workflows-list — Claude Code skill: what it does, how to install
Lists durable Zapier workflows via the CLI and inspects drafts. Useful for inspecting deployed automations directly from your agent session.
npx skills add zapier/agent-skills --skill workflows-list -a claude-code
npx skills add zapier/agent-skills --skill list -a claude-codeWhat workflows-list does
The skill queries your Zapier account using the experimental zapier-sdk CLI commands. It extracts workflow IDs, status flags, timestamps, and editor links. Sensitive trigger_url values stay hidden unless requested directly. If a trigger includes a webhook_url, the skill surfaces that URL for external services.
You need zapier-sdk version 0.85.0 or newer. Running the workflows-doctor check is required before this skill executes. If CLI authentication expires, you must run zapier-sdk login in an interactive shell. Because account profile UUIDs might not match numeric author IDs, the skill avoids silent filtering and explains any ambiguity.
Beyond simple listings, the tool inspects open drafts and execution history. An unpublished server draft explains why the live automation behaves differently from the web editor. Run history fetches execute one workflow at a time to keep API volume reasonable.
What it helps with
- list published and disabled Zapier workflows
- inspect unpublished server drafts for a specific flow
- retrieve editor links and trigger webhook URLs
- check the most recent execution timestamp for a workflow
Example prompts for the agent
- Show all my Zapier workflows with their editor links.
- Check if workflow <workflow-id> has any open drafts.
- When was workflow <workflow-id> last executed?
How to install workflows-list
1Skills CLI (Vercel)
npx skills add zapier/agent-skills --skill workflows-list -a claude-codenpx skills add zapier/agent-skills --skill list -a claude-code2Manually: put the files in place
~/.claude/skills/list/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/list/
1Skills CLI (Vercel)
npx skills add zapier/agent-skills --skill list -a codex2Manually: put the files in place
.agents/skills/list/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add zapier/agent-skills --skill list -a cursor2Manually: put the files in place
.cursor/skills/list/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install zapier/agent-skills list2Manually: put the files in place
.github/skills/list/SKILL.md1Skills CLI (Vercel)
npx skills add zapier/agent-skills --skill list -a gemini-cli2Platform CLI
gemini skills install https://github.com/zapier/agent-skills --path skills/workflows/listManually: put the files in place
.devin/skills/list/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add zapier/agent-skills --skill list -a opencodeClaude.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 workflows-list
How to install workflows-list in Claude Code?
Add the skill by running npx skills add zapier/agent-skills --skill workflows-list -a claude-code. You also need a configured zapier-sdk CLI in your environment.
What does workflows-list do?
It runs experimental Zapier SDK CLI commands to list durable workflows, retrieve direct editor links, and check trigger details. It can also inspect open drafts and recent execution logs for specific flows.
Why is trigger_url kept hidden by default?
Invoking a trigger_url executes the workflow as your authenticated account. To protect your setup, the skill suppresses this address unless you ask for it explicitly.
Source text
SKILL.md · MIT
--- name: workflows-list description: List durable workflows in the authenticated Zapier account using the Zapier SDK experimental Code Workflows commands. Use when the user asks to list my Zaps, show my durable workflows, what workflows do I have, or see what Zapier workflows are deployed. license: MIT metadata: author: zapier version: "1.3.0" sdk_cli_min: "0.85.0" sdk_cli_validated: "0.86.4" refresh_source: "zapier/agent-skills" --- # Zapier Workflows List Use the public SDK CLI experimental command surface. Do not use `zapier-sdk-code-substrate`. ## Compatibility Gate Before using this skill, run the `workflows-doctor` bundle compatibility check. If `workflows-doctor` is not installed or cannot be loaded, run `workflows-install` or install `workflows-doctor` from `zapier/agent-skills` before continuing. If `workflows-doctor` reports SDK/skill drift, follow its refresh instructions, stop this skill invocation, reload the agent workspace if needed, and ask the user to rerun the original request. ## Check Prerequisites ```bash zapier-sdk --version zapier-sdk get-profile --json zapier-sdk --stability experimental --help ``` If auth fails, ask the user to run `zapier-sdk login` in an interactive terminal and retry. ## List Workflows ```bash zapier-sdk --stability experimental list-workflows --json ``` Parse the JSON output and format what the user asked for. Common useful fields may include `id`, `name`, `enabled`, `is_private`, `created_by_user_id`, `created_at`, `updated_at`, `description`, `current_version`, and trigger-related metadata if present. For each workflow with an `id`, include the Zapier editor link: ```text https://zapier.com/workflow/<workflow-id> ``` Treat `trigger_url` as account-sensitive: firing it invokes the workflow as the authenticated account, so while the token in the URL is no longer a standalone credential, it is still not something to print gratuitously. Do not print `trigger_url` unless the user explicitly asks for it. Check each entry in `triggers[]` for `details.webhook_url`, regardless of trigger type — its presence alone tells you there's a catch URL. Unlike `trigger_url`, `webhook_url` is meant to be shared — it's the URL the user pastes into the external service — so surface it plainly when present. Most triggers have no `webhook_url`, and that is normal; do not flag its absence unless the user specifically expects one (for example they mention "Webhooks by Zapier"), in which case the installed SDK may predate this field. ## Open Drafts A workflow's published state is not the whole story — it may also have open server drafts, and an open draft always holds unpublished work (publishing consumes drafts). When the user asks about unpublished changes, in-progress work, or why the editor shows something different from what's live, check: ```bash zapier-sdk --stability experimental list-workflow-drafts <workflow-id> --json ``` Surface each open draft's `slug`, `last_edited_at`, and `last_edited_by_user_id`, and whether its `base_version_id` matches the newest published version (an older base means the draft predates the current live version). Include the draft's editor link: `https://zapier.com/workflow/<workflow-id>/draft/<draft-slug>/workflow.ts` — the final segment is one of the draft's `source_files` keys (`workflow.ts` in this bundle's flows). Do not fetch drafts for every workflow in a plain listing — it is one request per workflow; do it on request or for the workflows under discussion. ## Ownership Scoping `list-workflows` may return every workflow the authenticated user can see, including team workflows. If the user asks for "my workflows," first show the likely matches and explain any uncertainty rather than silently filtering by the wrong ID. Known quirk: `zapier-sdk get-profile` may return a UUID that does not match `list-workflows[].created_by_user_id`, which may be a separate numeric user ID. If you cannot confidently map those IDs, say so and present the unfiltered list with enough context for the user to choose. ## Last Run Time If the user asks for recent activity, fetch runs for each relevant workflow: ```bash zapier-sdk --stability experimental list-workflow-runs <workflow-id> --json ``` Use the most recent run. Be mindful of API volume for large accounts.
© zapier · MIT · zapier/agent-skills