菜单
Test a non-HTTP-trigger workflow (schedule, manual, errorTrigger) that n8nac cannot fire from the CLI. Resolves the n8n UI URL, waits for you to run it and report the execution-id, then inspects the run. Read-only against the instance.
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
Full 3-phase pipeline (Research → Write+Validate → Deploy+Test) for shipping an n8n workflow end-to-end. Wraps Etienne's `n8n-as-code:n8n-architect` skill for schema research + authoring, adds repo-scoped orchestration — community-template lookup, validate-push-test loop, mcpTrigger publish gate, execution inspection, Completion Report.
Review the current n8n-autopilot session for learnings (operational friction + workflow design anti-patterns), strip all PII, and push the redacted insights centrally via the plugin's ingest webhook (they land as batch comments on the public rollup issue). Side-effecting on `sync`/`review`-push — shows the redacted result and requires explicit confirmation.
Curated "user intent → exact command" mapping for the n8nac CLI. Use this BEFORE reading `n8nac-reference` or running `--help`. Covers the 60+ common workflows — lookup, deploy, test, debug, migrate, credentials, projects, environments. If your task matches a row here, run the linked command verbatim — no flag fishing.
Authoritative reference for every `n8nac` CLI command, subcommand, and flag (n8nac 2.4.0). Use this BEFORE running `--help` interactively, BEFORE guessing flags, and BEFORE inventing a subcommand. If a command does not appear in this file, it does not exist — research stops, do not invent CLI surface. Covers workspace, env, setup, credentials, credential, workflow, execution, skills, list/find/pull/push/promote/verify/test/test-plan/fetch/resolve/convert/native-mcp, plus subcommand-level help.
EXPERIMENTAL deterministic builder for a whole n8n workflow STACK (multiple sub-workflows wired via Execute Workflow), JS-orchestrated. Takes a PRP-style end-to-end use case, decomposes it into sub-workflows along known rules, fixes the handover contracts between them, documents the architecture (mermaid) in one central file, then builds each sub-workflow bottom-up via build-workflow-v2. Two modes: GREENFIELD (new stack) and EXTEND (change an existing one). Decomposition rules, build order (topological), and per-sub-WF gates are JS control flow the model cannot skip. Use for multi-workflow use cases; for a single workflow use build-workflow-v2.
EXPERIMENTAL deterministic variant of build-workflow + deploy, JS-orchestrated. Two modes: GREENFIELD (new workflow) and EDIT (change an existing one). Phase ordering, gate-checks (validate / drift-safe push --verify), and fix-loop limits are enforced by a Claude Code JS Workflow script instead of prose — gates become if/while control flow the model cannot skip or short-circuit. Subagent roles live in agents/n8n-*.md. Use when you want hard-enforced discipline over the soft prose pipelines.
| name | test-manual |
| description | Test a non-HTTP-trigger workflow (schedule, manual, errorTrigger) that n8nac cannot fire from the CLI. Resolves the n8n UI URL, waits for you to run it and report the execution-id, then inspects the run. Read-only against the instance. |
| argument-hint | <workflowId> |
| user-invocable | true |
| allowed-tools | Read, Bash(npx:*) |
npx n8nac test can only fire webhook / chat / form triggers. For schedule, manual, and
errorTrigger workflows the run must be started in the n8n UI. This skill packages that detour into
one flow so you do not have to hand-assemble the URL and the execution get command each time.
Why this exists: non-HTTP manual-test detours were the single most frequent friction observed in real production runs.
Use $ARGUMENTS as the workflow id. If empty, ask the user (or extract it from the .workflow.ts
they name: grep -oE "id:[[:space:]]*['\"][A-Za-z0-9]{10,}['\"]" <file> | head -1).
npx n8nac test-plan <workflowId> --json
triggerType is webhook / chat / form (i.e. testable: true) → STOP and tell the user
to use npx n8nac test <workflowId> (or /n8n-autopilot:deploy) instead — no manual step needed.schedule / manual / errorTrigger → continue.npx n8nac workflow present <workflowId> --json
Surface a clear instruction to the user with the URL from the output:
▶ MANUAL EXECUTION REQUIRED — <triggerType> trigger (n8nac cannot fire it)
Open n8n UI: <url from `n8nac workflow present`>
Click: "Execute Workflow"
Then paste the execution-id here (top of the execution, or from the URL).
Stop and wait for the user to report the execution-id. Do not fabricate one.
npx n8nac execution get <executionId> --include-data
Read the output and report: success/failure, which node failed (if any), and the relevant
output/error data. If it failed on a wiring error, hand back to /n8n-autopilot:deploy's fix loop.