legacy-code-summarizer
Summarizes undocumented legacy code by inferring intent from structure, naming, data flow, and calling context — explicitly flagging what's inferred vs. what's certain. Use when onboarding to inherited code, when documentation is missing or wrong, or when deciding whether legacy code is safe to change.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill legacy-code-summarizer100
Quality
100%
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 capability (summarizing undocumented legacy code with inference flagging), uses natural trigger terms users would actually say, and provides explicit 'Use when' guidance covering multiple relevant scenarios. The description is concise yet comprehensive, and carves out a distinct niche that won't conflict with general code analysis skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Summarizes undocumented legacy code by inferring intent from structure, naming, data flow, and calling context' and 'explicitly flagging what's inferred vs. what's certain'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Summarizes undocumented legacy code by inferring intent...flagging what's inferred vs. certain') AND when ('Use when onboarding to inherited code, when documentation is missing or wrong, or when deciding whether legacy code is safe to change'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'legacy code', 'undocumented', 'inherited code', 'documentation is missing', 'safe to change'. These cover common variations of how users describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on undocumented/legacy code analysis with distinct triggers like 'legacy', 'inherited', 'documentation missing'. Unlikely to conflict with general code review or documentation skills due to the specific legacy/undocumented focus. | 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 demonstrates how to write actionable, concise guidance. It teaches a specific methodology (archaeology with confidence tagging) through concrete examples rather than abstract explanation. The worked Perl example is particularly strong—it shows exactly what good output looks like with real confidence markers and hazard identification.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The reliability table is dense and useful, the worked example demonstrates rather than explains, and there's no padding about what legacy code is or why documentation matters. Claude's intelligence is respected throughout. | 3 / 3 |
Actionability | Provides concrete code examples (C function trace, Perl summary), specific shell commands for archaeology, and a copy-paste-ready output format. The worked example shows exactly what a good summary looks like with real confidence tags. | 3 / 3 |
Workflow Clarity | Clear three-step process (trace data → check callers → mark confidence) with explicit sequencing. The confidence tagging system provides built-in validation checkpoints, and the 'Do not' section prevents common workflow errors. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections: evidence hierarchy, steps, worked example, tools reference, anti-patterns, and output format. Content is appropriately inline for a skill of this scope—no need for external files, and the tables provide quick-reference density. | 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.
- 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.