill-name}
{what this skill teaches agents}
.squad-templates/skill.md on GitHub (opens in a new tab) -
waza-runner
Run evaluations on Agent Skills to measure their effectiveness. USE FOR: "run skill evals", "evaluate my skill", "test skill quality", "check skill triggers", "skill compliance check", "measure skill performance", "run evals on [skill-name]", "grade skill execution". DO NOT USE FOR: writing skills (use skill-authoring), improving frontmatter (use sensei), or general testing unrelated to skills.
waza-runner/SKILL.md on GitHub (opens in a new tab) -
code-explainer
**UTILITY SKILL** - Explain code snippets, functions, and algorithms in plain language. USE FOR: explain code, what does this code do, break down this function, help me understand this, walk through this algorithm, clarify this logic, explain this snippet, describe what happens here. DO NOT USE FOR: writing new code (use code generation), fixing bugs (use debugging), refactoring (use refactoring…
examples/code-explainer/SKILL.md on GitHub (opens in a new tab) -
waza-interactive
Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).
skills/waza-interactive/SKILL.md on GitHub (opens in a new tab) -
waza
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), c…
skills/waza/SKILL.md on GitHub (opens in a new tab) -
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
.copilot/skills/agent-collaboration/SKILL.md on GitHub (opens in a new tab) -
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
.copilot/skills/error-recovery/SKILL.md on GitHub (opens in a new tab) -
git-workflow
Squad branching model: dev-first workflow with insiders preview channel
.copilot/skills/git-workflow/SKILL.md on GitHub (opens in a new tab) -
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
.copilot/skills/reviewer-protocol/SKILL.md on GitHub (opens in a new tab) -
secret-handling
Never read .env files or write secrets to .squad/ committed files
.copilot/skills/secret-handling/SKILL.md on GitHub (opens in a new tab) -
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
.copilot/skills/session-recovery/SKILL.md on GitHub (opens in a new tab) -
squad-commands
Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.
.copilot/skills/squad-commands/SKILL.md on GitHub (opens in a new tab) -
squad-conventions
Core conventions and patterns used in the Squad codebase
.copilot/skills/squad-conventions/SKILL.md on GitHub (opens in a new tab) -
squad-version-check
No description in the SKILL.md.
.copilot/skills/squad-version-check/SKILL.md on GitHub (opens in a new tab) -
test-discipline
Update tests when changing APIs — no exceptions
.copilot/skills/test-discipline/SKILL.md on GitHub (opens in a new tab) -
azd-publish
Prepare and publish a new version of the waza azd extension. USE FOR: "publish extension", "release new version", "bump version", "prepare release", "update changelog", "azd publish", "new release", "version bump", "cut a release". DO NOT USE FOR: running evals (use waza), writing skills (use skill-authoring), CI/CD pipeline changes (edit workflow files directly).
.github/skills/azd-publish/SKILL.md on GitHub (opens in a new tab) -
pdf-processor
**WORKFLOW SKILL** - Process PDF files including text extraction, rotation, and merging. USE FOR: "extract PDF text", "rotate PDF", "merge PDFs", "split PDF pages", "convert PDF to text". DO NOT USE FOR: creating PDFs from scratch (use document-creator), editing PDF forms (use form-filler). INVOKES: pdf-tools MCP for extraction, file-system for I/O. FOR SINGLE OPERATIONS: Use pdf-tools MCP direct…
cmd/waza/dev/testdata/high/SKILL.md on GitHub (opens in a new tab) -
my-tool
No description in the SKILL.md.
cmd/waza/dev/testdata/minimal/SKILL.md on GitHub (opens in a new tab) -
no-frontmatter
No description in the SKILL.md.
cmd/waza/dev/testdata/no-frontmatter/SKILL.md on GitHub (opens in a new tab) -
count
No description in the SKILL.md.
cmd/waza/tokens/testdata/count/SKILL.md on GitHub (opens in a new tab) -
profile-test-skill
**PROFILE TEST** - A skill for testing the profile command. USE FOR: testing profile analysis, verifying structural metrics. DO NOT USE FOR: production use.
cmd/waza/tokens/testdata/profile/SKILL.md on GitHub (opens in a new tab) -
all-pass
No description in the SKILL.md.
cmd/waza/tokens/testdata/check/all-pass/SKILL.md on GitHub (opens in a new tab) -
legacy-json-only
No description in the SKILL.md.
cmd/waza/tokens/testdata/check/legacy-json-only/SKILL.md on GitHub (opens in a new tab) -
no-config
No description in the SKILL.md.
cmd/waza/tokens/testdata/check/no-config/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.