Managing Workflows
SkillDev toolsLets your agent create, validate, activate, or retire TraceDecay workflows and control or hand off running ones.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Managing Workflows skill
About this skill
Register, validate, activate, or retire TraceDecay Workflow definitions; issue handoffs or control an existing Workflow run.
What this skill tells your AI
The instructions your AI receives, as published by scriptedalchemy/tracedecay in plugin/skills/managing-workflows/SKILL.md and read by ahel’s review.
Validate a definition before registering it
(tracedecay_workflow_register_definition) and activating it
(tracedecay_workflow_activate_definition); rejection and
retirement (tracedecay_workflow_reject_definition,
tracedecay_workflow_retire_definition) are typed lifecycle transitions, not
deletions. Mutations consume the exact definition or run identity returned by a
read or registration; a name, label, or filesystem path is not authority.
Handoff redemption (tracedecay_workflow_handoff_redeem) consumes the grant
tracedecay_workflow_handoff_issue returned, never an invented grant identity.
Starting a run (tracedecay_workflow_start_run) differs from controlling an
existing run (tracedecay_workflow_pause_run, tracedecay_workflow_resume_run,
tracedecay_workflow_cancel_run). Preserve typed state when pausing, resuming,
or canceling, and inspect terminal effects before retrying an interrupted
request. Use live operation schemas for available arguments.
tracedecay_workflows retrieves historical wf_* session runs; it does not
control Workflow definitions or execution. Use managing-session-context for
that history and managing-work for task/attempt/placement operations.
Signals
- GitHub stars
- 77
- Forks
- 6
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
managing-workflows- Source
- github.com/scriptedalchemy/tracedecay