index-refresh
Keeps your wiki's index synchronized with its actual contents by walking the directory structure, spotting orphaned pages in the log, and reconciling deletions. Produces a clean, sorted index with one-line summaries per page—no dates or metadata clutter—and records all changes in the log for audit trails.
index-refresh rebuilds your wiki's index file to match the actual directory structure and log entries.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
index-refresh rebuilds your wiki's index file to match the actual directory structure and log entries. Keeps your wiki's index synchronized with its actual contents by walking the directory structure, spotting orphaned pages in the log, and reconciling deletions. Produces a clean, sorted index with one-line summaries per page—no dates or metadata clutter—and records all changes in the log for audit trails.
Use it when
- index-refresh reconciles missing or deleted wiki pages by comparing the index against actual files on disk.
- Yes.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
paperclipai/paperclip/index-refresh · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I rebuild wiki index from directory structure?
index-refresh walks your wiki's directory structure to rebuild the index from scratch. It scans all actual pages, generates a clean sorted index with one-line summaries per page, and logs every change. This ensures your index matches reality without manual editing of page content.
What does index-refresh do when pages are deleted?
index-refresh reconciles missing or deleted wiki pages by comparing the index against actual files on disk. It spots orphaned entries in the log, removes them from the index, and records the deletion. This keeps your navigation accurate and prevents broken links.
Can index-refresh sync wiki index with actual pages automatically?
Yes. index-refresh automates wiki index updates without touching page content. It detects new pages, removes deleted ones, and maintains accurate wiki navigation and discoverability—all through directory scanning and log reconciliation, no manual intervention needed.
Does index-refresh log changes for audit purposes?
index-refresh records all index changes in the log and verifies structural integrity. Every rebuild, deletion, and sync operation is tracked, giving you an audit trail of what changed and when—useful for debugging index drift or reviewing maintenance history.
What format does index-refresh produce for the wiki index?
index-refresh generates a clean, sorted index with one-line summaries per page—no dates or metadata clutter. The output is designed for easy navigation and discoverability, keeping your wiki's index file lean and readable while staying synchronized with actual directory contents.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Index Refresh
Keep wiki/index.md accurate and scannable. The index is the maintainer's first stop for navigation — its quality determines how cheap every subsequent operation becomes.
Inputs
- An operation issue with
operationType: "index"(or theindex-refreshroutine title). - The operation issue's target
wikiId,spaceSlug, and space root. Refresh only that space unless the issue explicitly says this is a multi-space sweep.
Workflow
- Read the target space's
wiki/index.mdas it currently stands. - Walk the target space's
wiki/.wiki/projects/<slug>/standup.mdentries are current-state companions for durablewiki/projects/<slug>/index.mdpages; index them only as links attached to the matching project entry. Walkwiki/by category (sources/,projects/,entities/,concepts/,synthesis/, plus any custom subdirectories the wiki schema added). - **Read the target space's last ~50 entries of
(truncated - see the full file via the links below)
File tree — 1 file
packages/plugins/plugin-llm-wiki/skills/index-refresh/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Rebuild and synchronize wiki index from actual directory structure”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill keeps your wiki's index accurate and current by walking the actual file structure, comparing against recent log activity, and rebuilding entries in scannable one-line format. It reconciles missing pages, drops deleted entries, and preserves custom categories—without touching page content itself.
Wiki Lint scans a wiki space to surface seven classes of structural and content issues: contradictions between pages, stale claims, orphaned pages, concept gaps, broken wiki-links, weak provenance, and index drift. It returns a severity-grouped triage list with evidence and suggested fixes, but never modifies wiki content—leaving all decisions to the maintainer.
LLM Wiki Maintainer helps you keep a company wiki organized and current using dedicated plugin tools. It handles source ingestion, page updates, index maintenance, and structural validation while enforcing citation discipline and immutable raw sources.
Wiki Lint performs read-only audits of wiki spaces, surfacing contradictions, orphaned pages, stale claims, concept gaps, broken links, and provenance issues. It returns a severity-grouped triage list with evidence and suggested fixes, leaving all decisions to the maintainer.
Paperclip Distill transforms project, issue, comment, and document activity from Paperclip into structured wiki pages that tell the story of what happened, what was decided, and what matters next. It produces executive standups and project indexes designed for readers unfamiliar with the source material, emphasizing interpretation and context over raw issue lists or dated status dumps.
wiki-ingest automates the transformation of a single source document into a structured wiki by creating and linking source, entity, concept, and synthesis pages. It reads your space's conventions, flags contradictions with existing content, and maintains a log of all ingestions. The skill ensures every claim traces back to its origin and all cross-references stay current.
More skills wiki-query (MIT) · wiki-ingest (MIT) · Wiki Query (MIT)