mcpField
W
workflows-history

workflows-history

github.com/zapierProductivity23462 installsUpdated 3w ago
Repository

About workflows-history

workflows-history is a Zapier agent skill for finding workflow runs and inspecting their outcomes or failures. It helps users trace run status, timing, inputs, outputs, and step-level errors, while distinguishing deployed runs from draft tests.

Key features

  1. 01Workflow lookup by ID or name
  2. 02Run history retrieval
  3. 03Run-level status and data summaries
  4. 04Step error inspection
  5. 05Draft test identification

Use cases

  1. 01Investigate a failed workflow run
  2. 02Review recent run status and outputs
  3. 03Check whether an edit is still unpublished

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/zapier/agent-skills --skill workflows-history

After installing, type/workflows-historyin Claude Code to confirm it loaded.

Details

From the project README

Zapier Workflows History

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.

Identify The Workflow

If the user provides a workflow ID, use it directly.

If the user refers to the workflow by name or description, list workflows first and find the matching ID:

zapier-sdk --stability experimental list-workflows --json

If multiple workflows match, show the candidates and ask the user which one they mean.

Fetch Run History

zapier-sdk --stability experimental list-workflow-runs <workflow-id> --json

Parse the JSON output. Useful fields may include id, status, started_at, finished_at, input, and output.

When the workflow ID is known, include the Zapier editor link:

https://zapier.com/workflow/<workflow-id>

Drill Into A Run

If a single deployed workflow run failed or the user wants step-level detail:

zapier-sdk --stability experimental get-workflow-run <run-id> --json

Draft test runs started with run-workflow-draft are workflow runs too (kind: "draft"); inspect them with get-workflow-run.

If a manual trigger response returns a trigger ID before a workflow run ID is available, bridge from trigger to run:

zapier-sdk --stability experimental get-trigger-run <trigger-id> --json

Summarize the failure, status, timing, input, output, and any step error details that appear in the response. Avoid dumping raw JSON unless the user asks for it.

Draft State

Runs execute published versions — unpublished draft edits never show up in run history. If the user expects a recent change to be reflected in runs and it isn't, check for an open draft holding that change:

zapier-sdk --stability experimental list-workflow-drafts <workflow-id> --json

If an open draft exists, tell the user their change is unpublished (note last_edited_at and the editor link) rather than concluding the workflow is broken.

Comments

Markdown supported