Menu
Move completed features from wip to archive
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Implementation planning with optional adversarial cross-review (Claude Code ⇄ Codex). Tasks are sequential vertical slices, each carrying its own testable behaviors. Pass --visual to also render the plan as a self-contained HTML page (PLAN.html). Pass --skills <skills> to preload skills that shape the plan and that execute loads before coding
Execute all fixes from a REVIEW.md — address warnings, blocking issues, and gaps found during review
Test-driven execution loop — one task at a time, red→green→refactor, atomic commits
Plan vs implementation verification with goal-backward analysis and test-quality audit
Socratic interview that captures domain language, decisions, and ADRs inside .neural/wip/<feature>/
Harvest knowledge from archived features into .neural/knowledge/ — run after archiving a feature, or invoke manually to rebuild the project knowledge base
| name | neural-archive |
| description | Move completed features from wip to archive |
Move completed features from .neural/wip/ to .neural/archive/.
Check for active features. List all directories in .neural/wip/. If none exist, report: "No active features in .neural/wip/. Nothing to archive." and stop.
Select the feature to archive.
.neural/wip/<name>/. If not found, list available features and ask the user to pick one.<name>? (y/n)"Move the feature directory. Run:
mkdir -p .neural/archive/
mv .neural/wip/<name>/ .neural/archive/<name>/
Confirm completion. Report:
Feature '<name>' archived. .neural/wip/<name>/ → .neural/archive/<name>/
Update the knowledge base. Run /neural:neural-learn to harvest the newly archived feature into .neural/knowledge/.