메뉴
Orchestrate the full Chaos Studio v2 workflow: auth → workspace → scenario → run. Shares a single state file and supports resume.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/microsoft/chaos-studio --skill start-chaos명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Execute a ScenarioConfiguration and stream ScenarioRun status with per-action breakdown until terminal state.
Discover recommended scenarios, build and validate a ScenarioConfiguration, and auto-fix resource permissions.
Provision a Microsoft.Chaos/workspaces resource (v2), bind a managed identity, set scopes, and grant Reader RBAC on the scope.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | start-chaos |
| description | Orchestrate the full Chaos Studio v2 workflow: auth → workspace → scenario → run. Shares a single state file and supports resume. |
⛔ ABSOLUTE RULE: Do NOT improvise, skip, or substitute any step. On ANY error, STOP and wait for the user.
This skill is the human-interactive path: it persists state, renders cards, prompts for missing inputs, and generates an HTML report at the end. Use it when there is a user in the loop.
If you are an autonomous agent with no user to prompt — or you need
typed, atomic operations to compose into your own workflow — use the
chaos-studio MCP server instead (see mcp/README.md). The MCP exposes
the same Chaos Studio v2 surface as discrete tools (chaos_create_workspace,
chaos_list_recommended_scenarios, chaos_execute_scenario, …) without the
state file, cards, or interactive prompts.
Both surfaces target Microsoft.Chaos 2026-05-01-preview and use the local
az login session for auth.
All pipeline logic lives in scripts/Invoke-StartChaos.ps1. The script handles auth, workspace creation, scenario setup, execution, permission validation/fix, and the final summary card.
The AI orchestrator's only job is:
$env:STARTCHAOS_STATE_PATH to ${SESSION_DIR}/startchaos-state.json$env:STARTCHAOS_STATE_PATH = "<session-dir>/startchaos-state.json"
& "<skill-dir>/scripts/Invoke-StartChaos.ps1" @args
On resume: the script reads state and skips completed phases automatically.
| Exit | Meaning | AI Action |
|---|---|---|
| 0 | Pipeline complete | Done — summary card already rendered by script |
| 1 | Error | STOP. Render the error from script output. Wait for user. |
| 4 | Workspace inputs needed | ask_user for: resource group, workspace name, location, identity type, scopes. Re-run with -ResourceGroup, -WorkspaceName, -Location, -IdentityType, -Scopes. |
| 2 | Scenario selection needed | Read state.setup.recommendedScenarios from state file. ask_user with scenario names+descriptions as choices. Re-run with -ScenarioName <chosen>. |
| 3 | Parameter mode needed | Show the parameter table from the script output. ask_user which parameters they want to customize (or accept all defaults). Re-run with -ParameterMode autofill and -ParameterValues @{ key = 'value' } for any overrides. |
When exit 2 is followed by exit 3 on re-run, combine both user answers in the next invocation:
& Invoke-StartChaos.ps1 -ScenarioName "ZoneDown-1.0" -ParameterMode "autofill" -ParameterValues @{ duration = 'PT5M' }
-ParameterMode manual uses Read-Host prompts that do not render in a non-interactive AI session.
Always use -ParameterMode autofill combined with -ParameterValues for any overrides the user requests.
When exit 3 fires, show the user the parameter table from the output, ask which values they want to change, then re-run with autofill + overrides.
| Parameter | Phase | Description |
|---|---|---|
-ResourceGroup | 1 | Azure resource group |
-WorkspaceName | 1 | Workspace name |
-Location | 1 | Azure region (default: westus2) |
-IdentityType | 1 | SystemAssigned or UserAssigned |
-UserAssignedIdentityResourceId | 1 | Required when IdentityType=UserAssigned |
-Scopes | 1 | ARM resource ID(s) for workspace scope |
-ScenarioName | 2 | Selected scenario (e.g. ZoneDown-1.0) |
-ParameterMode | 2 | autofill (always use this — manual does not work in AI sessions) |
-ParameterValues | 2 | Hashtable of parameter overrides, e.g. @{ duration = 'PT5M' }. Applied on top of defaults during configuration creation. |
-ForceReauth | 0 | Force re-authentication |
fixResourcePermissions auto-remediation