tracing-downstream-lineage
Trace downstream data lineage and impact analysis. Use when the user asks what depends on this data, what breaks if something changes, downstream dependencies, or needs to assess change risk before modifying a table or DAG.
79
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/tracing-downstream-lineage/SKILL.mdQuality
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 skill description with excellent trigger terms and completeness. The explicit 'Use when...' clause with multiple natural phrasings makes it highly selectable. The main weakness is that the capability description could be more specific about the concrete actions performed beyond 'trace lineage and impact analysis'.
Suggestions
Add more specific concrete actions to the capability portion, e.g., 'Trace downstream data lineage, generate dependency graphs, list affected tables and pipelines, and produce impact analysis reports.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (data lineage/impact analysis) and mentions some actions like tracing downstream lineage and assessing change risk, but doesn't list multiple concrete specific actions (e.g., doesn't specify generating dependency graphs, listing affected tables, producing impact reports). | 2 / 3 |
Completeness | Clearly answers both 'what' (trace downstream data lineage and impact analysis) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios including dependency questions, change risk assessment, and DAG modifications. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'what depends on this data', 'what breaks if something changes', 'downstream dependencies', 'change risk', 'table', 'DAG'. These cover multiple natural phrasings well. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around downstream data lineage and impact analysis with distinct triggers like 'DAG', 'downstream dependencies', and 'change risk'. Unlikely to conflict with general data or code skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%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 skill that provides a useful framework for downstream impact analysis with good structure and clear output templates. Its main weaknesses are that much of the guidance is conceptual rather than executable (the dependency tree building and risk assessment are frameworks, not concrete procedures), and the workflow lacks explicit validation checkpoints to ensure completeness before proceeding with changes. The output report template with tables and diagrams is a strong feature.
Suggestions
Add a validation checkpoint after Step 2 (e.g., 'Verify completeness: cross-reference your dependency tree against the Astro lineage UI or run a reverse-dependency query to confirm no consumers were missed before proceeding').
Make Step 2 more actionable by providing a concrete script or command sequence for building the dependency tree programmatically rather than just showing an example diagram.
Tighten the criticality categorization in Step 3—Claude can infer most of these categories. Consider reducing to a compact table or a single sentence with the key principle (e.g., 'Prioritize by: production-facing > internal operational > ad-hoc/dev').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary elaboration. The criticality categorization section (Critical/High/Medium/Low) is somewhat verbose with examples Claude could infer. The Astro UI paragraph adds context but could be tighter. Overall mostly efficient with some tightening possible. | 2 / 3 |
Actionability | Provides a mix of concrete and vague guidance. The SQL query for Snowflake views is executable, and the CLI commands (`af dags list`, `af dags source`) are specific. However, much of the skill is descriptive rather than executable—the dependency tree building, stakeholder finding, and risk assessment steps are more conceptual frameworks than concrete commands or code. The output templates are helpful but are examples rather than executable procedures. | 2 / 3 |
Workflow Clarity | The 5-step sequence is clearly laid out and logically ordered, which is good. However, for an impact analysis workflow that precedes potentially destructive changes, there are no explicit validation checkpoints or feedback loops. There's no 'verify your dependency tree is complete before proceeding' step or mechanism to confirm all consumers have been found. The checklist at the end is helpful but is an output template, not a validation gate within the workflow. | 2 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections progressing from identification to output. The 'Related Skills' section at the end provides clear one-level-deep references to related skills. Content is appropriately organized within a single file given its scope, with good use of headers, tables, and diagrams for navigation. | 3 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- astronomer/agents
- Commit
0642adb
- 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.