- Home
- Skills
- Technical Documentation
- Archive old wiki pages
Archive old wiki pages
Distills durable info from old wiki pages into active docs and archives the originals with full reference integrity.
Free
Works with the AI Agents you already use
Archive old wiki pages
Example session with this skill installed
Run wiki archive for all pages older than 3 months. Verify the 100-page floor before starting.
- Read your context and instructions
- Compiled the archive old wiki
I have scanned wiki/pages/ and identified 5 candidates for archiving. 2 pages were skipped due to status: open and 1 was skipped because of an open ## Follow-ups section. I successfully distilled durable decisions into active pages and moved the originals to the archive.
Archive Report
| Candidate | Result | Distilled Content |
|---|---|---|
2023-10-12-auth-session.md | Merged into auth-docs.md | JWT refresh logic and Biome linting rules. |
2023-11-05-db-migration.md | Merged into schema-design.md | Postgres indexing strategy for the orders table. |
2023-08-20-legacy-api.md | No target — archived | None (info superseded by v2 docs). |
2023-09-15-deployment.md | Merged into ci-cd-spec.md | GitHub Actions runner configuration for staging. |
2023-11-10-ui-refactor.md | Merged into design-system.md | Tailwind spacing scale and color palette refs. |
Next steps
- Review
auth-docs.mdto verify the merged JWT rationale. - Manually resolve the 3 pages in the "needs human review" list to clear them for the next archive cycle.
- Check
wiki/archive/to ensure thegit mvoperations correctly preserved history.
2 archived, 3 skipped, 3 needs-human-review.
Connects securely to your tools. The creator never sees your data.
About this skill
Technical debt in documentation builds up quickly, burying architectural decisions under layers of outdated session notes. This skill automates the cleanup of your project wiki by distilling durable information from old pages into active ones and archiving the originals.
What it does
- Automatic aging Identifies pages older than three months using frontmatter dates.
- Durable extraction Distills architectural choices, stable patterns, and external references while discarding session-specific debug narratives.
- Smart merging Transfers useful info into relevant target pages, complete with source attribution and backlink updates.
- Reference integrity Rewrites cross-links in
INDEX.md,QUESTIONS.md, and body text to prevent dangling pointers. - Archive management Relocates retired files to an archive directory using
git mvto preserve version history.
How it works
- Discovery Scans the
wiki/pages/directory to filter candidates based on age, status, and open follow-ups. - Merge planning Analyzes candidates for durable content and identifies the most relevant current pages for integration.
- Execution Updates target frontmatter and body sections before cleaning up all internal wiki references.
- Archiving Moves original files to the archive and updates session mapping files.
Frameworks & tools
This tool operates on standard Markdown files with YAML frontmatter. It requires a specific directory structure (wiki/pages/, wiki/archive/) and uses git mv for file operations.
Why this beats prompting it yourself
Manually tracking every cross-link in a complex wiki is error-prone and tedious. This skill enforces a 100-page safety floor and handles complex reference updates across multiple files that simple prompts often miss.
Use cases
- Pruning a large project wiki that has become difficult to navigate.
- Consolidating scattered architectural decisions into a central source of truth.
- Preparing for a new project phase by archiving old session logs.
- Maintaining documentation hygiene without losing historical context.
Known limitations
Requires specific frontmatter fields like date and status to identify candidates. It will not process pages with open follow-ups or active statuses without human intervention.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.
Requires YAML frontmatter with date and status fields. Skips pages with open follow-ups. Enforces a 100-page minimum in the active directory.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 20 days ago
- Free with an Agensi account