doc-gather

Name: doc-gather
Author: opendatahub-io

36stars74forks

How to install doc-gather?

opendatahub-io/ai-helpers/doc-gather

$npx -y skills add opendatahub-io/ai-helpers --skill doc-gather

Installs into the current project.

Summary

Use when you need to gather context for a Jira ticket or PR. Resolves ticket metadata, clones relevant repos, collects candidate files, runs filtering pipeline, and produces workspace/context-package.json.

Files · 1

View on GitHub

SKILL.md

1	# doc-gather
2
3	Gather context from Jira tickets, source repos, and documentation repos to produce a structured context package for downstream skills.
4
5	## Parse arguments
6
7	`$ARGUMENTS` contains either:
8	- A Jira ticket key (e.g., `RHOAIENG-55490`)
9	- A PR/MR URL (e.g., `https://github.com/org/repo/pull/123`)
10
11	Detect the input type:
12	- If it starts with `http` → PR URL
13	- Otherwise → Jira ticket key
14
15	## Step 1: Resolve ticket metadata
16
17	### For Jira tickets
18
19	Use the resolve script to fetch and structure ticket metadata:
20
21	```bash
22	bash ${CLAUDE_SKILL_DIR}/scripts/resolve-jira.sh <JIRA-KEY>
23	```
24
25	This returns JSON with: `key`, `summary`, `description`, `acceptance_criteria`, `fix_versions`, `components`, `linked_tickets`, `epic_key`, `status`, `issue_type`.
26
27	If the ticket has linked tickets that provide useful context (e.g., parent epic, related stories), resolve those too (up to 5 linked tickets):
28
29	```bash
30	bash ${CLAUDE_SKILL_DIR}/scripts/resolve-jira.sh <LINKED-KEY>
31	```
32
33	### For PR URLs
34
35	Use `gh` CLI to extract PR metadata:
36
37	```bash
38	gh pr view <PR-URL> --json title,body,labels,files,headRefName
39	```
40
41	Extract the Jira key from the PR title or body (pattern: `[A-Z]+-\d+`), then resolve the Jira ticket using the resolve script as above.
42
43	## Step 2: Parse product configuration
44
45	Read the product configuration bundled with this skill:
46
47	```bash
48	python3 ${CLAUDE_SKILL_DIR}/scripts/parse-product-config.py ${CLAUDE_SKILL_DIR}/references/rhoai.yaml
49	```
50
51	From the config, determine:
52	1. Context sources — which repos to clone and where to find files
53	2. Version mappings — how to map Jira fixVersion to git branches
54	3. Component resolver — map Jira component names to repo slugs
55	4. Docs conventions — module prefixes, framework, attribute files
56
57	## Step 3: Resolve version to branches
58
59	For each fixVersion from the ticket:
60
61	```bash
62	python3 ${CLAUDE_SKILL_DIR}/scripts/parse-product-config.py ${CLAUDE_SKILL_DIR}/references/rhoai.yaml --resolve-version "<fixVersion>"
63	```
64
65	This determines which branch to checkout for each repo.
66
67	## Step 4: Resolve components to repos
68
69	For each component from the ticket:
70
71	```bash
72	python3 ${CLAUDE_SKILL_DIR}/scripts/parse-product-config.py ${CLAUDE_SKILL_DIR}/references/rhoai.yaml --resolve-component "<component-name>"
73	```
74
75	This identifies which source repos are relevant.
76
77	## Step 5: Clone and collect candidate files
78
79	For each context source in the product config, plus each resolved component repo:
80
81	```bash
82	bash ${CLAUDE_SKILL_DIR}/scripts/gather-context.sh <repo-slug> <branch> <path-patterns...>
83	```
84
85	The branch is determined by:
86	1. Version resolution from Step 3 (if applicable)
87	2. The `branch_hint` from the context source declaration
88	3. Fallback to `main`
89
90	## Step 6: Run filtering pipeline
91
92	Assemble a JSON input for the filtering pipeline combining:
93	- All candidate files from Step 5
94	- Task context (ticket metadata as keywords, components, version)
95	- Source declarations from product config
96
97	```bash
98	python3 ${CLAUDE_SKILL_DIR}/scripts/context-filter.py <<< '<assembled-json>'
99	```
100
101	The pipeline runs six stages:
102	1. Static inclusion — mark always_include sources
103	2. Version branch — (already resolved in Step 3)
104	3. Component affinity — filter by component overlap
105	4. Path relevance — score by path patterns and keywords
106	5. Keyword relevance — BM25 scoring against ticket text
107	6. Budget enforcement — select top candidates within 100K token budget
108
109	## Step 7: Read file contents
110
111	Source the git utilities (which internally uses `scripts/load-env.sh` to load credentials from the environment) and read each selected candidate's content from the cloned repo:
112
113	```bash
114	source ${CLAUDE_SKILL_DIR}/scripts/git-utils.sh
115	git_file_content "workspace/repos/<repo-slug>" "<file-path>"
116	```
117
118	Attach content to each candidate entry.
119
120	## Step 8: Write context package
121
122	Write `workspace/context-package.json` with this structure:
123
124	```json
125	{
126	"ticket": {
127	"key": "RHOAIENG-55490",
128	"summary": "...",
129	"description": "...",
130	"fix_versions": ["rhoai-2.18"],
131	"components": ["Dashboard"],
132	"linked_tickets": [],
133	"epic_key": "",
134	"status": "In Progress",
135	"issue_type": "Story"
136	},
137	"product": {
138	"product_id": "rhoai",
139	"display_name": "Red Hat OpenShift AI",
140	"docs_repo": "opendatahub-io/opendatahub-documentation",
141	"docs_branch": "main",
142	"framework": "asciidoc-modular",
143	"module_prefixes": {
144	"concept": "con_",
145	"procedure": "proc_",
146	"reference": "ref_",
147	"assembly": "assembly_",
148	"snippet": "snip_"
149	}
150	},
151	"context

