test-guided-migration-assistant
Uses an existing test suite as the behavioral oracle during a migration, tracking which tests pass at each step and localizing regressions to specific migration changes. Use when porting or refactoring code that has tests, when the user wants to migrate incrementally with a safety net, or when a migration broke something and you need to find which step did it.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill test-guided-migration-assistant97
Quality
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 a specific, well-defined capability. It uses third person voice correctly, provides concrete actions, includes natural trigger terms, and has an explicit 'Use when' clause with multiple relevant scenarios. The description effectively carves out a distinct niche that would be easy to differentiate from other testing or migration-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'uses test suite as behavioral oracle', 'tracking which tests pass at each step', 'localizing regressions to specific migration changes'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (uses test suite as oracle, tracks passing tests, localizes regressions) AND when with explicit 'Use when' clause covering three distinct scenarios: porting/refactoring with tests, incremental migration, and debugging broken migrations. | 3 / 3 |
Trigger Term Quality | Includes natural terms users would say: 'migration', 'porting', 'refactoring', 'tests', 'migrate incrementally', 'safety net', 'migration broke something'. Good coverage of both technical and conversational language. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining test-driven migration with regression localization. The specific focus on 'behavioral oracle' and 'localizing regressions to specific migration changes' clearly distinguishes it from general testing or refactoring skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%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 provides comprehensive, actionable guidance for test-guided migrations. It excels at workflow clarity with explicit validation checkpoints and feedback loops, includes concrete examples with real code, and maintains token efficiency by assuming Claude's competence. The worked example effectively demonstrates the methodology in practice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanation of what tests are or how migrations work conceptually. The content is dense with actionable guidance, tables, and examples without padding. | 3 / 3 |
Actionability | Provides concrete commands (pytest --cov, git bisect), executable code examples, specific thresholds (>70% coverage), and a complete worked example with real Python 2→3 migration scenarios. | 3 / 3 |
Workflow Clarity | Clear numbered steps with explicit validation checkpoints ('Never proceed with a red test'), ASCII flowchart for the decision process, and explicit feedback loops (bisect → fix → retry). The 'Do not' section reinforces critical validation requirements. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and a reference to external skill (test-suite-prioritizer), but the content is fairly long and some sections (like the worked example) could potentially be split into separate files. However, for a skill of this complexity, inline content is reasonable. | 2 / 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
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.