sensei

**WORKFLOW SKILL** — Evaluates and improves agent skill quality in `.github/skills/` using waza. Scores skill compliance (frontmatter, triggers, anti-triggers, eval coverage), suggests improvements, runs eval suites, and iterates until target quality is reached. INVOKES: waza CLI, ask_user. USE FOR: evaluate skill, improve skill, check skill compliance, run skill evals, sensei, skill quality, validate skills, skill audit, waza check, waza run. DO NOT USE FOR: creating new skills from scratch (use waza new), deploying code (use azure-deploy), code review (use code-review).

Zur Installation springen Dateien prüfen

Repository: Azure/azure-dev
Letzte Quellaktivität: 8. April 2026 um 22:33
Erkannte Sprache von SKILL.md: Englisch
Sterne: 570
Forks: 367

Installationsoptionen

Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/Azure/azure-dev/tree/main/.github/skills/sensei.

Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.

npx skills add https://github.com/Azure/azure-dev --skill sensei

Der Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.

Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.

Quelldateien prüfen

Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.

Datei-Explorer

2 Dateien

SKILL.md

Quellanweisungen · Schreibgeschützte Vorschau

name: sensei
license: MIT
metadata: {"version":"1.0"}
description: **WORKFLOW SKILL** — Evaluates and improves agent skill quality in `.github/skills/` using waza. Scores skill compliance (frontmatter, triggers, anti-triggers, eval coverage), suggests improvements, runs eval suites, and iterates until target quality is reached. INVOKES: waza CLI, ask_user. USE FOR: evaluate skill, improve skill, check skill compliance, run skill evals, sensei, skill quality, validate skills, skill audit, waza check, waza run. DO NOT USE FOR: creating new skills from scratch (use waza new), deploying code (use azure-deploy), code review (use code-review).

# sensei Evaluates and improves agent skill quality using waza. ## Overview Sensei automates the evaluation and improvement of agent skills in this repository. It uses [waza](https://github.com/microsoft/waza) to score compliance, run eval suites, and iteratively improve skills until they meet quality targets. ## Prerequisites - **waza**: `go install github.com/microsoft/waza/cmd/waza@latest` or `azd ext install microsoft.azd.waza` {{ references/workflow.md }} ## Exit Criteria - All target skills have been checked and optionally improved - Compliance scores and eval results are reported - Changes saved to disk (user decides when to commit)

Auf GitHub ansehen

Zurück zur Suche Zurück zur Installation

foundry-extension-scenario-authoring

**WORKFLOW SKILL** — Authors and validates cli-interactive-tester scenarios for the azure.ai.agents extension: writes a new scenario YAML (or fixes an existing one) so it follows the tier/tag/hook/fixtures/requires conventions and goals-are-the-contract judging rules, then lint-validates it via list_scenarios (never start_session — no Azure cost). Typically driven through the foundry-extension-scenario-author agent. USE FOR: write a new scenario, add coverage for a command/flag, fix a scenario's tags/hooks/requires, add a fixture, close a coverage gap flagged by a PR regression run. DO NOT USE FOR: RUNNING scenarios or a suite — never drives a scenario or incurs Azure cost (use foundry-extension-scenario-suite-run for a sweep, or foundry-extension-scenario-pr-regression for a PR), driving a single scenario (foundry-extension-scenario-worker), azd core preflight (azd-preflight), changelog (changelog-generation), creating PRs (pull-request), scenarios for other extensions.

2026-09-25

foundry-extension-scenario-pr-regression

**WORKFLOW SKILL** — Runs the azure.ai.agents extension's cli-interactive-tester scenarios locally as a PR-scoped regression check (Tier 0 is free/offline; Tier 1b/Tier 2 incur Azure cost). Resolves the current branch's PR, maps changed files to impacted scenario tags, drives matching scenarios via foundry-extension-scenario-worker agents, and posts a results comment on the PR. Typically dispatched by foundry-extension-scenario-orchestrator, but can trigger directly. USE FOR: run agent scenarios for a PR, scenario regression check, test agents extension PR, run impacted scenarios, check for regressions before merge, validate an azure.ai.agents diff. DO NOT USE FOR: running the whole suite or a tag/tier sweep not tied to a diff (foundry-extension-scenario-suite-run), authoring/editing scenarios without running them — no Azure cost (foundry-extension-scenario-authoring), azd core preflight (azd-preflight), changelog (changelog-generation), creating PRs (pull-request), scenarios for other extensions.

2026-09-25

foundry-extension-scenario-suite-run

**WORKFLOW SKILL** — Runs the azure.ai.agents extension's cli-interactive-tester scenarios as a full or tag/tier-filtered sweep NOT tied to a PR diff (Tier 0 free; Tier 1b/2 cost-gated). Discovers scenarios via list_scenarios, drives them concurrently via foundry-extension-scenario-worker agents, then writes an aggregate report. Dispatched by foundry-extension-scenario-orchestrator, or triggered directly. USE FOR: run the whole suite, run all scenarios, smoke-test the extension, a tag-filtered sweep (e.g. "run every `init` scenario"), a tier sweep (e.g. "run all of Tier 0"), a scheduled/periodic full regression not scoped to a diff. DO NOT USE FOR: PR- or diff-scoped selection (foundry-extension-scenario-pr-regression maps changed files to tags and comments on the PR), authoring/editing scenarios without running them — no Azure cost (foundry-extension-scenario-authoring), azd core preflight (azd-preflight), changelog (changelog-generation), creating PRs (pull-request), scenarios for other extensions.

2026-09-25

Alle aus diesem Repository ansehen

sensei

Quellinformationen

Installationsoptionen

Mit einem KI-Assistenten installieren

Quelldateien prüfen

Mehr aus diesem Repository

Mit einem KI-Assistenten installieren

Mehr aus diesem Repository