manage-flows — Claude Code skill: what it does, how to install
manage-flows manages Power Automate flow lifecycles in Claude Code: handles publish-test loops, batch changes, tenant inventories, and runaway run cancellations.
MIT ★ 1,167 updated 2026-10-29
/plugin marketplace add microsoft/power-platform-skills
/plugin install power-automate@power-platform-skillsWhat manage-flows does
The skill drives Power Automate operations through FlowAgent MCP tools. It handles publish-and-test runs by invoking publish_flow, triggering an execution with a 30-second timeout, and returning step statuses. For bulk maintenance, it processes multi-flow activation, deactivation, and deletion. Deletion safety is built in: server policies trigger BulkDeleteConfirmRequired after 3 deletions within 10 minutes, and removed items remain recoverable via restore_backup.
Tenant inventory commands page through environment lists, caching discovery metadata for up to 60 seconds. The agent processes at least 10 environments before delivering a summary, following every cursor in list_flows to avoid truncated counts. For active incidents, cancel_all_runs halts running or waiting tasks and can pass turnOff: true to shut down the faulty flow immediately.
Execution requires FlowAgent MCP tools exposed to Claude Code or the local CLI engine build for environment-level tasks.
What it helps with
- Run automated publish-and-test cycles on Power Automate flows
- Generate tenant-wide flow inventories across multiple environments
- Flag unhealthy flows showing over 50% failure across their last 5 runs
- Bulk-cancel runaway flow queues and deactivate misbehaving triggers
Example prompts for the agent
- Publish flow flow-123 and run a smoke test waiting up to 30 seconds
- Run an inventory report across environments and list partial counts
- Cancel all running executions for flow-999 and turn it off
How to install manage-flows
1Plugin marketplace
/plugin marketplace add microsoft/power-platform-skills/plugin install power-automate@power-platform-skillsThis installs the whole power-automate plugin with all its skills
2Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill manage-flows -a claude-code3Manually: put the files in place
~/.claude/skills/manage-flows/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/manage-flows/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill manage-flows -a codex2Manually: put the files in place
.agents/skills/manage-flows/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill manage-flows -a cursor2Manually: put the files in place
.cursor/skills/manage-flows/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/power-platform-skills plugins/power-automate/skills/manage-flows2Manually: put the files in place
.github/skills/manage-flows/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill manage-flows -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/power-platform-skills --path plugins/power-automate/skills/manage-flowsManually: put the files in place
.devin/skills/manage-flows/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about manage-flows
How to install manage-flows in Claude Code?
Add the marketplace source with /plugin marketplace add microsoft/power-platform-skills, then run /plugin install power-automate@power-platform-skills.
What does manage-flows do?
It manages Power Automate flow lifecycles, performing health checks, bulk state modifications, runaway execution cancellation, and tenant environment inventories.
What happens when multiple flows are deleted at once?
The skill requires explicit confirmation of flow names and IDs. After 3 deletes within 10 minutes, it passes confirmBulk: true to satisfy server requirements.
Source text
SKILL.md · MIT
--- name: manage-flows description: Manage flow lifecycle - publish, test, batch operations, inventory reports. Use when the user asks to publish, test, batch manage, or get an inventory of flows. Inventories page large environment lists and state which environments were covered. user-invocable: true argument-hint: "<operation> [flow-ids...]" context: fork allowed-tools: Bash, Read, Write, Glob, Grep, mcp__flowagent__list_environments, mcp__flowagent__set_current_env, mcp__flowagent__get_current_env, mcp__flowagent__resolve_environment, mcp__flowagent__list_flows, mcp__flowagent__get_flow, mcp__flowagent__create_flow, mcp__flowagent__update_flow, mcp__flowagent__edit_flow, mcp__flowagent__copy_flow, mcp__flowagent__publish_flow, mcp__flowagent__disable_flow, mcp__flowagent__delete_flow, mcp__flowagent__run_flow, mcp__flowagent__get_run_history, mcp__flowagent__get_run_details, mcp__flowagent__get_run_actions, mcp__flowagent__get_run_action_repetitions, mcp__flowagent__cancel_run, mcp__flowagent__cancel_all_runs, mcp__flowagent__resubmit_run, mcp__flowagent__diagnose_run, mcp__flowagent__list_connections, mcp__flowagent__list_connectors, mcp__flowagent__get_connector, mcp__flowagent__search_operations, mcp__flowagent__get_operation_details, mcp__flowagent__pick_or_create_connection, mcp__flowagent__resolve_refs, mcp__flowagent__resolve_params, mcp__flowagent__scaffold_flow, mcp__flowagent__list_templates, mcp__flowagent__validate_flow, mcp__flowagent__preflight_flow, mcp__flowagent__smoke_test, mcp__flowagent__get_expression_help, mcp__flowagent__list_desktop_flows, mcp__flowagent__list_machine_groups, mcp__flowagent__run_desktop_flow, mcp__flowagent__get_flow_context, mcp__flowagent__set_current_flow, mcp__flowagent__clear_current_flow, mcp__flowagent__invoke_operation, mcp__flowagent__get_past_trigger_inputs, mcp__flowagent__test_connection, mcp__flowagent__fix_connection, mcp__flowagent__delete_connection, mcp__flowagent__preview_update, mcp__flowagent__get_backup, mcp__flowagent__list_backups, mcp__flowagent__restore_backup, mcp__flowagent__list_trigger_emulators, mcp__flowagent__resolve_entity, mcp__flowagent__list_datasets, mcp__flowagent__list_tables, mcp__flowagent__whoami, mcp__flowagent__doctor, mcp__flowagent__reconnect, mcp__flowagent__list_accounts, mcp__flowagent__switch_account model: opus --- # Flow Lifecycle Manager Autonomous agent for flow lifecycle operations: publish-and-test, batch operations, inventory reports. ## Tools This skill uses the **FlowAgent MCP tools**, referred to by bare name (clients surface them as `mcp__flowagent__<tool>` in Claude Code or `flowagent-<tool>` in Copilot CLI). Use CLI shell commands (local engine build only) for CLI-only operations (connection lifecycle, sharing, solutions/admin) or when no MCP tools are present. ## Capabilities ### 1. Publish-and-Test Cycle 1. Call `publish_flow` to enable 2. Call `run_flow` with `wait: true` and `timeout: 30` to trigger and wait for completion 3. Report: pass/fail, duration, action statuses ### 2. Batch Operations For multiple flows (IDs from `$ARGUMENTS` or from `list_flows`): - **Batch disable**: Call `disable_flow` per flow - **Batch delete**: First list the exact flows (name + ID) to the user and get explicit confirmation. Never delete "all flows" in an environment from a single instruction. Then call `delete_flow` per flow. After 3 deletes in 10 minutes the server returns `BulkDeleteConfirmRequired`; pass `confirmBulk: true` only for flows the user has confirmed. Deleted flows can be recovered with `list_backups` / `restore_backup`. - **Batch publish**: Call `publish_flow` per flow Report per-item success/failure. ### 3. Inventory Report 1. Call `list_environments` to get environments. Large tenants return a partial page (`total`, `nextSkip`, `note`) - page with `skip` or filter with `query`; never treat a partial page as the full list. Reuse this discovery across the per-environment loop rather than listing environments again for every flow lookup. Metadata is cached in memory for up to 60 seconds; use `fresh: true` for explicitly requested current discovery, then page without repeating the fresh bypass 2. Call `list_flows` on **each** environment (or only the ones the user specified) - do not stop at the current one. A partial response contains `flows`, `complete: false` and `nextCursor`: continue with `cursor: nextCursor` and unchanged `env`, `top`, `name` and `filter`. Follow all cursors before treating an environment's count as complete. Continuations may reuse one metadata page for up to 60 seconds; start without a cursor for fresh data. If a changed page requires restarting, discard earlier partial counts for that environment. For many environments, cap the loop (e.g. the first 10-20, or those the user names), and keep going past individual failures. A large tenant is a reason to cap, never a reason to inventory only one: unless the user scoped it, cover at least the first 10 environments before reporting, then offer to continue 3. Produce summary: flow counts by state, trigger types, recent modifications 4. State coverage explicitly: "N of M environments inventoried" and list any skipped, failed or still-partial environments. Count an environment as fully inventoried only when its flow cursors are exhausted. If only one was inventoried (user scoped it, or others failed), say so rather than presenting it as the full tenant ### 4. Health Check For each flow in an environment: 1. Call `get_run_history` with `top: 5` 2. Count Succeeded vs Failed runs 3. Flag flows with >50% failure rate Report: flow name, success rate, last run status, last failure error. ### 5. Incident Response (runaway runs) When a flow is misfiring with many queued runs: 1. Call `cancel_all_runs` to bulk-cancel every Running/Waiting run (uses the Dataverse bulk action for solution & modern non-solution flows, per-run fallback otherwise). Pass `turnOff: true` to also disable the flow while the root cause is fixed. 2. After fixing, `resubmit_run` the affected runs (note: only self-invoked runs are resubmittable per PA policy).
© Microsoft · MIT · microsoft/power-platform-skills