szz-bug-identifier
Applies the SZZ algorithm to VCS history to identify which commits introduced bugs by correlating bug-fix commits with earlier changes. Use when mining a repository for bug-introducing commits, when building a defect-prediction dataset, or when the user asks which commit introduced a given fixed bug.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill szz-bug-identifier97
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 specialized capability (SZZ algorithm for bug introduction analysis) with specific actions and explicit trigger conditions. It uses third person voice correctly, provides domain-specific but natural terminology, and carves out a distinct niche that won't conflict with general version control skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Applies the SZZ algorithm', 'identify which commits introduced bugs', 'correlating bug-fix commits with earlier changes'. These are precise, technical operations clearly describing what the skill does. | 3 / 3 |
Completeness | Clearly answers both what ('Applies the SZZ algorithm to VCS history to identify which commits introduced bugs') AND when ('Use when mining a repository for bug-introducing commits, when building a defect-prediction dataset, or when the user asks which commit introduced a given fixed bug'). | 3 / 3 |
Trigger Term Quality | Includes natural terms users would say: 'bug-introducing commits', 'defect-prediction dataset', 'which commit introduced a given fixed bug', 'mining a repository', 'VCS history'. Good coverage of domain-specific but user-natural terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific triggers like 'SZZ algorithm', 'bug-introducing commits', 'defect-prediction dataset'. This is a clear niche that would not conflict with general git or code analysis 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 a high-quality skill that efficiently explains the SZZ algorithm with concrete commands, a complete worked example, and explicit validation filters. The noise filter table is particularly well-structured. Minor weakness is the unclear reference format for related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude understands git, blame, and basic algorithms. No unnecessary explanations of what git is or how version control works. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete git commands (`git blame -w`, `git blame -C -M`, `git blame --ignore-rev`), a complete worked example with actual diff syntax, and specific filter criteria. The algorithm steps are executable. | 3 / 3 |
Workflow Clarity | The 4-step algorithm is clearly sequenced, the worked example walks through each step with explicit filter validation checkpoints, and edge cases are enumerated with specific handling guidance. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but references to other skills (`semantic-szz-analyzer`, `regression-root-cause-analyzer`) use arrow notation without explaining if these are files to consult. The skill is self-contained but could better signal external references. | 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.