investigate-to-confluence

Name: investigate-to-confluence
Author: testdouble

122stars12forks

How to install investigate-to-confluence?

testdouble/han/investigate-to-confluence

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

Installs into the current project.

Summary

Runs an evidence-based investigation of a bug, failure, or unexpected behavior with investigate and publishes the resulting investigation report to a user-specified Confluence location. Use when the user wants something debugged, diagnosed, or root-caused AND the findings posted

Files · 1

View on GitHub

SKILL.md

1	# Investigate to Confluence
2
3	This skill runs an evidence-based investigation with the core `han-coding:investigate`
4	skill, lets the user review the resulting report, and then publishes it to a
5	Confluence location that the user must specify. It is a thin orchestrator:
6	the investigation work belongs to `han-coding:investigate`, and the publishing work
7	belongs to `han-atlassian:markdown-to-confluence`. This skill only validates its inputs,
8	runs the investigation to a temporary file, gets the user's review and publish
9	choice, and hands the file to the publisher.
10
11	`han-coding:investigate` produces a single report file (the investigation plan:
12	problem statement, evidence summary, root cause analysis, planned fix, validation
13	results, and summary). It does not produce companion artifacts, so this skill
14	publishes that one file as a single Confluence page — the single-page sibling of
15	`han-atlassian:project-documentation-to-confluence`, not the parent-plus-children tree of
16	`han-atlassian:plan-a-feature-to-confluence`.
17
18	The five steps below are the whole skill. It does not resolve Confluence pages or
19	call the Confluence MCP create/update tools itself; `han-atlassian:markdown-to-confluence`
20	owns all of that.
21
22	## Step 1: Validate Inputs
23
24	Confirm the skill has everything it needs before spending effort on an
25	investigation:
26
27	1. Atlassian MCP reachable (hard requirement). Call
28	`mcp__claude_ai_Atlassian__getAccessibleAtlassianResources` to confirm the
29	server is connected and retrieve the cloud ID(s). If the tool is not
30	available, the call errors, or it returns no accessible resources (typically
31	an authentication or configuration problem), stop immediately. Tell the
32	user this skill requires the Atlassian MCP server to be installed, configured,
33	and authenticated, and that they can re-run it once it is connected. Do not
34	fall back to a local-only run; for a local-only investigation, point them at
35	`han-coding:investigate`. This preflight runs first so a missing server fails
36	before any investigation work begins.
37	2. A symptom or question to investigate. Confirm the request names a bug,
38	failure, error, integration, or unexpected behavior to investigate. This —
39	together with any relevant conversation context — is forwarded to
40	`han-coding:investigate` verbatim in Step 2. If the request is too thin to
41	start, let `han-coding:investigate` run its own investigation rather than
42	pre-empting it here.
43	3. A Confluence destination. Confirm the request provides a target location:
44	a Confluence page URL (to update that page, or create a child under it),
45	or a space (key or name) plus an optional parent page. If none was
46	provided, ask for one with `AskUserQuestion`, explaining plainly that the
47	skill needs an exact destination because it does not search Confluence. Do not
48	resolve the page tree here — only confirm a location was given. Carry it
49	through to Step 5; `han-atlassian:markdown-to-confluence` resolves it.
50
51	## Step 2: Produce the Investigation Report to a Temporary File
52
53	Invoke the `han-coding:investigate` skill with the Skill tool, **forwarding all
54	provided context** verbatim: the symptom or question, any known reproduction
55	steps or error messages, any suspected entry points, and the relevant
56	conversation context. Do not summarize, trim, or reinterpret the user's context;
57	pass it through so `han-coding:investigate` runs exactly as it would on its own
58	(parallel investigators, conditional specialist analysts, adversarial validation,
59	and the final report) — except add two explicit instructions:
60
61	- It must write the resulting investigation report to a file under `/tmp/` (for
62	example `/tmp/<symptom-slug>.md`) rather than into the project's docs or plans
63	directory. This keeps the working report out of the repo until the user decides
64	to publish it.
65	- It must **stop after producing the re

