菜单
Use this skill when the user wants to check AI agent logs, automation execution logs, org-level usage stats, AI credit consumption, or export automation job history. Covers 10 MCP tools.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill when an MCP tool 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.
Use this skill when the user wants to read, create, update, or delete pipes, phases, phase fields, labels, cards, comments, or field conditions. Covers 40 MCP tools for the core pipe and card lifecycle. Use the seed-pipe-across-phases workflow when populating empty phases for demos or QA.
Use this skill when the user wants to create, read, update, delete, or export pipe reports or organization reports. Covers the async export workflow (trigger, poll, download). 17 MCP tools.
Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Covers 20 MCP tools on Interfaces + internal_api. Not for pipes/cards.
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.
Use this skill when the user wants to upload a file to a Pipefy card or table-record attachment field. Covers the local file_path input mode through the MCP tools and the CLI.
| name | pipefy-observability |
| description | Use this skill when the user wants to check AI agent logs, automation execution logs, org-level usage stats, AI credit consumption, or export automation job history. Covers 10 MCP tools. |
| tags | ["pipefy","observability","logs","usage","credits","exports"] |
Monitor AI agent and automation execution, usage stats, credit consumption, and export job history. 10 MCP tools.
CLI status (v0.1): use MCP tools below. Observability Typer commands are planned for v0.3+.
| Concept | What tools expect | How to obtain |
|---|---|---|
| Pipe for AI agent logs | repo_uuid — the pipe UUID | get_pipe with numeric pipe_id; use pipe.uuid. |
| Automation for logs | automation_id — numeric | get_automations pipe_id=... |
| Org for usage stats | organization_id — numeric | Known from account setup or get_organization. |
| Tool (MCP) | CLI | Read-only | Purpose |
|---|---|---|---|
get_ai_agent_logs | — (CLI v0.3+) | Yes | Execution history for a specific AI agent. |
get_ai_agent_log_details | — (CLI v0.3+) | Yes | Single execution detail for an AI agent log entry. |
get_automation_logs | — (CLI v0.3+) | Yes | Execution history for an automation (by automation ID or pipe). |
get_automation_logs_by_repo | — (CLI v0.3+) | Yes | Automation logs filtered by pipe UUID. |
get_agents_usage | — (CLI v0.3+) | Yes | Org-level AI agent execution count and trends. |
get_automations_usage | — (CLI v0.3+) | Yes | Org-level automation execution stats. |
get_ai_credit_usage | — (CLI v0.3+) | Yes | AI credit consumption and remaining balance. |
export_automation_jobs | — (CLI v0.3+) | Yes | Trigger async export of automation job history. |
get_automation_jobs_export | — (CLI v0.3+) | Yes | Poll export job status (after export_automation_jobs). |
get_automation_jobs_export_csv | — (CLI v0.3+) | Yes | Download finished automation-jobs export as CSV text. |
Get the pipe UUID (not the numeric pipe ID):
MCP: get_pipe pipe_id=67890
Capture pipe.uuid from the response.
Fetch recent agent logs:
MCP: get_ai_agent_logs repo_uuid=<UUID> page=1
Identify the failed execution — look for status: failed entries.
Check credit usage if the agent stopped unexpectedly:
MCP: get_ai_credit_usage organization_id=123
Fix and re-enable — update the agent config (see skills/ai-agents/) and toggle status:
MCP: toggle_ai_agent_status agent_id=456
Trigger the export:
MCP: export_automation_jobs organization_id=123 period="current_month"
Poll for completion:
MCP: get_automation_jobs_export export_id=<EXPORT_ID>
Repeat until status is finished or failed.
Fetch CSV text (when finished):
MCP: get_automation_jobs_export_csv export_id=<EXPORT_ID>
get_ai_agent_logs returns empty: use the pipe UUID (e.g., abc123-...), not the numeric pipe ID. Get UUID from get_pipe.get_automation_jobs_export stays in processing: large exports take time. Wait at least 60 seconds between polls. If still processing after several minutes, retry the export trigger.skills/ai-agents/ — create and configure AI agents.skills/automations/ — create and debug automation rules.