markdown-to-confluence

Name: markdown-to-confluence
Author: testdouble

122stars12forks

How to install markdown-to-confluence?

testdouble/han/markdown-to-confluence

$npx -y skills add testdouble/han --skill markdown-to-confluence

Installs into the current project.

Summary

Publishes a local Markdown file to a user-specified Confluence location, creating a new page or updating an existing one through the Atlassian MCP server. Use when the user wants to post, publish, push, or sync a Markdown file to a Confluence space or page. Requires a configured

Files · 1

View on GitHub

SKILL.md

1	# Markdown to Confluence
2
3	This skill takes one local Markdown file and publishes it to a Confluence
4	location that the user must specify — creating a new page or updating an
5	existing one through the Atlassian MCP server. It owns everything about the
6	posting itself: the MCP preflight, resolving the destination, reading the file,
7	the create-or-update call, and reporting the result. It does not write the
8	Markdown; the caller supplies an existing file.
9
10	Callers that supply an explicit publish mode and location (for example
11	`han-atlassian:project-documentation-to-confluence`) run this skill straight through without
12	re-asking. Invoked on its own with pieces missing, it asks for them and defaults
13	to a safe unpublished draft.
14
15	## Step 0: Atlassian MCP Preflight (hard requirement)
16
17	This skill cannot run without a configured and connected Atlassian MCP server.
18
19	Confirm the server is reachable by calling
20	`mcp__claude_ai_Atlassian__getAccessibleAtlassianResources` to retrieve the
21	cloud ID(s). If the tool is not available, the call errors, or it returns no
22	accessible resources (typically an authentication or configuration problem),
23	stop immediately. Tell the user this skill requires the Atlassian MCP server
24	to be installed, configured, and authenticated, and that they can re-run the
25	skill once it is connected.
26
27	If more than one cloud / site is accessible, note which sites are available;
28	you will confirm the correct one while resolving the location in Step 2.
29
30	## Step 1: Confirm the Source Markdown File
31
32	Resolve the Markdown file path from the arguments or conversation. Read it and
33	confirm it exists and has content. If no file path was provided, or the path
34	does not resolve to a readable file, ask the user for the path with
35	`AskUserQuestion` and do not proceed without one. This is the exact content that
36	will be posted; do not rewrite, summarize, or restructure it.
37
38	A body may legitimately contain embedded Confluence storage macros mixed into the
39	Markdown — for example, an orchestrating skill such as
40	`han-atlassian:plan-a-feature-to-confluence` rewrites its cross-page links into
41	title-based page-link macros (the `<ac:link><ri:page ri:content-title="..."/>…</ac:link>`
42	form, link body included) before handing the file over. Post these verbatim along
43	with the rest of the body; do not strip or escape them.
44
45	## Step 2: Resolve the Target Confluence Location (required)
46
47	This skill does not search Confluence for the right place. A typical
48	Confluence instance is large and full of duplicate or similarly-named pages, so
49	guessing the destination is unreliable. The user must name the exact location.
50
51	1. Find a location in the request. Check the arguments and conversation for
52	either of:
53	- a Confluence page URL (to update that page, or to create a child page
54	under it), or
55	- a space (key or name) plus an optional parent page (title, ID, or
56	URL).
57	2. If no location was provided, ask for one. Use `AskUserQuestion` to
58	request it, and explain plainly that the skill needs an exact destination
59	because it does not search Confluence. Offer both accepted forms (a page URL,
60	or a space plus parent page). This is required: do not proceed without a
61	location.
62	3. Resolve the location concretely now, so failures surface early. Use the
63	cloud ID from Step 0 for every call.
64	- From a page URL: extract the page ID from the `/pages/<id>/` segment and
65	call `mcp__claude_ai_Atlassian__getConfluencePage` to confirm it exists and
66	to read its space and title. Then determine the intent: update that page,
67	or create a new child page under it. If the user did not already say,
68	ask with `AskUserQuestion`.
69	- From a space (+ parent): call
70	`mcp__claude_ai_Atlassian__g

