debugging-dags
Comprehensive DAG failure diagnosis and root cause analysis. Use for complex debugging requests requiring deep investigation like "diagnose and fix the pipeline", "full root cause analysis", "why is this failing and how to prevent it". For simple debugging ("why did dag fail", "show logs"), the airflow entrypoint skill handles it directly. This skill provides structured investigation and prevention recommendations.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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-crafted description that excels at completeness and distinctiveness by explicitly defining when to use it versus a related simpler skill. The trigger terms are natural and varied. The main weakness is that the specific capabilities could be more concrete—listing actual diagnostic actions rather than abstract phrases like 'structured investigation.'
Suggestions
Add more concrete action verbs describing what the skill actually does, e.g., 'analyzes task logs, traces dependency chains, identifies upstream failures, checks resource constraints, and provides prevention recommendations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (DAG failure diagnosis, root cause analysis) and mentions 'structured investigation and prevention recommendations,' but doesn't list multiple concrete actions like 'analyze task logs, trace dependency failures, check scheduler health, review XCom data.' The actions remain somewhat abstract. | 2 / 3 |
Completeness | Clearly answers both 'what' (comprehensive DAG failure diagnosis and root cause analysis, structured investigation and prevention recommendations) and 'when' (complex debugging requests requiring deep investigation, with explicit example triggers and a clear boundary distinguishing it from the simpler entrypoint skill). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'diagnose and fix the pipeline', 'full root cause analysis', 'why is this failing and how to prevent it', 'complex debugging'. Also differentiates from simpler queries like 'why did dag fail' and 'show logs', which helps with routing. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from the 'airflow entrypoint skill' for simple debugging, creating a clear boundary. The focus on 'complex debugging', 'deep investigation', and 'prevention recommendations' carves out a distinct niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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 diagnostic workflow skill with strong actionability through specific CLI commands and a clear multi-step investigation process. The workflow clarity is excellent with good branching logic and a structured output template. Minor weaknesses include some verbosity in explanatory sections and all content being inline rather than leveraging progressive disclosure for platform-specific guidance.
Suggestions
Consider splitting Astro-specific and OSS-specific context into separate reference files (e.g., ASTRO_DIAGNOSIS.md, OSS_DIAGNOSIS.md) to keep the main skill leaner.
Trim the explanatory text in Step 4's 'Root Cause' section — Claude doesn't need to be told the difference between a vague and specific root cause description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary elaboration. The 'On Astro' and 'On OSS Airflow' sections add context that could be trimmed. Some bullet points in Step 3 and Step 4 are slightly verbose (e.g., explaining what 'Root Cause' means with 'not the task failed but...'). However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | Provides specific, executable CLI commands throughout (af runs diagnose, af tasks logs, af runs clear, etc.) with concrete argument patterns. The failure categorization taxonomy is specific and useful. The Quick Commands section at the end gives copy-paste ready commands with placeholders. | 3 / 3 |
Workflow Clarity | Clear 4-step sequential workflow with logical progression from identification → error details → context gathering → actionable output. Each step has explicit sub-steps. The workflow handles branching cases (DAG specified vs not, run_id provided vs not). The diagnosis output structure in Step 4 serves as a validation/completeness checklist ensuring thorough analysis. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and logical sections, but everything is inline in a single file. The Astro-specific and OSS-specific sections could be split into separate reference files. For a skill of this length (~80 lines of content), some separation would improve scannability, though the lack of bundle files means there's no deeper reference structure. | 2 / 3 |
Total | 10 / 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
535a040
- 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.