dataflow-mapping
Trace and document how data transforms through a multi-step pipeline or function chain, showing intermediate state at each step with concrete example values. Use when explaining a data pipeline or complicated codepaths, tracing how a value changes across function calls, answering questions like "how does X get to Y", or producing a step-by-step dataflow walkthrough for a code review or design doc.
99
100%
Does it follow best practices?
Impact
98%
1.15xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly articulates specific capabilities (tracing data transformations, showing intermediate state with concrete values), provides a comprehensive 'Use when' clause with multiple natural trigger scenarios, and occupies a distinct niche unlikely to conflict with other skills. The description is concise yet thorough, using third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'trace and document how data transforms', 'showing intermediate state at each step', 'with concrete example values'. These are specific, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (trace and document data transformations through pipelines, showing intermediate state with example values) and 'when' (explicit 'Use when' clause listing four specific trigger scenarios including explaining pipelines, tracing values, answering 'how does X get to Y' questions, and producing walkthroughs). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'data pipeline', 'function chain', 'how does X get to Y', 'dataflow walkthrough', 'code review', 'design doc', 'tracing how a value changes across function calls'. These cover a good range of natural phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around data transformation tracing and pipeline documentation with intermediate state visualization. This is distinct from general code explanation, debugging, or documentation skills due to its focus on step-by-step dataflow with concrete values. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently teaches a specific documentation technique through concrete examples rather than abstract explanation. The three examples at different complexity levels (single function, multi-stage pipeline, authorization flow) demonstrate the format thoroughly while the tips section adds practical edge-case guidance. The format specification is precise with well-defined symbols and conventions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It assumes Claude's competence, avoids explaining what dataflow tracing is conceptually, and jumps straight into the format specification and examples. Every section earns its place. | 3 / 3 |
Actionability | The skill provides a concrete format template, three detailed examples at different complexity levels (multi-stage pipeline, compile pipeline, single function), and specific tips for producing good traces. The examples are copy-paste ready and demonstrate the exact output format expected. | 3 / 3 |
Workflow Clarity | The 'When to use which depth' section clearly sequences the decision of how much detail to show. The format specification is unambiguous with explicit symbols (→, ✓, ✗, ←) and their meanings. For this type of skill (producing documentation artifacts rather than destructive operations), validation checkpoints are not needed, and the workflow is clear. | 3 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized with clear sections: format specification, depth guidance, three graduated examples, and tips. The structure progresses logically from format → when to use → examples → tips, and the length is appropriate without needing external files. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- gitlabhq/orbit-knowledge-graph
- Commit
f5efc36
- 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.