coding-agent-helpers/regression-scout
Use when the user wants regression hunting after a change. Identify nearby flows, shared code paths, error states, and configuration edges that may have broken even if the main fix works. Good triggers include "check for regressions", "what else might this have broken", and "test the surrounding area".
96
94%
Does it follow best practices?
Impact
98%
2.72xAverage score across 8 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 a strong skill description that clearly defines its purpose (regression hunting after changes), lists specific concrete actions, and provides explicit trigger phrases. It uses third person voice appropriately and covers both the 'what' and 'when' dimensions thoroughly. The description is concise yet comprehensive, with natural language triggers that users would realistically use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Identify nearby flows, shared code paths, error states, and configuration edges', 'run focused checks such as related tests, adjacent commands, or neighboring API paths'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (identify nearby flows, shared code paths, error states, run focused checks) and when ('Use when the user wants regression hunting after a change') with explicit trigger examples listed under 'Good triggers include...'. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'check for regressions', 'what else might this have broken', 'test the surrounding area', plus domain terms like 'regression hunting', 'shared code paths', 'related tests'. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around regression hunting and blast-radius analysis after code changes. The specific focus on 'nearby flows', 'adjacent commands', and 'neighboring API paths' distinguishes it well from general testing or debugging skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, concise skill that clearly defines a regression hunting workflow with an explicit output format and useful mini example. Its main weakness is that the 'Run focused checks' step could be more actionable with concrete tool usage patterns (e.g., specific commands for finding related tests, grep patterns for shared code paths). Overall it's a strong instruction-only skill that respects token budget while providing clear guidance.
Suggestions
Add 1-2 concrete examples of how to identify and run focused checks, such as specific grep/search patterns for shared code paths or example test runner commands for nearby test targets.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line serves a purpose. No unnecessary explanations of what regressions are or how testing works. The skill assumes Claude's competence and focuses purely on the process and output format. | 3 / 3 |
Actionability | The workflow provides clear conceptual steps and the output format is well-specified with examples, but the 'Run focused checks' step lacks concrete executable commands or code. Phrases like 'nearby test targets' and 'adjacent commands or routes' are somewhat abstract rather than showing specific tool invocations (e.g., running test commands, grep patterns for shared code paths). | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced from identifying the change surface through reporting. The output format with exact headings serves as a validation checkpoint, and the rules section provides explicit constraints including minimum check counts and required result annotations. The mini example demonstrates the expected flow end-to-end. | 3 / 3 |
Progressive Disclosure | This is a concise, single-purpose skill under 50 lines that is well-organized with clear sections (Goal, Workflow, Output Format, Rules). No external references are needed and the content is appropriately structured for its scope. | 3 / 3 |
Total | 11 / 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.
Reviewed
Table of Contents