People who liked this also viewed

6 picks

Type

grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.SkillsJul 2026537k182k
lark-minutes飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要SkillsJul 2026379k16k
lark-markdown飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。SkillsJul 2026295k16k
docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', SkillsJul 2026157k163k
edit-articleSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026154k181k
lark-note飞书会议纪要（Note）直查：已知 note_id 时查询纪要详情、展示类型、关联文档 token，并读取 unified 原始逐字记录。当用户已持有 note_id，或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。SkillsJul 2026154k16k

doc-gather

36stars74forks

View on GitHub

How to install doc-gather?

opendatahub-io/ai-helpers/doc-gather

$npx -y skills add opendatahub-io/ai-helpers --skill doc-gather

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# doc-gather
2
3	Gather context from Jira tickets, source repos, and documentation repos to produce a structured context package for downstream skills.
4
5	## Parse arguments
6
7	`$ARGUMENTS` contains either:
8	- A Jira ticket key (e.g., `RHOAIENG-55490`)
9	- A PR/MR URL (e.g., `https://github.com/org/repo/pull/123`)
10
11	Detect the input type:
12	- If it starts with `http` → PR URL
13	- Otherwise → Jira ticket key
14
15	## Step 1: Resolve ticket metadata
16
17	### For Jira tickets
18
19	Use the resolve script to fetch and structure ticket metadata:
20
21	```bash
22	bash ${CLAUDE_SKILL_DIR}/scripts/resolve-jira.sh <JIRA-KEY>
23	```
24
25	This returns JSON with: `key`, `summary`, `description`, `acceptance_criteria`, `fix_versions`, `components`, `linked_tickets`, `epic_key`, `status`, `issue_type`.
26
27	If the ticket has linked tickets that provide useful context (e.g., parent epic, related stories), resolve those too (up to 5 linked tickets):
28
29	```bash
30	bash ${CLAUDE_SKILL_DIR}/scripts/resolve-jira.sh <LINKED-KEY>
31	```
32
33	### For PR URLs
34
35	Use `gh` CLI to extract PR metadata:
36
37	```bash
38	gh pr view <PR-URL> --json title,body,labels,files,headRefName
39	```
40
41	Extract the Jira key from the PR title or body (pattern: `[A-Z]+-\d+`), then resolve the Jira ticket using the resolve script as above.
42
43	## Step 2: Parse product configuration
44
45	Read the product configuration bundled with this skill:
46
47	```bash
48	python3 ${CLAUDE_SKILL_DIR}/scripts/parse-product-config.py ${CLAUDE_SKILL_DIR}/references/rhoai.yaml
49	```
50
51	From the config, determine:
52	1. Context sources — which repos to clone and where to find files
53	2. Version mappings — how to map Jira fixVersion to git branches
54	3. Component resolver — map Jira component names to repo slugs
55	4. Docs conventions — module prefixes, framework, attribute files
56
57	## Step 3: Resolve version to branches
58
59	For each fixVersion from the ticket:
60
61	```bash
