browse-flows — Claude Code skill: what it does, how to install
browse-flows explores Power Automate environments and flows inside Claude Code. Useful when you need to inspect existing cloud flows, view triggers, or pick a flow for debugging.
MIT ★ 1,167 updated 2026-10-29
/plugin marketplace add microsoft/power-platform-skills
/plugin install power-automate@power-platform-skillsWhat browse-flows does
The skill interacts with Power Automate through FlowAgent MCP tools. It checks an environment ID from arguments or queries list_environments and asks you to select one, then presents matching cloud flows in a table with name, state, trigger, and modification date.
Pagination handles large lists via cursor tokens. Discovery metadata stays cached in memory for up to 60 seconds unless requested with fresh: true to bypass the cache.
Without FlowAgent MCP tools registered in Claude Code, this skill fails immediately. You must run the setup skill first to connect the required plugin tools.
What it helps with
- list Power Automate environments and active cloud flows
- inspect flow state, triggers, and modification timestamps
- locate a specific automation flow before debugging or checking run history
Example prompts for the agent
- List all Power Automate flows in environment env-prod-01
- Search for Power Automate flows matching invoice
- Explore available Power Automate environments
How to install browse-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 browse-flows -a claude-code3Manually: put the files in place
~/.claude/skills/browse-flows/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/browse-flows/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill browse-flows -a codex2Manually: put the files in place
.agents/skills/browse-flows/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill browse-flows -a cursor2Manually: put the files in place
.cursor/skills/browse-flows/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/power-platform-skills plugins/power-automate/skills/browse-flows2Manually: put the files in place
.github/skills/browse-flows/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/power-platform-skills --skill browse-flows -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/power-platform-skills --path plugins/power-automate/skills/browse-flowsManually: put the files in place
.devin/skills/browse-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 browse-flows
How to install browse-flows in Claude Code?
Run /plugin marketplace add microsoft/power-platform-skills, followed by /plugin install power-automate@power-platform-skills in your Claude Code session.
What does browse-flows do?
It scans Power Automate environments and renders a summary table of flows displaying their current state, triggers, action count, and timestamps.
What is required before running browse-flows?
It requires FlowAgent MCP tools. If those tools are missing in your client, run the setup skill first to wire them up.
Source text
SKILL.md · MIT
--- name: browse-flows description: Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments. user-invocable: true argument-hint: "[environment-id]" allowed-tools: Bash, Read, Glob, Grep, AskUserQuestion, 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__get_run_history, mcp__flowagent__get_run_details, mcp__flowagent__get_run_actions, mcp__flowagent__list_connections, mcp__flowagent__list_connectors, mcp__flowagent__get_connector, mcp__flowagent__get_flow_context, mcp__flowagent__set_current_flow, mcp__flowagent__clear_current_flow, mcp__flowagent__whoami, mcp__flowagent__doctor, mcp__flowagent__reconnect, mcp__flowagent__list_accounts, mcp__flowagent__switch_account model: opus --- # Browse Environments and Flows Interactive skill for discovering Power Automate environments and flows. ## 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). If no MCP tools are present, the plugin is not wired up — run the `setup` skill. ## Steps 1. **Resolve environment**: - If `$ARGUMENTS` contains an environment ID, use it. - Otherwise call `list_environments` (use `query` to filter if user mentioned a name). - Reuse the returned environment metadata while browsing. It is cached in memory for up to 60 seconds; use `fresh: true` when the user explicitly needs current discovery or permissions. - If multiple environments, use AskUserQuestion to let user pick. 2. **List flows**: Call `list_flows` on the selected environment. Use `name` param if user is looking for something specific. - A partial response contains `flows`, `complete: false` and `nextCursor`. Continue with `cursor: nextCursor`, keeping `env`, `top`, `name` and `filter` unchanged. - Follow cursors before reporting a complete count or claiming a search found nothing. If stopping early, label the results partial. - Continuations may reuse one metadata page for up to 60 seconds, not a fresh inventory. Omit the cursor for a fresh search. If the service page changed, restart without a cursor and discard that search's earlier partial counts. 3. **Present results** in a table: | # | Name | State | Trigger | Actions | Last Modified | |---|------|-------|---------|---------|---------------| 4. **Offer next steps** via AskUserQuestion: - View flow details (`get_flow`) - Check run history (`get_run_history`) - Debug a failed flow (use `/debug-flow`) - Create a new flow (use `/create-flow`)
© Microsoft · MIT · microsoft/power-platform-skills