CtrlK
BlogDocsLog inGet started
Tessl Logo

debugging-dags

Comprehensive DAG failure diagnosis and root-cause analysis with structured investigation and prevention recommendations. Use when deep failure investigation is needed, a DAG fails to import/parse or 'airflow dags list' errors on a file; a task or run is failing and must be diagnosed and fixed; requests like 'why did X fail', 'my dag keeps failing — find and fix it', or fixing a broken DAG so it loads cleanly. For simple 'why did it fail / show logs', the airflow skill handles it directly.

77

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The body is lean, highly actionable, and clearly sequenced with verification beats in the diagnosis loop. Its main weakness is progressive disclosure: a >50-line skill with several specialized subsections carries everything inline instead of pointing to reference files.

Suggestions

Extract the 'Package version changes' deep-dive (worker image diff, venv-style operators, index lookup) into a references file (e.g. references/dependency-drift.md) and link to it one level deep from Step 3 to slim the SKILL.md overview.

Consider splitting the 'On Astro' and 'On OSS Airflow' platform-specific guidance into a separate reference so the core diagnostic workflow stays the focal path.

Add an explicit verification checkpoint before destructive remediation (e.g. 'after applying the fix, rerun with af runs clear and confirm the run goes green before declaring resolved') to close the feedback loop around the clear/delete quick commands.

DimensionReasoningScore

Conciseness

The body is dense and technical, assuming Claude's competence — it never explains what Airflow or a DAG is — and nearly every line is actionable domain knowledge (Astro deploys, venv-style operator drift, index lookup) that earns its place, fitting the lean-and-efficient anchor.

3 / 3

Actionability

Provides copy-paste-ready, fully executable commands throughout — 'af runs diagnose <dag_id> <dag_run_id>', 'af tasks logs …', the docker pip-freeze diff, and the curl/jq PyPI release query — matching the anchor for executable code and specific examples.

3 / 3

Workflow Clarity

A clear four-step sequence (Identify → Get Details → Check Context → Provide Output) with failure-type categorization and a structured output template, plus root-cause verification beats ('compare the failed run against recent successful runs', 'a release timestamp landing between the last green run and the first red run… is the answer'), meeting the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

Sections are well-organized with a well-signaled in-document link ('See [Package version changes](#package-version-changes) below'), but at ~120 lines with no external reference files, specialized deep-dives (Package version changes, On Astro, On OSS Airflow) are inline that could be split into one-level-deep reference files, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

11

/

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.

The description is specific, trigger-rich, and complete, with an explicit 'Use when' clause and a direct disambiguation against the simpler airflow skill. It is a strong, low-conflict description.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'DAG failure diagnosis', 'root-cause analysis', 'structured investigation and prevention recommendations', 'fixing a broken DAG so it loads cleanly' — matching the anchor that lists several specific concrete actions rather than a vague domain label.

3 / 3

Completeness

Explicitly answers both what (diagnosis, root-cause analysis, prevention) and when via a clear 'Use when deep failure investigation is needed…' clause with concrete triggers, satisfying the top anchor for both what AND when.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say — 'why did X fail', 'my dag keeps failing — find and fix it', 'a DAG fails to import/parse', 'airflow dags list errors on a file' — giving strong coverage of realistic trigger terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (deep root-cause debugging) and explicitly disambiguates from a sibling — 'For simple "why did it fail / show logs", the airflow skill handles it directly' — making conflict with the airflow skill unlikely.

3 / 3

Total

12

/

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.

Validation16 / 16 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.