tracing-upstream-lineage

Trace upstream data lineage. Use when the user asks where data comes from, what feeds a table, upstream dependencies, data sources, or needs to understand data origins.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with real CLI commands and worked examples, and is well-structured for a self-contained skill. It would improve by trimming introductory restatements and adding an explicit validation/verification checkpoint to the investigation workflow.

Suggestions

Cut context Claude already knows (e.g., 'Tables are typically populated by Airflow DAGs') and lead each step directly with the action to raise conciseness to a 3.

Add a verification checkpoint in the lineage workflow, e.g., after Step 4 a 'Verify each source resolves to an external system or a further DAG; if a source table has no producing DAG, flag the gap' step, to lift workflow_clarity to 3.

Consider splitting the column-lineage and output-report subsections into a referenced file if the body grows, to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	Most sections are lean and assume competence (CLI commands, SQL snippets, an ASCII lineage tree), but explanatory filler like 'Tables are typically populated by Airflow DAGs. Find the connection:' and 'Determine what we're tracing' restates context Claude already knows and could be trimmed.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands ('af dags list', 'af dags source <dag_id>', 'af tasks list <dag_id>'), executable SQL patterns, and a worked lineage-chain example, matching the score-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	The five-step sequence is clearly ordered, but there are no validation checkpoints or error-recovery loops; the lineage investigation is a read-only tracing task rather than a destructive one, so this stays at 2 rather than being capped, yet it lacks the explicit verify-step that defines a 3.	2 / 3
Progressive Disclosure	It is a self-contained, well-organized single-file skill (no bundle directories exist) under the simple-skill threshold with clearly delimited sections and inline related-skill pointers, satisfying the rubric note that simple, well-organized skills can score 3 without external references.	3 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, uses third person, includes an explicit 'Use when' trigger clause, and covers natural user phrasings well. Its only weakness is that 'Trace' is a single action rather than a list of several concrete capabilities.

Suggestions

Expand the opening action from a single verb ('Trace') to two or three concrete operations (e.g., 'Trace upstream data lineage, identify source tables, and map producing DAGs') to lift specificity to the top anchor.

Add '.sql' or query-related trigger terms if users commonly phrase lineage requests around SQL/DAG objects, to broaden trigger coverage further.

Dimension	Reasoning	Score
Specificity	It names the domain ('upstream data lineage') and a concrete action ('Trace'), but does not enumerate multiple specific operations the way the score-3 anchor ('Extract text and tables, fill forms, merge documents') does.	2 / 3
Completeness	It states what the skill does ('Trace upstream data lineage') and an explicit 'Use when...' clause enumerating triggers, satisfying the score-3 requirement of clearly answering both what and when.	3 / 3
Trigger Term Quality	It covers natural phrasings a user would actually say — 'where data comes from', 'what feeds a table', 'upstream dependencies', 'data sources', 'data origins' — matching the score-3 anchor's broad coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	The 'upstream' framing and lineage-specific triggers carve a clear niche distinct from the related downstream/freshness skills listed in the body, making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: astronomer/agents
Commit: 8827e93

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.