agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/wiki-update/SKILL.md

wiki-update

Skill9 starsChanged 7 months agoMITView on GitHub

Targeted update to a single wiki page (not source-driven like /wiki-ingest). Use when you need to edit, correct, expand, or restructure a specific page based on user feedback or newly-discovered information. Reads the page and its Related links, drafts the change, presents the diff, and applies on approval.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use claude-history-ingest, graph-colorize and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Ivy-Chen1999Skill

    claude-history-ingest

    Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, past conversation logs, local-agent-mode sessions, or audit logs.

    Also in 3 projects that use this

  • Ivy-Chen1999Skill

    graph-colorize

    Color-code the Obsidian graph view by rewriting `.obsidian/graph.json` colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes in Obsidian's graph view tinted by tag, folder, or visibility. Generates a `colorGroups` array from the vault's actual tags/categories and merges it into the existing graph.json without clobbering other graph settings. Always backs up first.

    Also in 3 projects that use this

  • nexuschainsSkill

    cross-linker

    Scans the wiki vault and adds missing [[wikilinks]] between pages that are related but not yet connected. Use this skill when the operator says "link my pages", "find missing links", "cross-reference the wiki", "connect my wiki", "add wikilinks", or after any large ingest to weave new pages into the existing knowledge graph. Also trigger when orphaned pages need connecting or when wiki-lint reports fragmented tag clusters. This is a write-heavy skill — it modifies page files to insert links, unlike wiki-lint which only reports.

    Also in 3 projects that use this

  • nexuschainsSkill

    tag-taxonomy

    Enforces and normalizes tags across the wiki against the controlled vocabulary in wiki/schema/tag-taxonomy.md. Use this skill when the operator says "fix my tags", "normalize tags", "tag audit", "clean up tags", "tag taxonomy", or "my tags are a mess". Also use when creating or updating wiki pages and the right tags are unclear. Operates in three modes: Audit (report current state), Normalize (apply fixes), and Classify (tag a single new page). Always reads the taxonomy file before assigning any tags.

    Also in 3 projects that use this

  • jehrhardtSkill

    wiki-capture

    Quickly capture raw thoughts, links, images, or notes to today's Obsidian daily note from anywhere in Pi. Use when the user wants to jot something down for later wiki processing.

    Also in 3 projects that use this

  • +6 more from Ivy-Chen1999
  • +1 more from nexuschains

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 12 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If argument is a full path, use it directly.

    line 34
  2. Distinctive:

    If the page doesn't exist, offer to:

    line 42
  3. Distinctive:

    Create it as a stub (if user wants to start a new page)

    line 43
  4. Distinctive:

    Check if it should be elsewhere (maybe user meant a different category)

    line 44
  5. Very specific:

    Read every page referenced in the ## Related section.

    line 55
  6. Very specific:

    If the page has an owner: other than wiki-curator, and the edit is domain-specific, delegate to the owner agent for a draft.

    line 71
  7. Distinctive:

    Wait for the owner's draft.

    line 77
  8. Very specific:

    If the edit is purely structural (formatting, cross-references, frontmatter), wiki-curator can handle it directly.

    line 79
  9. Distinctive:

    Before presenting the change, verify:

    line 93
  10. Very specific:

    No new broken [[wikilinks]] introduced

    line 97
  11. Distinctive:

    If the edit adds or removes cross-references:

    line 102
  12. Very specific:

    Update wiki/index.md if the page's status changed (stub → complete, etc.) or title changed

    line 141
  13. Distinctive:

    After the update, run a quick sanity check on the affected pages:

    line 155
  14. Distinctive:

    If any issues, report them and offer to fix in a follow-up update.

    line 160
  15. Very specific:

    If the user requests updates to multiple pages (e.g., "add [[trove-cleanup]] to Related on all combat pages"), batch them:

    line 164
  16. Distinctive:

    Read the raw source(s) that justified the upgrade

    line 178
  17. Distinctive:

    Write the full content per the schema's required sections

    line 179
  18. Distinctive:

    Run the standard diff/approval flow

    line 182

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/wiki-update — Targeted Page Edit

Delegate to: wiki-curator (which may delegate to the page's owner)

Arguments

  • <page> — wiki page path (e.g., wiki/services/DataStoreService.md or just DataStoreService)
  • [note] — optional reason or description of the change

When to Use

  • User spotted an inaccuracy on a page
  • Owner agent wants to refine their page without a new source
  • Schema change requires touching multiple pages
  • Contradiction resolution
  • Adding missing cross-references
  • Upgrading a stub to complete status

When NOT to Use

  • Ingesting a new raw source → use /wiki-ingest instead
  • Fixing lint issues → use /wiki-lint --fix
  • Creating a brand-new page for a topic from scratch with no source → write a proper page via /wiki-ingest with a raw source first

Workflow

1. Resolve the Page

If argument is a full path, use it directly. Otherwise, search for the page:

find wiki/ -name "*<arg>*.md" -not -path "wiki/raw/*"

Handle ambiguity: if multiple matches, list them and ask user to disambiguate.

If the page doesn't exist, offer to:

  1. Create it as a stub (if user wants to start a new page)
  2. Check if it should be elsewhere (maybe user meant a different category)

2. Read the Page

Load the full page. Note:

  • owner:, status:, sources:, updated: from frontmatter
  • Current structure (which sections exist)
  • Current Related links

3. Read Related Pages

Read every page referenced in the ## Related section. Skim their content to understand the context.

Also load wiki/SCHEMA.md to ensure the edit complies with the schema.

4. Understand the Requested Change

Parse the user's intent:

  • Correction — "this is wrong, fix it"
  • Expansion — "add info about X"
  • Restructure — "split this page" or "merge these sections"
  • Cross-reference — "link to Y"
  • Status upgrade — "this stub should be complete now"
  • Schema conformance — "add missing required sections"

5. Delegate to Owner (If Appropriate)

If the page has an owner: other than wiki-curator, and the edit is domain-specific, delegate to the owner agent for a draft. Pass the owner:

  • The current page content
  • The requested change
  • Any relevant Related page content
  • The schema section for the page type

Wait for the owner's draft.

If the edit is purely structural (formatting, cross-references, frontmatter), wiki-curator can handle it directly.

6. Draft the Change

Produce the edit. Options:

In-place edit: For small changes, use Edit with old_string → new_string.

Section rewrite: For larger changes within a section, present the new section content.

Full page rewrite: For major restructures, present the full new page content.

7. Validate Against Schema

Before presenting the change, verify:

  • Frontmatter still valid (all required fields present)
  • H1 still matches title:
  • Required sections still present (unless converting to stub)
  • No new broken [[wikilinks]] introduced
  • updated: timestamp will be bumped to today

8. Update Related Links

If the edit adds or removes cross-references:

  • For each added link: verify the target page exists (create stub if needed)
  • For each added link: add reverse link in the target's Related section
  • For each removed link: remove reverse link in the target's Related section

9. Present Diff to User

# Update Proposal: [[<Page Title>]]

**Reason:** <user's note>
**Owner:** <agent>
**Change size:** <small | medium | large>
**Schema check:** ✅ valid

## Diff

<show the before/after — for small edits, inline; for large, in a code fence>

## Side Effects

- Related page `[[X]]` will get a new back-link in its Related section
- Frontmatter `updated:` will change from 2026-03-10 → 2026-04-16
- `sources:` will <be unchanged | gain a new citation>

## Approval needed

Proceed?

10. Wait for Approval

On approval, apply the change and any side effects.

11. Apply the Update

  1. Edit the target page
  2. Bump updated: in frontmatter to today
  3. Apply Related link side effects on other pages
  4. Update wiki/index.md if the page's status changed (stub → complete, etc.) or title changed

12. Append to Log

## [YYYY-MM-DD] update | [[<Page Title>]]
- Reason: <note>
- Change: <one-line summary>
- Status: <old status> → <new status> (if changed)
- Side effects: <pages with added/removed back-links>

13. Run a Mini-Lint

After the update, run a quick sanity check on the affected pages:

  • Frontmatter still valid
  • Required sections still present
  • All wikilinks resolve

If any issues, report them and offer to fix in a follow-up update.

Batch Updates

If the user requests updates to multiple pages (e.g., "add [[trove-cleanup]] to Related on all combat pages"), batch them:

  1. Collect all target pages
  2. Draft changes for each (in parallel if simple, delegated if complex)
  3. Present combined diff
  4. One approval, one application pass
  5. One log entry per page, or one grouped entry if the changes are uniform

Stub → Complete Upgrade Pattern

A common update: converting a stub page to a complete page, usually after a new source was ingested.

Workflow:

  1. Read the stub
  2. Read the raw source(s) that justified the upgrade
  3. Write the full content per the schema's required sections
  4. Change status: stub → status: complete
  5. Add sources: citations
  6. Run the standard diff/approval flow

Anti-Patterns

  • ❌ Do not edit a page without reading it fully first
  • ❌ Do not break wikilinks (either resolve new links to real pages or create stubs)
  • ❌ Do not skip the Related link side-effects (bidirectional links must stay consistent)
  • ❌ Do not forget to bump updated:
  • ❌ Do not merge domain-specific edits without delegating to the owner
  • ❌ Do not silently resolve contradictions — those require explicit approval

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.