How do I install the Openspec Archive skill?

Run npx skillmds@latest add nklofy/openspec-archive in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Openspec Archive safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openspec Archive?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openspec Archive free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openspec Archive?

nklofy (@nklofy) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openspec Archive by nklofy — Agent Skill

Name: Openspec Archive
Rating: 4.2 (5 reviews)
Author: nklofy

File contents

OpenSpec Archive

Purpose

Finalize a completed OpenSpec change by moving it to the archive only when it is safe to do so.

This skill is the lifecycle closing step. It should not implement new work or perform complex spec edits unless the user explicitly asks for pre-archive fixes.

When To Invoke

Invoke when the user asks to:

archive a change
finalize a completed change
move a change to archive/
complete the OpenSpec lifecycle
clean up after implementation and spec sync

Inputs

Useful inputs include:

change name
whether incomplete tasks are accepted
whether spec sync should be required before archive
archive date or default current date

Repository Files

This skill reads:

openspec/changes/<change-name>/tasks.md
openspec/changes/<change-name>/proposal.md
openspec/changes/<change-name>/design.md
openspec/changes/<change-name>/specs/**/spec.md
openspec/specs/**/spec.md

This skill moves:

openspec/changes/<change-name>/
to openspec/changes/archive/YYYY-MM-DD-<change-name>/

Procedure

Identify the target change.
Check whether the change is already archived.
Inspect tasks.md for incomplete items.
Check whether approved change specs still need syncing.
Verify no obvious artifact contradiction remains.
Ask for confirmation if tasks are incomplete or sync is skipped.
Move the change directory into archive.
Report the archive path and final status.

Decision Rules

Do not archive incomplete tasks unless the user explicitly accepts them.
Do not archive when required spec sync is pending unless the user explicitly skips it.
If the archive target already exists, ask before choosing a new path.
If the change is already archived, report that state instead of moving it again.

Guardrails

Do not delete change history.
Do not silently skip unresolved work.
Do not implement feature code.
Do not perform broad spec rewrites.
Preserve archive path clarity with a date prefix.

Output Format

Using change: <change-name>
Status: ready-to-archive

Archived to:
- openspec/changes/archive/YYYY-MM-DD-<change-name>/

Skipped or warnings:
- <item or none>

Next action: <recommended next step>

Examples

User: "Archive add-user-auth."

Action: check tasks and spec sync state, then move the change to the dated archive directory if safe.

---name: openspec-archivedescription: Archives completed OpenSpec changes safely. Invoke when tasks are done and the user wants to finalize a change.---# OpenSpec Archive## PurposeFinalize a completed OpenSpec change by moving it to the archive only when it is safe to do so.This skill is the lifecycle closing step. It should not implement new work or perform complex spec edits unless the user explicitly asks for pre-archive fixes.## When To InvokeInvoke when the user asks to:- archive a change- finalize a completed change- move a change to `archive/`- complete the OpenSpec lifecycle- clean up after implementation and spec sync## InputsUseful inputs include:- change name- whether incomplete tasks are accepted- whether spec sync should be required before archive- archive date or default current date## Repository FilesThis skill reads:- `openspec/changes/<change-name>/tasks.md`- `openspec/changes/<change-name>/proposal.md`- `openspec/changes/<change-name>/design.md`- `openspec/changes/<change-name>/specs/**/spec.md`- `openspec/specs/**/spec.md`This skill moves:- `openspec/changes/<change-name>/`- to `openspec/changes/archive/YYYY-MM-DD-<change-name>/`## Procedure1. Identify the target change.2. Check whether the change is already archived.3. Inspect `tasks.md` for incomplete items.4. Check whether approved change specs still need syncing.5. Verify no obvious artifact contradiction remains.6. Ask for confirmation if tasks are incomplete or sync is skipped.7. Move the change directory into archive.8. Report the archive path and final status.## Decision Rules- Do not archive incomplete tasks unless the user explicitly accepts them.- Do not archive when required spec sync is pending unless the user explicitly skips it.- If the archive target already exists, ask before choosing a new path.- If the change is already archived, report that state instead of moving it again.## Guardrails- Do not delete change history.- Do not silently skip unresolved work.- Do not implement feature code.- Do not perform broad spec rewrites.- Preserve archive path clarity with a date prefix.## Output Format```textUsing change: <change-name>Status: ready-to-archiveArchived to:- openspec/changes/archive/YYYY-MM-DD-<change-name>/Skipped or warnings:- <item or none>Next action: <recommended next step>```## ExamplesUser: "Archive add-user-auth."Action: check tasks and spec sync state, then move the change to the dated archive directory if safe.

Frequently asked questions

Openspec Archive