# Pocdd Archive

> Archive a done POC out of the active set but keep it as a parity/regression oracle, moving it under .pocs/archive/. Use for "/poc archive <name>" after implementation.

- Skill: `dailybothq/pocdd-archive` (Agent Skill)
- Install (CLI): `npx skillmds@latest add dailybothq/pocdd-archive`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dailybothq/pocdd-archive/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: dailybothq (https://skillmd.com/u/dailybothq)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dailybothq/pocdd-archive

---


# POCDD — Archive

Retain a POC as a parity oracle without cluttering the active list. Resolve it
with `pocdd_resolve <name>` from [`../shared/context.sh`](../shared/context.sh).

## Procedure

1. Confirm the POC exists and report its current phase.
2. Move it into an `archive/` subfolder of `.pocs/` (still gitignored):
   ```bash
   . "$(dirname "$0")/../shared/context.sh"
   dir="$(pocdd_dir)"; mkdir -p "$dir/archive"
   mv "$(pocdd_resolve <name>)" "$dir/archive/"
   ```
3. Report the new location and that it remains usable as a regression check
   ("did the provider change its JSON shape?") — runnable POCs especially.

Prefer **archive** over **remove** when the external API is volatile, the POC is
still useful for onboarding, or integration tests don't yet cover its signal.