skills/confluence-to-wiki/SKILL.md
Pull a Confluence page into an llm-wiki vault as a source-note via the wiki's /ingest convention. One-way (Confluence → wiki), defaults to llm-wiki-simplicity-taskforce-partnership. Use when partner-shared research in Confluence needs to live in the wiki for query, synthesis, or cross-vault linking. Pairs with /ro:confluence and /ingest.
npx skillsauth add RonanCodes/ronan-skills confluence-to-wikiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Mirrors a Confluence page (or page tree) into an llm-wiki-* vault as a source-note. Conforms to the wiki's /ingest source-note conventions: frontmatter, inline ## Sources section, and the canonical wiki page-type fields.
One-way: changes in Confluence are reflected by re-running this skill; changes in the wiki do not flow back. The Confluence page remains the source of truth for partner-shared content.
/ro:confluence-to-wiki 123456789
/ro:confluence-to-wiki https://simplicitylabs.atlassian.net/wiki/spaces/dataforce/pages/123456789/Inventory+sync+algorithm+v2
/ro:confluence-to-wiki 123456789 --vault llm-wiki-simplicity-taskforce-partnership
/ro:confluence-to-wiki 123456789 --with-children # pull the page and all descendants
Default vault: llm-wiki-simplicity-taskforce-partnership (matches the dataforce Confluence space).
/ro:confluence for setup)$LLM_WIKI_DIR/vaults/<vault-name>/ (resolve the wiki repo via bash "${CLAUDE_PLUGIN_ROOT:-$HOME/Dev/ronan-skills}/scripts/resolve-repo.sh" LLM_WIKI). If not, run /vault-create first.getConfluencePage). Get title, body, last-updated, author, space, parent.vaults/<vault>/wiki/sources/confluence-<page-id>-<slug>.md:
---
title: <Confluence page title>
page-type: source-note
source-type: confluence
source-url: <full Confluence URL>
source-id: <page-id>
source-space: <space-key>
author: <Confluence author display name>
created: <ISO date>
updated: <ISO date — Confluence last-modified>
mirrored: <today's ISO date>
domain: <vault default domain>
tags: [confluence, partnership]
sources:
- <full Confluence URL>
related: []
---
# <Confluence page title>
> Mirrored from Confluence on <date>. Source of truth: <URL>
<converted body as markdown>
## Sources
- [<page title>](<full Confluence URL>) — Confluence page, space `<space-key>`, last updated <date>
vaults/<vault>/log.md:
- <date>: mirrored Confluence page "<title>" (<id>) → wiki/sources/confluence-<id>-<slug>.md
--with-children: recurse, mirroring each descendant. Link parent ↔ children in the related: frontmatter array.obsidian://open URL so the user can jump straight in.The Atlassian MCP typically returns Confluence content as ADF (Atlassian Document Format) or markdown. Convert to clean wiki markdown:
<ac:image> macros →  (download the image to vaults/<vault>/wiki/assets/ and rewrite the URL to relative)> Embedded Confluence: <url> blockquote@<display name> (lookup their actual entity page in the vault is out-of-scope for v1)If conversion is lossy enough that the page reads badly, fall back to including the raw ADF JSON as a code block at the bottom of the source-note and flag in the body: > Raw ADF preserved below — markdown conversion was partial.
/ingest/ro:confluence-to-wiki — for pages already in Confluence. Wiki-side becomes a mirror. Re-run to refresh./ingest <url> with a Confluence URL — should route here automatically once the confluence: source-type handler is added to the wiki's /ingest router. Until then, this skill is the explicit path./ro:confluence create — when authoring NEW content that needs to live in Confluence (partner-facing). After publishing, optionally mirror back to the wiki via this skill if it's worth querying.| Symptom | Cause | Fix |
|---|---|---|
| "No atlassian MCP tools" | OAuth not done | /mcp → browser auth |
| "Vault not found" | Target vault doesn't exist | Run /vault-create <name> first |
| Body conversion mangles tables | ADF table → markdown is lossy for complex tables | Include raw ADF block as fallback (see above) |
| Page has restricted access | OAuthed user doesn't have view permission on the page | Have the page owner share it, or use an account with broader access |
/ro:confluence — page CRUD inside Confluence/ingest — wiki's generic ingestion router (will get a confluence: handler hooked in separately)/promote — graduate a Confluence-sourced page from this Spoke vault into llm-wiki-research (Hub) if it's reusable knowledgellm-wiki-simplicity-taskforce-partnership — default target vaulttesting
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".