task-lifecycle-workflow
Run a full evidence-to-completion lifecycle for long, correction-heavy, multi-artifact, or release-bound work. Use when asked to "coordinate dependent work", "preserve cumulative requirements", "recover off-rails work", "cold-read the result", or "continue until fully ready". Do not use for planning alone, factual answers, typos, or reversible one-owner work with one check; use Autorun's focused plan skills for those.
- Version
- 0.8.0
- License
- Apache-2.0
Pinned to revision 78cda181b69f, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/task-lifecycle-workflow/SKILL.md
- skills/task-lifecycle-workflow/agents/openai.yaml
- skills/task-lifecycle-workflow/references/compatibility-and-validation.md
- skills/task-lifecycle-workflow/references/continuity-recovery-and-gates.md
- skills/task-lifecycle-workflow/references/off-rails-recovery.mmd
- skills/task-lifecycle-workflow/references/orchestration-and-state.md
- skills/task-lifecycle-workflow/references/outer-lifecycle.mmd
- skills/task-lifecycle-workflow/references/planning-delegation-and-joins.md
- skills/task-lifecycle-workflow/references/qualitative-coding-pipeline.mmd
- skills/task-lifecycle-workflow/references/qualitative-coding.md
- skills/task-lifecycle-workflow/references/role-packets-and-messages.md
- skills/task-lifecycle-workflow/references/sources.md
- skills/task-lifecycle-workflow/references/work-cycle.mmd
- skills/task-lifecycle-workflow/scripts/check_workflow.py
Every link opens the file at its source, pinned to the revision this page describes.