Confluence

Skill ngocsangyem/MeowKit/.claude/skills/confluence

Production ready. AI Agent Workflow System for Claude Code

Install

npx -y skills add ngocsangyem/MeowKit --skill confluence

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Routing skill — recommends the correct mk:confluence-* leaf for any Confluence Cloud task. Triggers: 'confluence', 'wiki page', 'spec page', ambiguous Confluence intent. NOT an executor — every actual operation forks via a leaf skill.

SKILL.md

5.0 KB, as published. Nobody here has run it

mk:confluence — Routing Skill

This skill is a pure routing layer. Its sole purpose: identify the right mk:confluence-* leaf for the user's Confluence task, then point at it. No execution.

Routing Table

User intent	Leaf skill
Get/create/update/delete a single page or blog post; copy/move/version	`mk:confluence-page`
Search pages with CQL; list spaces; export results	`mk:confluence-search`
Deep spec analysis: requirements, gaps, suggested stories	`mk:confluence-spec-analyst`
Bulk ops on 10+ pages (label, move, delete) — dry-run mandatory	`mk:confluence-bulk`
Comments, attachments, labels, watchers (collaboration surface)	`mk:confluence-collaborate`

Disambiguation

User says skill name verbatim → route immediately
Numeric token (likely page ID) + verb → match verb to leaf
Uppercase short token (likely space key) + read intent → mk:confluence-search
CQL syntax (=, AND, OR, currentUser()) → mk:confluence-search
10+ items / bulk / batch / mass keyword → mk:confluence-bulk
Spec analysis intent (requirements, acceptance criteria, analyze the spec) → mk:confluence-spec-analyst
Labels: mk:confluence-collaborate owns label CRUD (add/remove/list). mk:confluence-page does NOT duplicate — if user says "label page X", route to collaborate.
Comments / attachments / watchers: always mk:confluence-collaborate, even if scoped to a single page
Truly ambiguous → ask user one clarifying question

Setup

See references/install-and-auth.md for one-time setup (.claude/scripts/bin/setup-workflow installs confluence-assistant-skills into .claude/skills/.venv per scripts/requirements.txt; populate .meowkit/.env with the 3 MEOW_CONFLUENCE_* vars).

Shared Resources (used by leaves)

scripts/confluence-as.sh — env-translating wrapper (MEOW_CONFLUENCE_* → CONFLUENCE_*, sets CONFLUENCE_OUTPUT=json, refuses settings.local.json fallback, gates non-Cloud URLs)
scripts/cql-sanitize.sh — CQL injection guard for user-derived input
scripts/adf-to-md.sh + scripts/adf_to_md.py — macro-aware ADF→Markdown walker (panel, decisionList/Item, taskList/Item, expand, mention, media, inlineCard preserved with explicit labels)
scripts/requirements.txt — pip dependency manifest auto-discovered by .claude/scripts/bin/setup-workflow
scripts/smoke-live.sh — manual live-creds smoke test
references/install-and-auth.md — env vars, setup, Cloud-only gate, escape hatch
references/cli-idioms.md — wrapper invocation patterns + safe-invocation rules + conversion-helper idioms

Handoff

mk:planning-engine accepts --spec <report-path> flag pointing at an existing mk:confluence-spec-analyst report; user runs spec-analyst FIRST, then passes path
mk:intake recognizes Confluence URL/page-id as a 5th source; fetches page content directly via wrapper, does NOT auto-invoke spec-analyst
mk:jira → sister hub for Jira ticketing; spec-analyst report pairs with mk:jira-issue create to turn extracted user stories into tickets (manual review required, --with-commands is opt-in)
No write-back from mk:cook — Confluence write paths are out of scope

Gotchas

mk:confluence itself never executes; if you're in this skill thinking about wrapper commands, you're in the wrong place — forward to a leaf.
Binary name is confluence-as (NOT confluence despite some upstream README docs). The wrapper handles this; leaves call the wrapper.
Cloud-only — wrapper exits 3 on non-*.atlassian.net URLs. For Server/DC, users invoke MCP Atlassian directly per references/install-and-auth.md. Hub does NOT auto-fallback.