People who liked this also viewed

6 picks

Type

markdown-to-confluence

122stars12forks

View on GitHub

How to install markdown-to-confluence?

testdouble/han/markdown-to-confluence

$npx -y skills add testdouble/han --skill markdown-to-confluence

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Markdown to Confluence
2
3	This skill takes one local Markdown file and publishes it to a Confluence
4	location that the user must specify — creating a new page or updating an
5	existing one through the Atlassian MCP server. It owns everything about the
6	posting itself: the MCP preflight, resolving the destination, reading the file,
7	the create-or-update call, and reporting the result. It does not write the
8	Markdown; the caller supplies an existing file.
9
10	Callers that supply an explicit publish mode and location (for example
11	`han-atlassian:project-documentation-to-confluence`) run this skill straight through without
12	re-asking. Invoked on its own with pieces missing, it asks for them and defaults
13	to a safe unpublished draft.
14
15	## Step 0: Atlassian MCP Preflight (hard requirement)
16
17	This skill cannot run without a configured and connected Atlassian MCP server.
18
19	Confirm the server is reachable by calling
20	`mcp__claude_ai_Atlassian__getAccessibleAtlassianResources` to retrieve the
21	cloud ID(s). If the tool is not available, the call errors, or it returns no
22	accessible resources (typically an authentication or configuration problem),
23	stop immediately. Tell the user this skill requires the Atlassian MCP server
24	to be installed, configured, and authenticated, and that they can re-run the
25	skill once it is connected.
26
27	If more than one cloud / site is accessible, note which sites are available;
28	you will confirm the correct one while resolving the location in Step 2.
29
30	## Step 1: Confirm the Source Markdown File
31
32	Resolve the Markdown file path from the arguments or conversation. Read it and
33	confirm it exists and has content. If no file path was provided, or the path
34	does not resolve to a readable file, ask the user for the path with
35	`AskUserQuestion` and do not proceed without one. This is the exact content that
36	will be posted; do not rewrite, summarize, or restructure it.
37
38	A body may legitimately contain embedded Confluence storage macros mixed into the
39	Markdown — for example, an orchestrating skill such as
40	`han-atlassian:plan-a-feature-to-confluence` rewrites its cross-page links into
41	title-based page-link macros (the `<ac:link><ri:page ri:content-title="..."/>…</ac:link>`
42	form, link body included) before handing the file over. Post these verbatim along
43	with the rest of the body; do not strip or escape them.
44
45	## Step 2: Resolve the Target Confluence Location (required)
46
47	This skill does not search Confluence for the right place. A typical
48	Confluence instance is large and full of duplicate or similarly-named pages, so
49	guessing the destination is unreliable. The user must name the exact location.
50
51	1. Find a location in the request. Check the arguments and conversation for
52	either of:
53	- a Confluence page URL (to update that page, or to create a child page
54	under it), or
55	- a space (key or name) plus an optional parent page (title, ID, or
56	URL).
57	2. If no location was provided, ask for one. Use `AskUserQuestion` to
58	request it, and explain plainly that the skill needs an exact destination
59	because it does not search Confluence. Offer both accepted forms (a page URL,
60	or a space plus parent page). This is required: do not proceed without a
61	location.
62	3. Resolve the location concretely now, so failures surface early. Use the
63	cloud ID from Step 0 for every call.
64	- From a page URL: extract the page ID from the `/pages/<id>/` segment and
65	call `mcp__claude_ai_Atlassian__getConfluencePage` to confirm it exists and
66	to read its space and title. Then determine the intent: update that page,
67	or create a new child page under it. If the user did not already say,
68	ask with `AskUserQuestion`.
69	- From a space (+ parent): call
70	`mcp__claude_ai_Atlassian__g

People who liked this also viewed

6 picks

Type