confluence-to-markdown

Name: confluence-to-markdown
Author: iurykrieger

82stars8forks

How to install confluence-to-markdown?

iurykrieger/claude-bedrock/confluence-to-markdown

$npx -y skills add iurykrieger/claude-bedrock --skill confluence-to-markdown

Installs into the current project.

Summary

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:learn and /bedrock:sync — not intended for direct

Files · 1

View on GitHub

SKILL.md

1	# Confluence Fetcher
2
3	Internal module — invoked by `/bedrock:learn` Phase 1 and `/bedrock:sync` Phase 2, not user-invocable.
4
5	Fetches a Confluence page and returns its content as Markdown. Three layers in fallback order:
6	MCP (preferred) → REST API → Browser DOM extraction.
7
8	Dependency: Browser fallback (Layer 3) requires `scripts/extract.js` (relative to this skill directory).
9
10	---
11
12	## Step 1 — Parse URL
13
14	Parse the Confluence URL. Accept these formats:
15	- `https://<domain>.atlassian.net/wiki/spaces/<spaceKey>/pages/<pageId>/<title>`
16	- `https://<domain>.atlassian.net/wiki/spaces/<spaceKey>/pages/<pageId>`
17	- `https://<domain>.atlassian.net/wiki/x/<shortlink>`
18	- `https://<domain>.atlassian.net/wiki/pages/viewpage.action?pageId=<pageId>`
19
20	Extract:
21	- Base URL: `https://<domain>.atlassian.net` (everything before `/wiki/...`)
22	- Page ID: the numeric ID from the URL path (segment after `/pages/`) or `pageId` query parameter
23	- Full URL: the original URL as provided (needed for browser fallback)
24
25	---
26
27	## Step 2 — Layer 1: MCP (Atlassian)
28
29	The preferred layer. Uses the `plugin:atlassian:atlassian` MCP server if installed and authenticated.
30
31	### 2.1 Check MCP availability
32
33	Use ToolSearch to check if Atlassian MCP tools are available:
34
35	```
36	ToolSearch(query: "atlassian confluence page", max_results: 5)
37	```
38
39	Evaluate the result:
40
41	- MCP tools found and functional (tools other than `authenticate` and `complete_authentication` are available) → proceed to 2.2 Fetch via MCP
42	- Only `authenticate` / `complete_authentication` tools found (MCP installed but not authenticated) → proceed to 2.3 Guide authentication
43	- No Atlassian MCP tools found → log and fall through:
44
45	> MCP not available: No Atlassian MCP server installed.
46	> Install the Atlassian MCP plugin for Claude Code to enable direct Confluence access.
47	> Falling back to API (Layer 2).
48
49	### 2.2 Fetch via MCP
50
51	Use the Atlassian MCP tools to fetch the page content. The specific tool depends on what the MCP exposes after authentication (typically a page read or content retrieval tool).
52
53	Call the MCP tool passing the page ID or URL. The MCP returns the page content directly.
54
55	- Success → convert content to Markdown if not already, proceed to Output Contract
56	- Error → log the error and fall through to Layer 2:
57
58	> MCP fetch failed: {error message}.
59	> Falling back to API (Layer 2).
60
61	### 2.3 Guide authentication
62
63	If the MCP is installed but not authenticated, guide the user:
64
65	> MCP not authenticated: The Atlassian MCP server is installed but requires authentication.
66	> Run `mcp__plugin_atlassian_atlassian__authenticate` to start the OAuth flow, then complete it in your browser.
67	> After authentication, Confluence pages can be fetched directly via MCP.
68
69	Ask the user: "Would you like to authenticate the Atlassian MCP now, or skip to API fallback (Layer 2)?"
70
71	- User wants to authenticate → invoke `mcp__plugin_atlassian_atlassian__authenticate`, wait for the user to complete the OAuth flow, then retry 2.2 Fetch via MCP
72	- User declines → log "User declined MCP authentication, falling to Layer 2" → continue to Step 3
73
74	---
75
76	## Step 3 — Layer 2: API (REST)
77
78	Uses the Confluence REST API with Basic Auth (API token + email).
79
80	### 3.1 Check credentials
81
82	```bash
83	echo "CONFLUENCE_API_TOKEN: ${CONFLUENCE_API_TOKEN:+set}" && echo "CONFLUENCE_USER_EMAIL: ${CONFLUENCE_USER_EMAIL:+set}"
84	```
85
86	- Both set → proceed to 3.2 Compute auth header
87	- Either missing → guide and fall through:
88
89	> API not available: `CONFLUENCE_API_TOKEN` or `CONFLUENCE_USER_EMAIL` environment variable is not set.
90	> Generate an API token at https://id.atlassian.com/manage-profile/security/api-tokens and export both variables:
91	> `export CONFLUENCE_API_TOKEN="your-token"` and `export CONFLUENCE_USER_EMAIL="your-email"`.
92	> Falling back to Browser extraction (Layer 3).
93
94	### 3.2 Compute Basic Auth header
95
96	```bash
97	echo -n "${CONFLUENCE_USER_EMAIL}:${CONFLUENCE_API_TOKEN}" \| base64
98	```
99
100	### 3.3 Fetch the page
101
102	Use `WebFetch`:
103	```
104	WebFetch(
105	url: "{baseUrl}/wiki/api/v2/pages/{pageId}?body-format=storage",
106	headers: {
107	"Authorization": "Basic {base64_value}",
108	"Accept": "application/json"
109	}
110	)
111	```
112
113	If WebFetch cannot send the Authorization header, fall back to `curl` via Bash:
114	```bash
115	curl -sL -H "Authorization: Basic {base64_value}" -H "Accept: application/json" \
116	"{baseUrl}/wiki/api/v2/pages/{pageId}?body-format=storage"
117	```
118
119	### 3.4 Extract content from re

