plugin-src/shared/skills/orchestrate/SKILL.md
Run the flowai-workflow orchestration policy loop. Delegates policy execution to the workflow orchestrator agent, which selects workflows from ORCHESTRATION.md and supervisor summaries.
npx skillsauth add korchasa/flowai-workflow orchestrateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Start or continue a project-local flowai-workflow orchestration loop. This is
the public entry point and dispatch bridge. Policy decisions belong to
orchestrator; run recovery belongs to
supervisor.
orchestrator with the host's real subagent
mechanism:
Agent / Task tool with
subagent_type=orchestrator;@orchestrator <task prompt> mention
syntax.worker subagent (the parent dispatches; Codex
max_depth=1 forbids nested spawns) and instruct it — by skill name —
to invoke the orchestrator skill and return the SUPERVISOR_DELEGATION
block as its final message. The worker, not the parent, performs all
policy reads.STOP: <reason>; orSUPERVISOR_DELEGATION block with workflow path, optional run id,
reason, and requested short-result fields.SUPERVISOR_DELEGATION, launch supervisor
from the parent context using the real subagent mechanism:
Agent / Task with
subagent_type=supervisor;@supervisor <task prompt>.worker subagent and instruct it — by skill
name — to invoke the supervisor skill with the delegation prompt and
return the SUPERVISOR_REPORT block.workflow, run_id, status, fixes, repeat, blocker.Pass the orchestrator:
If the host has neither a native subagent mechanism (Claude subagent_type,
OpenCode @mention) nor Codex-style worker dispatch, say that
context-isolated orchestration is unavailable in this IDE and stop. Do not
inline the loop in the parent context. Do not simulate delegation with bash,
echo, heredocs, or placeholder text.
The parent session may identify that .flowai-workflow/ exists, but must not:
.flowai-workflow/ORCHESTRATION.md deeply;runs/, state.json, journal.jsonl, logs/, or node
artifacts;flowai-workflow directly for a selected workflow.Those actions belong to the orchestrator subagent and, for a single run, the supervisor subagent. The parent only dispatches between them because some hosts do not allow nested subagent calls.
Ask the orchestrator to report:
.flowai-workflow/orchestration.jsonl;development
Supervisor for one flowai-workflow run (Codex). Starts or resumes a single workflow, diagnoses failures from run artifacts, patches root causes, resumes the same run. Run inside an isolated Codex worker subagent spawned by the `supervise`/`orchestrate` skill.
development
Long-cycle flowai-workflow orchestrator (Codex). Reads project orchestration policy, selects the next workflow, and returns a structured supervisor delegation request. Run inside an isolated Codex worker subagent spawned by the `orchestrate` skill.
data-ai
Live flowai-workflow run supervisor. Use only for requests to run, monitor, continue, or resume a current workflow now. Exclude last-night, finished, post-mortem, root-cause-report, and conceptual questions.
data-ai
Scaffold or adapt flowai-workflow DAGs in a project. Use for adding flowai-workflow, adapting an existing .flowai-workflow/<name>, validating workflow.yaml, or wiring agent prompts/scripts.