using-datahub

Name: using-datahub
Author: datahub-project

134installs28forks

How to install using-datahub?

datahub-project/datahub-skills/using-datahub

$npx -y skills add datahub-project/datahub-skills --skill using-datahub

Installs into the current project.

Summary

This skill provides routing guidance for all DataHub interaction skills. It is injected at session start and helps map user intent to the correct skill. Do not invoke this skill directly — it is loaded automatically.

Files · 1

View on GitHub

SKILL.md

1	# Using DataHub Skills
2
3	You have access to 5 DataHub catalog interaction skills. Use this guide to route the user's request to the correct skill.
4
5	---
6
7	## Skill Routing Table
8
9	\| User Intent \| Skill \| Command \|
10	\| -------------------------------------------------------------------------------- \| ----------- \| ------------------ \|
11	\| Find or discover entities (search, browse, filter, list) \| Search \| `/datahub-search` \|
12	\| Answer a question about the catalog ("who owns X?", "how many X?") \| Search \| `/datahub-search` \|
13	\| Update metadata (descriptions, tags, glossary terms, ownership, deprecation) \| Enrich \| `/datahub-enrich` \|
14	\| Explore lineage (upstream, downstream, impact, root cause, dependencies) \| Lineage \| `/datahub-lineage` \|
15	\| Data quality (assertions, incidents, health checks) \| Quality \| `/datahub-quality` \|
16	\| Notifications (subscribe to assertion failures, incidents) \| Quality \| `/datahub-quality` \|
17	\| Install CLI, authenticate, verify connection \| Setup \| `/datahub-setup` \|
18	\| Configure default scopes and profiles \| Setup \| `/datahub-setup` \|
19
20	---
21
22	## Disambiguation Rules
23
24	When the intent is ambiguous, use these rules:
25
26	### "Tag" requests
27
28	- All tag operations (PII, sensitive, important, reviewed, team-x) → Enrich (general metadata)
29
30	### "Domain" requests
31
32	- Filter search to a domain → Search (scoped search)
33	- Configure default domain → Setup (profile configuration)
34
35	### "Quality" or "health" requests
36
37	- Failing assertions, active incidents, health status → Quality
38	- Create assertions, run quality checks, raise incidents → Quality
39	- Subscribe to assertion failures or incidents → Quality
40	- Metadata quality/documentation/ownership coverage → Use Search to gather the data and synthesize the answer
41
42	### Lineage vs. Search
43
44	- "What feeds into X" / "what depends on X" / "impact of changing X" → Lineage
45	- "What dashboards use table X" → Lineage (relationship traversal)
46	- "Who owns X" / "what is X" → Search (metadata lookup)
47
48	### Setup vs. other skills
49
50	- "Set up" / "install" / "authenticate" / "verify connection" → Setup
51	- "Configure defaults" / "set default platform" / "create profile" → Setup
52	- "Check if DataHub is working" → Setup (connectivity verification)
53
54	---
55
56	## CLI Attribution
57
58	When running `datahub` CLI commands, pass `-C skill=<name>` on the root command so usage can be attributed:
59
60	```bash
61	datahub -C skill=datahub-search search "revenue"
62	datahub -C skill=datahub-enrich graphql --query '...'
63	datahub -C skill=datahub-lineage lineage --urn "..."
64	```
65
66	Use the skill name from the YAML frontmatter. If `-C` is not recognized, omit it — the command works the same without it.
67
68	---
69
70	## Critical Rules
71
72	1. Never guess the skill. If the intent is genuinely ambiguous, ask the user to clarify.
73	2. One skill per request unless the user explicitly asks for multiple operations.
74	3. Lineage is for lineage only — not for general "what is this entity?" questions (that's Search).
75	4. Search handles ad-hoc questions. "Who owns X?" and "what columns does X have?" are Search questions, not Lineage.
76	5. Enrich handles all metadata writes — descriptions, tags, glossary terms, ownership, deprecation.
77	6. Quality handles data quality — assertions, incidents, health checks, subscriptions.
78	7. Setup handles environment and configuration — CLI install, auth, connectivity, default scopes.

