pipefy/ai-toolkit

pipefy-reports

Use this skill when the user wants to create, read, update, delete, or export pipe reports or organization reports.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/pipefy/ai-toolkit --skill pipefy-reports

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

Reports

Read the MCP reference or CLI reference for the surface you are using. Load only the relevant reference.

Pipe reports and organization reports: discovery, CRUD, and async exports.


Cross-cutting patterns

  • Build ReportCardsFilter using get_pipe_report_columns and get_pipe_report_filterable_fields; use introspect_type for uncommon inputs.
  • get_pipe_reports omits cardCount in the query (Pipefy can error when resolving it).

Pipe report tools

OperationRead-onlyPurpose
get_pipe_reportsYesList all reports for a pipe.
get_pipe_reportsYesLoad one report by report_id when needed.
get_pipe_report_columnsYesDiscover available columns for a report filter.
get_pipe_report_filterable_fieldsYesDiscover filterable fields for a report.
create_pipe_reportNoCreate a new pipe report.
update_pipe_reportNoUpdate report name or filters.
delete_pipe_reportNoDestructive; review and approve first. Use the selected surface's confirmation flow if one exists.
export_pipe_reportNoTrigger async export.

Organization report tools

OperationRead-onlyPurpose
get_organization_reportsYesList all org-level reports.
get_organization_reportYesSingle org report data.
create_organization_reportNoCreate an org-wide report.
update_organization_reportNoUpdate report config.
delete_organization_reportNoDestructive; review and approve first. Use the selected surface's confirmation flow if one exists.
export_organization_reportNoTrigger async export.

Export status & download

OperationPurpose
get_pipe_report_exportPoll pipe report export status (after export_pipe_report).
get_organization_report_exportPoll org report export status (after export_organization_report).
export_pipe_audit_logsExport pipe audit logs (separate from card report exports).

Steps — export a pipe report

  1. List available reports:

Operation: get_pipe_reports pipe_uuid=<PIPE_UUID> (get_pipe supplies the UUID).

  1. Trigger the export:

Operation: export_pipe_report pipe_id=67890 pipe_report_id=123

  1. Poll until done:

Operation: get_pipe_report_export export_id=<EXPORT_ID>

Repeat every 5–10 seconds until state is done (or failed).

  1. Download: use the signed fileURL from the done export response over HTTPS.

The link expires 1 hour after the read that returned it, and anyone holding it can download the file until then. When you hand it to the user, say that it expires in 1 hour; for a fresh link, read the export again.


Steps — create a filtered pipe report

  1. Discover filterable fields:

Operation: get_pipe_report_filterable_fields pipe_uuid=<PIPE_UUID> (get_pipe supplies the UUID).

  1. Create the report with a `ReportCardsFilter` shape (not a top-level current_phase array):

Arguments:

   create_pipe_report pipe_id=67890 name="Phase subset" filter='{"operator":"and","queries":[{"field":"current_phase","operator":"eq","type":"select","value":"<phase_id>"}]}'

Use the exact field string from step 1. Invalid shapes are rejected before GraphQL with a message pointing at get_pipe_report_filterable_fields.


Success criteria

  • get_pipe_report_export (or get_organization_report_export) reaches a terminal done or failed state.
  • Downloaded export contains the expected card/report data.

Failure modes

  • Export stuck in `processing`: large pipes with many cards can take minutes. If the export is still processing after a minute of polling every 5 to 10 seconds, poll once every 60 seconds instead. Retry the export trigger if still processing after several minutes.
  • `get_pipe_reports` returns `null` for `cardCount`: known Pipefy API behavior; the tool omits that field automatically.
  • Filter rejected before GraphQL: do not pass {"current_phase":["id"]}; use operator + queries (see step 2 above).
  • Filter not working after create: use get_pipe_report_filterable_fields to confirm the exact field string and value format.

See also

  • pipefy-observability — export automation job history (different from pipe reports).
  • pipefy-introspection — discover ReportCardsFilter input shape for complex filters.

Related by task

from this repository

More skills

All skills
pipefy
Community

pipefy-ai-agents

Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Includes pre-flight validation and pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For traditional automations and AI automations, see pipefy-automations.

1h installs
3
GitHub stars
50
Updated
Oct 20
pipefy
Community

pipefy-api-fallback

Use this skill when a toolkit operation fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow the 3-tier resolution strategy before reaching this point.

1h installs
3
GitHub stars
50
Updated
Oct 20
pipefy
Community

pipefy-attachments

Use this skill when the user wants to upload a file to a Pipefy card or table-record attachment field. Covers local and downloaded file sources, plus a presigned-URL handshake for uploading files directly.

1h installs
3
GitHub stars
50
Updated
Oct 20
pipefy
Community

pipefy-automations

Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). For AI agents (conversational), see pipefy-ai-agents.

1h installs
3
GitHub stars
50
Updated
Oct 20