code-translation
Translates a single function or small code unit between programming languages, mapping idioms and preserving observable behavior. Use when porting one function, when the user pastes code and asks for it in another language, or as the per-unit primitive for larger migrations.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill code-translation94
Quality
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
85%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 well-crafted description that clearly defines scope (single function/small code unit), specifies the approach (mapping idioms, preserving behavior), and provides explicit trigger scenarios. The main weakness is trigger term coverage - it could benefit from more natural language variations users might employ when requesting code translation.
Suggestions
Add more natural trigger terms users commonly say, such as 'convert', 'rewrite in [language]', 'port to', or specific language pairs like 'Python to JavaScript'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Translates a single function or small code unit', 'mapping idioms', 'preserving observable behavior'. These are precise, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Translates a single function or small code unit between programming languages, mapping idioms and preserving observable behavior') and when ('Use when porting one function, when the user pastes code and asks for it in another language, or as the per-unit primitive for larger migrations'). | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'porting', 'pastes code', 'another language', but misses common variations users might say like 'convert', 'rewrite in', specific language names, or 'translate code'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on single function/small unit translation between languages, explicitly scoped to avoid overlap with larger migration tools or general code assistance. The 'per-unit primitive' framing further distinguishes it. | 3 / 3 |
Total | 11 / 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 exemplary skill that demonstrates expert-level content design. It efficiently conveys complex translation knowledge through tables, provides a complete worked example with semantic delta annotations, and includes clear verification steps. The 'Do not' section and semantic minefields table show deep understanding of where translations fail.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely efficient use of tokens. Tables compress language-pair gotchas elegantly. No explanation of what code translation is or how languages work—assumes Claude's competence throughout. Every section earns its place. | 3 / 3 |
Actionability | Provides fully executable code examples (Python and Go), concrete idiom mapping tables, specific semantic minefields per language pair, and a clear output format template. The worked example is copy-paste ready with detailed annotations. | 3 / 3 |
Workflow Clarity | Clear three-layer mental model (syntax/semantics/idiom), explicit instruction to 'write down three semantic mismatches before translating,' verification step pointing to specific tools, and structured output format. The 'Do not' section provides explicit guardrails. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (layers, minefields, idiom mapping, worked example, verification, anti-patterns, output format). References to related skills (module-level-code-translator, behavior-preservation-checker) are one level deep and clearly signaled with arrows. | 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.