Internal fetcher module for Confluence pages. Fetches content via Atlassian MCP (preferred), REST API with Basic Auth (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:teach and /bedrock:sync — not intended for direct user invocation.
SkillScore59Maintained
Automatic
◆Knowledge Management pack
Last verified 9/24/2026
What it changes
Passed 10 of 17 test cases with the skill, and 4 of 17 without it.
Without skill23%
With skill59%
Checks it passed that the model alone missed
Calls window.__confluence.chunk for chunk index 0.
Calls window.__confluence.chunk for chunk index 1.
Calls window.__confluence.chunk for chunk index 2.
and 8 more in the full report
8 fixed5 passed either way9 still failing0 broke
Pass-rate lift
+36 pp
Tokens
+92%
Agent turns
0%
Response time
-62%
Model gemini-3.6-flashMeasured 9/24/2026v113 of 22 cases passed with skill · 17 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
ToolSearch found `mcp__plugin_atlassian_atlassian__authenticate` and `complete_authentication`, but no direct page fetch tools. What action should be taken before falling back to Layer 2 REST API?
What was checked, without and with the skill
Checked
Without skill
With skill
Guides user to run mcp__plugin_atlassian_atlassian__authenticate for OAuth flow.
Passed
Passed
Asks user whether to authenticate MCP or skip to API fallback.
Missed
Passed
case-15 · gemini-3.6-flash · 9/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md293 lines2 filesincludes scripts
Confluence Fetcher
Internal module — invoked by /bedrock:teach Phase 1 and /bedrock:sync Phase 2, not user-invocable.
Fetches a Confluence page and returns its content as Markdown. Three layers in fallback order:
MCP (preferred) → REST API → Browser DOM extraction.
Dependency: Browser fallback (Layer 3) requires scripts/extract.js (relative to this skill directory).