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

80%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/tracing-upstream-lineage/SKILL.md

Quality

Discovery

89%

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

This is a well-structured description with an explicit 'Use when...' clause and excellent trigger term coverage using natural language users would actually say. Its main weakness is that the 'what' portion is somewhat thin—it only describes one action ('trace upstream data lineage') rather than listing multiple specific capabilities like generating dependency graphs, identifying source systems, or mapping transformations.

Suggestions

Expand the capability description with additional concrete actions, e.g., 'Trace upstream data lineage, identify source systems, map table-to-table dependencies, and generate lineage graphs.'

Dimension	Reasoning	Score
Specificity	Names the domain (data lineage) and a core action (trace upstream data lineage), but doesn't list multiple concrete actions beyond tracing. It could mention specific outputs like dependency graphs, source identification, or transformation tracking.	2 / 3
Completeness	Clearly answers both 'what' (trace upstream data lineage) and 'when' (explicit 'Use when...' clause listing multiple trigger scenarios like asking about data sources, upstream dependencies, and data origins).	3 / 3
Trigger Term Quality	Includes strong natural keywords users would actually say: 'where data comes from', 'what feeds a table', 'upstream dependencies', 'data sources', 'data origins'. These cover multiple natural phrasings a user might use.	3 / 3
Distinctiveness Conflict Risk	The focus on 'upstream data lineage' is a clear niche. The trigger terms are specific to lineage tracing and unlikely to conflict with general data analysis, ETL, or other data-related skills.	3 / 3
	Total	11 / 12 Passed

Implementation

70%

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

This is a well-structured skill with excellent workflow clarity and progressive disclosure. The 5-step investigation process is logical and thorough, with good examples of lineage chains and output formats. The main weaknesses are moderate verbosity in the output template section and actionability that relies more on illustrative patterns than fully executable commands, though this is somewhat inherent to the investigative nature of the task.

Suggestions

Tighten the output template section - the full table schema and Data Quality Implications checklist could be condensed since Claude can generate appropriate output formats from a brief description.

Make CLI examples more concrete by showing full command sequences with expected output snippets, e.g., show what `af dags source <dag_id>` output looks like and exactly what patterns to grep for.

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient but includes some unnecessary elaboration. The Astro vs OSS Airflow sections add useful context but the output template section is quite verbose with the full table template and data quality implications checklist that could be trimmed. Some explanations like 'Tables are typically populated by Airflow DAGs' are slightly redundant for Claude.	2 / 3
Actionability	Provides concrete CLI commands (af dags list, af dags source, af tasks list, af dags stats) and specific patterns to look for (FROM clauses, operator types), but the code examples are illustrative rather than executable. The SQL and Python snippets are fragments showing what to look for rather than copy-paste ready commands. The guidance is specific enough to follow but not fully executable.	2 / 3
Workflow Clarity	The 5-step workflow is clearly sequenced and logical: identify target → find producing DAG → trace sources → build lineage chain → check source health. The recursive tracing in Step 4 with the ASCII diagram is an excellent feedback loop pattern. Step 5 includes validation by checking source health and freshness, and the column lineage section provides a clear sub-workflow.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections progressing from investigation steps to specialized column lineage to output format. References to related skills (checking-freshness, debugging-dags, tracing-downstream-lineage, etc.) are clearly signaled at the end as one-level-deep pointers. Content is appropriately scoped for a single SKILL.md file.	3 / 3
	Total	10 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: astronomer/agents
Commit: 0642adb

Reviewed: 3 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.