CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Content

50%

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

This is a solid instructional skill that provides a clear multi-step methodology for tracing upstream data lineage in Airflow environments. Its strengths are the logical step sequence, concrete CLI commands, and useful output template. Its weaknesses are the lack of validation checkpoints in the workflow, somewhat verbose output formatting guidance, and illustrative rather than executable code examples.

Suggestions

Add explicit validation checkpoints, e.g., after Step 2 confirm the DAG actually writes to the target table before proceeding, and after Step 4 verify completeness of the lineage chain.

Make code examples more executable — for instance, show a complete sequence of CLI commands with expected output patterns rather than just SQL fragments.

Consider moving the detailed output template (Lineage Report section) to a separate reference file to keep the main skill focused on the investigation process.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but includes some unnecessary elaboration. The external sources list, file sources section, and the detailed output template with Data Quality Implications section add bulk. Some sections like 'On Astro' vs 'On OSS Airflow' are brief but could be tighter. Overall mostly efficient with room to trim.

2 / 3

Actionability

Provides concrete CLI commands (af dags list, af dags source, af tasks list) and SQL pattern examples, which is good. However, the code examples are illustrative rather than executable — the SQL snippets are fragments, the lineage diagram is ASCII art for output formatting, and there's no complete executable workflow. The guidance is specific enough to follow but falls short of copy-paste ready.

2 / 3

Workflow Clarity

The 5-step sequence is clearly laid out and logically ordered, with Step 4 showing recursive tracing. However, there are no explicit validation checkpoints — no verification that the correct DAG was found, no confirmation that all sources were identified, and no feedback loop for when tracing hits a dead end or ambiguous source. For a multi-step investigative process, these gaps matter.

2 / 3

Progressive Disclosure

The skill references several related skills (checking-freshness, debugging-dags, etc.) which is good for navigation. However, with no bundle files, these references are unverifiable. The content itself is somewhat long and monolithic — the detailed output template section and the column lineage section could potentially be separate files. The structure is decent but the inline content is heavy for a single SKILL.md.

2 / 3

Total

8

/

12

Passed

Description

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 names one action ('trace upstream data lineage') rather than listing multiple concrete capabilities. Adding more specific actions would strengthen it further.

Suggestions

Expand the 'what' portion with additional concrete actions, e.g., 'Trace upstream data lineage, map table dependencies, identify source systems, and visualize data flow paths.'

DimensionReasoningScore

Specificity

The description names the domain (data lineage) and a core action ('trace upstream data lineage'), but it only describes one action rather than listing multiple specific concrete actions like resolving dependency chains, generating lineage diagrams, or querying metadata catalogs.

2 / 3

Completeness

Clearly answers both 'what' (trace upstream data lineage) and 'when' (explicit 'Use when...' clause listing multiple trigger scenarios like asking where data comes from, upstream dependencies, data sources, 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 with distinct triggers like 'feeds a table', 'upstream dependencies', and 'data origins' that are unlikely to conflict with general data analysis or ETL skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
astronomer/agents
Reviewed

Table of Contents

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.