62	python3 ${CLAUDE_SKILL_DIR}/scripts/parse-product-config.py ${CLAUDE_SKILL_DIR}/references/rhoai.yaml --resolve-version "<fixVersion>"
63	```
64
65	This determines which branch to checkout for each repo.
66
67	## Step 4: Resolve components to repos
68
69	For each component from the ticket:
70
71	```bash
72	python3 ${CLAUDE_SKILL_DIR}/scripts/parse-product-config.py ${CLAUDE_SKILL_DIR}/references/rhoai.yaml --resolve-component "<component-name>"
73	```
74
75	This identifies which source repos are relevant.
76
77	## Step 5: Clone and collect candidate files
78
79	For each context source in the product config, plus each resolved component repo:
80
81	```bash
82	bash ${CLAUDE_SKILL_DIR}/scripts/gather-context.sh <repo-slug> <branch> <path-patterns...>
83	```
84
85	The branch is determined by:
86	1. Version resolution from Step 3 (if applicable)
87	2. The `branch_hint` from the context source declaration
88	3. Fallback to `main`
89
90	## Step 6: Run filtering pipeline
91
92	Assemble a JSON input for the filtering pipeline combining:
93	- All candidate files from Step 5
94	- Task context (ticket metadata as keywords, components, version)
95	- Source declarations from product config
96
97	```bash
98	python3 ${CLAUDE_SKILL_DIR}/scripts/context-filter.py <<< '<assembled-json>'
99	```
100
101	The pipeline runs six stages:
102	1. Static inclusion — mark always_include sources
103	2. Version branch — (already resolved in Step 3)
104	3. Component affinity — filter by component overlap
105	4. Path relevance — score by path patterns and keywords
106	5. Keyword relevance — BM25 scoring against ticket text
107	6. Budget enforcement — select top candidates within 100K token budget
108
109	## Step 7: Read file contents
110
111	Source the git utilities (which internally uses `scripts/load-env.sh` to load credentials from the environment) and read each selected candidate's content from the cloned repo:
112
113	```bash
114	source ${CLAUDE_SKILL_DIR}/scripts/git-utils.sh
115	git_file_content "workspace/repos/<repo-slug>" "<file-path>"
116	```
117
118	Attach content to each candidate entry.
119
120	## Step 8: Write context package
121
122	Write `workspace/context-package.json` with this structure:
123
124	```json
125	{
126	"ticket": {
127	"key": "RHOAIENG-55490",
128	"summary": "...",
129	"description": "...",
130	"fix_versions": ["rhoai-2.18"],
131	"components": ["Dashboard"],
132	"linked_tickets": [],
133	"epic_key": "",
134	"status": "In Progress",
135	"issue_type": "Story"
136	},
137	"product": {
138	"product_id": "rhoai",
139	"display_name": "Red Hat OpenShift AI",
140	"docs_repo": "opendatahub-io/opendatahub-documentation",
141	"docs_branch": "main",
142	"framework": "asciidoc-modular",
143	"module_prefixes": {
144	"concept": "con_",
145	"procedure": "proc_",
146	"reference": "ref_",
147	"assembly": "assembly_",
148	"snippet": "snip_"
149	}
150	},
151	"context

People who liked this also viewed

6 picks

Type