People who liked this also viewed

6 picks

Type

confluence-to-markdown

82stars8forks

View on GitHub

How to install confluence-to-markdown?

iurykrieger/claude-bedrock/confluence-to-markdown

$npx -y skills add iurykrieger/claude-bedrock --skill confluence-to-markdown

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Confluence Fetcher
2
3	Internal module — invoked by `/bedrock:learn` Phase 1 and `/bedrock:sync` Phase 2, not user-invocable.
4
5	Fetches a Confluence page and returns its content as Markdown. Three layers in fallback order:
6	MCP (preferred) → REST API → Browser DOM extraction.
7
8	Dependency: Browser fallback (Layer 3) requires `scripts/extract.js` (relative to this skill directory).
9
10	---
11
12	## Step 1 — Parse URL
13
14	Parse the Confluence URL. Accept these formats:
15	- `https://<domain>.atlassian.net/wiki/spaces/<spaceKey>/pages/<pageId>/<title>`
16	- `https://<domain>.atlassian.net/wiki/spaces/<spaceKey>/pages/<pageId>`
17	- `https://<domain>.atlassian.net/wiki/x/<shortlink>`
18	- `https://<domain>.atlassian.net/wiki/pages/viewpage.action?pageId=<pageId>`
19
20	Extract:
21	- Base URL: `https://<domain>.atlassian.net` (everything before `/wiki/...`)
22	- Page ID: the numeric ID from the URL path (segment after `/pages/`) or `pageId` query parameter
23	- Full URL: the original URL as provided (needed for browser fallback)
24
25	---
26
27	## Step 2 — Layer 1: MCP (Atlassian)
28
29	The preferred layer. Uses the `plugin:atlassian:atlassian` MCP server if installed and authenticated.
30
31	### 2.1 Check MCP availability
32
33	Use ToolSearch to check if Atlassian MCP tools are available:
34
35	```
36	ToolSearch(query: "atlassian confluence page", max_results: 5)
37	```
38
39	Evaluate the result:
40
41	- MCP tools found and functional (tools other than `authenticate` and `complete_authentication` are available) → proceed to 2.2 Fetch via MCP
42	- Only `authenticate` / `complete_authentication` tools found (MCP installed but not authenticated) → proceed to 2.3 Guide authentication
43	- No Atlassian MCP tools found → log and fall through:
44
45	> MCP not available: No Atlassian MCP server installed.
46	> Install the Atlassian MCP plugin for Claude Code to enable direct Confluence access.
47	> Falling back to API (Layer 2).
48
49	### 2.2 Fetch via MCP
50
51	Use the Atlassian MCP tools to fetch the page content. The specific tool depends on what the MCP exposes after authentication (typically a page read or content retrieval tool).
52
53	Call the MCP tool passing the page ID or URL. The MCP returns the page content directly.
54
55	- Success → convert content to Markdown if not already, proceed to Output Contract
56	- Error → log the error and fall through to Layer 2:
57
58	> MCP fetch failed: {error message}.
59	> Falling back to API (Layer 2).
60
61	### 2.3 Guide authentication
62
63	If the MCP is installed but not authenticated, guide the user:
64
65	> MCP not authenticated: The Atlassian MCP server is installed but requires authentication.
66	> Run `mcp__plugin_atlassian_atlassian__authenticate` to start the OAuth flow, then complete it in your browser.
67	> After authentication, Confluence pages can be fetched directly via MCP.
68
69	Ask the user: "Would you like to authenticate the Atlassian MCP now, or skip to API fallback (Layer 2)?"
70
71	- User wants to authenticate → invoke `mcp__plugin_atlassian_atlassian__authenticate`, wait for the user to complete the OAuth flow, then retry 2.2 Fetch via MCP
72	- User declines → log "User declined MCP authentication, falling to Layer 2" → continue to Step 3
73
74	---
75
76	## Step 3 — Layer 2: API (REST)
77
78	Uses the Confluence REST API with Basic Auth (API token + email).
79
80	### 3.1 Check credentials
81
82	```bash
83	echo "CONFLUENCE_API_TOKEN: ${CONFLUENCE_API_TOKEN:+set}" && echo "CONFLUENCE_USER_EMAIL: ${CONFLUENCE_USER_EMAIL:+set}"
84	```
85
86	- Both set → proceed to 3.2 Compute auth header
87	- Either missing → guide and fall through:
88
89	> API not available: `CONFLUENCE_API_TOKEN` or `CONFLUENCE_USER_EMAIL` environment variable is not set.
90	> Generate an API token at https://id.atlassian.com/manage-profile/security/api-tokens and export both variables:
91	> `export CONFLUENCE_API_TOKEN="your-token"` and `export CONFLUENCE_USER_EMAIL="your-email"`.
92	> Falling back to Browser extraction (Layer 3).
93
94	### 3.2 Compute Basic Auth header
95
96	```bash
97	echo -n "${CONFLUENCE_USER_EMAIL}:${CONFLUENCE_API_TOKEN}" \| base64
98	```
99
100	### 3.3 Fetch the page
101
102	Use `WebFetch`:
103	```
104	WebFetch(
105	url: "{baseUrl}/wiki/api/v2/pages/{pageId}?body-format=storage",
106	headers: {
107	"Authorization": "Basic {base64_value}",
108	"Accept": "application/json"
109	}
110	)
111	```
112
113	If WebFetch cannot send the Authorization header, fall back to `curl` via Bash:
114	```bash
115	curl -sL -H "Authorization: Basic {base64_value}" -H "Accept: application/json" \
116	"{baseUrl}/wiki/api/v2/pages/{pageId}?body-format=storage"
117	```
118
119	### 3.4 Extract content from re

People who liked this also viewed

6 picks

Type