Updated today
by microsoft
waza
CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness
1.5k GitHub stars (1,500)
+102 in 30 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 |
| Oct 17 | +2 |
| Oct 18 | +1 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | +4 |
| Oct 22 | 0 |
| Oct 23 | +1 |
| Oct 24 | +2 |
| Oct 25 | +1 |
| Oct 26 | 0 |
| Oct 27 | 0 |
| Oct 28 | +2 |
| Oct 29 | +57 |
| Oct 30 | +7 |
| Oct 31 | +2 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | +3 |
| Nov 4 | 0 |
| Nov 5 | +1 |
- 27 skills (27 skills found in its SKILL.md files)
- 98 forks (98 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 27 of 45 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/ on GitHub (opens in a new tab)SKILL.md -
evidence-judge
Read a supplied report and summarize its recorded status and numeric items.
examples/evidence-judge/ on GitHub (opens in a new tab)SKILL.md -
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/ on GitHub (opens in a new tab)SKILL.md -
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/ on GitHub (opens in a new tab)SKILL.md -
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/ on GitHub (opens in a new tab)squad-commands/ SKILL.md -
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
.github/skills/ on GitHub (opens in a new tab)agent-collaboration/ SKILL.md -
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/ on GitHub (opens in a new tab)azd-publish/ SKILL.md -
coordinator-init-mode
The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad/ scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad/team.md…
.github/skills/ on GitHub (opens in a new tab)coordinator-init-mode/ SKILL.md -
coordinator-response-mode
Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode. This skill contains the complete decision table, exemplar prompts for each mode, the Lightweight spawn template, and the upgrade rules. Squad coordinator loads this on demand once routing has identified the agent — to pick the right ceremony level for the task.
.github/skills/ on GitHub (opens in a new tab)coordinator-response-mode/ SKILL.md -
coordinator-source-of-truth
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may read each one, and the precedence rules when they conflict. Squad coordinator loads this on demand when it needs to resolve a write conflict, decide where a piece of state belongs, or answer a 'who owns this file' question.
.github/skills/ on GitHub (opens in a new tab)coordinator-source-of-truth/ SKILL.md -
cross-squad-communication
Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories
.github/skills/ on GitHub (opens in a new tab)cross-squad-communication/ SKILL.md -
cross-squad
Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says 'squad' (the product) vs casual English 'group of agents'.
.github/skills/ on GitHub (opens in a new tab)cross-squad/ SKILL.md -
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
.github/skills/ on GitHub (opens in a new tab)error-recovery/ SKILL.md -
git-workflow
Squad branching model: dev-first workflow with insiders preview channel
.github/skills/ on GitHub (opens in a new tab)git-workflow/ SKILL.md -
iterative-retrieval
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.
.github/skills/ on GitHub (opens in a new tab)iterative-retrieval/ SKILL.md -
reflect
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
.github/skills/ on GitHub (opens in a new tab)reflect/ SKILL.md -
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
.github/skills/ on GitHub (opens in a new tab)reviewer-protocol/ SKILL.md -
secret-handling
Never read .env files or write secrets to .squad/ committed files
.github/skills/ on GitHub (opens in a new tab)secret-handling/ SKILL.md -
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
.github/skills/ on GitHub (opens in a new tab)session-recovery/ SKILL.md -
squad-conventions
Core conventions and patterns used in the Squad codebase
.github/skills/ on GitHub (opens in a new tab)squad-conventions/ SKILL.md -
squad-help
How to use the Squad coordinator agent and the separate squad menu skill, with host-dependent discovery and slash-command support.
.github/skills/ on GitHub (opens in a new tab)squad-help/ SKILL.md -
squad-version-check
Internals of how @bradygaster/squad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.
.github/skills/ on GitHub (opens in a new tab)squad-version-check/ SKILL.md -
squad
Squad's command catalog and interactive menu. Invoke via /squad where the host exposes user-invocable skills as commands, or natural language ("squad commands", "what can squad do", "show me squad options"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI co…
.github/skills/ on GitHub (opens in a new tab)squad/ SKILL.md -
test-discipline
Design assertions that prove the actual contract and fail on realistic regressions
.github/skills/ on GitHub (opens in a new tab)test-discipline/ SKILL.md -
tiered-memory
Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn
.github/skills/ on GitHub (opens in a new tab)tiered-memory/ SKILL.md
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.