People who liked this also viewed

6 picks

Type

investigate-to-confluence

122stars12forks

View on GitHub

How to install investigate-to-confluence?

testdouble/han/investigate-to-confluence

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Investigate to Confluence
2
3	This skill runs an evidence-based investigation with the core `han-coding:investigate`
4	skill, lets the user review the resulting report, and then publishes it to a
5	Confluence location that the user must specify. It is a thin orchestrator:
6	the investigation work belongs to `han-coding:investigate`, and the publishing work
7	belongs to `han-atlassian:markdown-to-confluence`. This skill only validates its inputs,
8	runs the investigation to a temporary file, gets the user's review and publish
9	choice, and hands the file to the publisher.
10
11	`han-coding:investigate` produces a single report file (the investigation plan:
12	problem statement, evidence summary, root cause analysis, planned fix, validation
13	results, and summary). It does not produce companion artifacts, so this skill
14	publishes that one file as a single Confluence page — the single-page sibling of
15	`han-atlassian:project-documentation-to-confluence`, not the parent-plus-children tree of
16	`han-atlassian:plan-a-feature-to-confluence`.
17
18	The five steps below are the whole skill. It does not resolve Confluence pages or
19	call the Confluence MCP create/update tools itself; `han-atlassian:markdown-to-confluence`
20	owns all of that.
21
22	## Step 1: Validate Inputs
23
24	Confirm the skill has everything it needs before spending effort on an
25	investigation:
26
27	1. Atlassian MCP reachable (hard requirement). Call
28	`mcp__claude_ai_Atlassian__getAccessibleAtlassianResources` to confirm the
29	server is connected and retrieve the cloud ID(s). If the tool is not
30	available, the call errors, or it returns no accessible resources (typically
31	an authentication or configuration problem), stop immediately. Tell the
32	user this skill requires the Atlassian MCP server to be installed, configured,
33	and authenticated, and that they can re-run it once it is connected. Do not
34	fall back to a local-only run; for a local-only investigation, point them at
35	`han-coding:investigate`. This preflight runs first so a missing server fails
36	before any investigation work begins.
37	2. A symptom or question to investigate. Confirm the request names a bug,
38	failure, error, integration, or unexpected behavior to investigate. This —
39	together with any relevant conversation context — is forwarded to
40	`han-coding:investigate` verbatim in Step 2. If the request is too thin to
41	start, let `han-coding:investigate` run its own investigation rather than
42	pre-empting it here.
43	3. A Confluence destination. Confirm the request provides a target location:
44	a Confluence page URL (to update that page, or create a child under it),
45	or a space (key or name) plus an optional parent page. If none was
46	provided, ask for one with `AskUserQuestion`, explaining plainly that the
47	skill needs an exact destination because it does not search Confluence. Do not
48	resolve the page tree here — only confirm a location was given. Carry it
49	through to Step 5; `han-atlassian:markdown-to-confluence` resolves it.
50
51	## Step 2: Produce the Investigation Report to a Temporary File
52
53	Invoke the `han-coding:investigate` skill with the Skill tool, **forwarding all
54	provided context** verbatim: the symptom or question, any known reproduction
55	steps or error messages, any suspected entry points, and the relevant
56	conversation context. Do not summarize, trim, or reinterpret the user's context;
57	pass it through so `han-coding:investigate` runs exactly as it would on its own
58	(parallel investigators, conditional specialist analysts, adversarial validation,
59	and the final report) — except add two explicit instructions:
60
61	- It must write the resulting investigation report to a file under `/tmp/` (for
62	example `/tmp/<symptom-slug>.md`) rather than into the project's docs or plans
63	directory. This keeps the working report out of the repo until the user decides
64	to publish it.
65	- It must **stop after producing the re

People who liked this also viewed

6 picks

Type