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.

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 concrete commands and templates and a clear 5-step sequence, but it is a monolithic file that adds some verbosity via categorization tables and lacks the explicit validation feedback loop the rubric expects for change-risk gating. No bundle files exist to support progressive disclosure.

Suggestions

Add an explicit validation checkpoint in Step 4 (e.g., 'Before proceeding, confirm the full dependency tree is mapped and every Critical item has an owner notified') to create a validate-then-proceed feedback loop.

Trim or move the criticality categorization tables to a references/ file so the core workflow stays lean and earns its tokens.

Introduce a reference file (e.g., references/impact-report-template.md) and link to it from the Output section to enable one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and examples, but contains restating prose ('Dashboards often query tables directly') and categorization tables that pad length without teaching Claude anything it does not already know.	2 / 3
Actionability	Provides concrete, executable commands (`af dags list`, `af dags source <dag_id>`, SQL against information_schema.view_table_usage) plus copy-ready output templates and checklists, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1–5) and there is an output checklist, but for a change-risk assessment that gates destructive modifications there is no validate-then-proceed feedback loop or verification checkpoint, which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Well-organized into sections with a Related Skills pointer list, but it is a single monolithic SKILL.md with no bundle files (no references/, scripts/, assets/) and no one-level-deep references to detail documents, so structure is good but disclosure is not multi-file.	2 / 3
	Total	9 / 12 Passed

Description

100%

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

A strong description: it states concrete capabilities, provides natural trigger terms, includes an explicit 'Use when' clause, and occupies a distinct niche relative to sibling lineage skills. No fluff or over-claims; written in the correct imperative/ third-person voice.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Trace downstream data lineage and impact analysis', 'assess change risk') tied to specific artifacts (tables, DAGs), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers what ('Trace downstream data lineage and impact analysis') and when via an explicit 'Use when...' clause enumerating trigger conditions, satisfying the top anchor.	3 / 3
Trigger Term Quality	Includes natural phrases users would say ('what depends on this data', 'what breaks if something changes', 'downstream dependencies') plus technical triggers (tables, DAGs), giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Niche is clearly bounded to downstream lineage and change-risk assessment, with triggers unlikely to fire for the upstream-lineage or freshness sibling skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 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.