People who liked this also viewed

6 picks

Type

using-datahub

134installs28forks

View on GitHub

How to install using-datahub?

datahub-project/datahub-skills/using-datahub

$npx -y skills add datahub-project/datahub-skills --skill using-datahub

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Using DataHub Skills
2
3	You have access to 5 DataHub catalog interaction skills. Use this guide to route the user's request to the correct skill.
4
5	---
6
7	## Skill Routing Table
8
9	\| User Intent \| Skill \| Command \|
10	\| -------------------------------------------------------------------------------- \| ----------- \| ------------------ \|
11	\| Find or discover entities (search, browse, filter, list) \| Search \| `/datahub-search` \|
12	\| Answer a question about the catalog ("who owns X?", "how many X?") \| Search \| `/datahub-search` \|
13	\| Update metadata (descriptions, tags, glossary terms, ownership, deprecation) \| Enrich \| `/datahub-enrich` \|
14	\| Explore lineage (upstream, downstream, impact, root cause, dependencies) \| Lineage \| `/datahub-lineage` \|
15	\| Data quality (assertions, incidents, health checks) \| Quality \| `/datahub-quality` \|
16	\| Notifications (subscribe to assertion failures, incidents) \| Quality \| `/datahub-quality` \|
17	\| Install CLI, authenticate, verify connection \| Setup \| `/datahub-setup` \|
18	\| Configure default scopes and profiles \| Setup \| `/datahub-setup` \|
19
20	---
21
22	## Disambiguation Rules
23
24	When the intent is ambiguous, use these rules:
25
26	### "Tag" requests
27
28	- All tag operations (PII, sensitive, important, reviewed, team-x) → Enrich (general metadata)
29
30	### "Domain" requests
31
32	- Filter search to a domain → Search (scoped search)
33	- Configure default domain → Setup (profile configuration)
34
35	### "Quality" or "health" requests
36
37	- Failing assertions, active incidents, health status → Quality
38	- Create assertions, run quality checks, raise incidents → Quality
39	- Subscribe to assertion failures or incidents → Quality
40	- Metadata quality/documentation/ownership coverage → Use Search to gather the data and synthesize the answer
41
42	### Lineage vs. Search
43
44	- "What feeds into X" / "what depends on X" / "impact of changing X" → Lineage
45	- "What dashboards use table X" → Lineage (relationship traversal)
46	- "Who owns X" / "what is X" → Search (metadata lookup)
47
48	### Setup vs. other skills
49
50	- "Set up" / "install" / "authenticate" / "verify connection" → Setup
51	- "Configure defaults" / "set default platform" / "create profile" → Setup
52	- "Check if DataHub is working" → Setup (connectivity verification)
53
54	---
55
56	## CLI Attribution
57
58	When running `datahub` CLI commands, pass `-C skill=<name>` on the root command so usage can be attributed:
59
60	```bash
61	datahub -C skill=datahub-search search "revenue"
62	datahub -C skill=datahub-enrich graphql --query '...'
63	datahub -C skill=datahub-lineage lineage --urn "..."
64	```
65
66	Use the skill name from the YAML frontmatter. If `-C` is not recognized, omit it — the command works the same without it.
67
68	---
69
70	## Critical Rules
71
72	1. Never guess the skill. If the intent is genuinely ambiguous, ask the user to clarify.
73	2. One skill per request unless the user explicitly asks for multiple operations.
74	3. Lineage is for lineage only — not for general "what is this entity?" questions (that's Search).
75	4. Search handles ad-hoc questions. "Who owns X?" and "what columns does X have?" are Search questions, not Lineage.
76	5. Enrich handles all metadata writes — descriptions, tags, glossary terms, ownership, deprecation.
77	6. Quality handles data quality — assertions, incidents, health checks, subscriptions.
78	7. Setup handles environment and configuration — CLI install, auth, connectivity, default scopes.

People who liked this also viewed

6 picks

Type