coding

Rosetta coding skill for implementation with KISS/SOLID/DRY principles, zero-tolerance quality, multi-environment awareness, and systematic validation. Use when implementing features, fixing bugs, or making code changes.

1.02x

Quality

41%

Does it follow best practices?

Impact

85%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./instructions/r2/core/skills/coding/SKILL.md

Quality

Discovery

32%

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 description relies heavily on buzzwords and abstract principles (KISS, SOLID, DRY, zero-tolerance quality) without specifying concrete actions the skill performs. While it includes a 'Use when' clause, the triggers are so broad ('implementing features, fixing bugs, or making code changes') that they would match nearly any coding skill, creating high conflict risk. The description fails to communicate what makes this skill distinct or what specific capabilities it offers.

Suggestions

Replace abstract buzzwords with concrete actions the skill performs (e.g., 'Generates implementation code with test coverage, refactors existing code for maintainability, validates changes across environments').

Narrow the 'Use when' clause to specific, distinguishable triggers rather than the overly broad 'implementing features, fixing bugs, or making code changes'—specify what kind of code, language, or context makes this skill the right choice over other coding skills.

Clarify what 'Rosetta coding skill' means in practical terms—does it translate between languages, apply specific patterns, or target a particular codebase? This would greatly improve distinctiveness.

Dimension	Reasoning	Score
Specificity	The description uses abstract buzzwords like 'KISS/SOLID/DRY principles', 'zero-tolerance quality', 'multi-environment awareness', and 'systematic validation' without listing any concrete actions. It does not describe what the skill actually does in terms of specific operations.	1 / 3
Completeness	It has a 'Use when...' clause mentioning implementing features, fixing bugs, or making code changes, which addresses the 'when'. However, the 'what' is vague—it says 'Rosetta coding skill for implementation' without clearly explaining what it concretely does.	2 / 3
Trigger Term Quality	It includes some natural terms like 'implementing features', 'fixing bugs', and 'code changes' that users might say, but these are extremely broad. Terms like 'zero-tolerance quality' and 'multi-environment awareness' are not things users would naturally say.	2 / 3
Distinctiveness Conflict Risk	The triggers 'implementing features, fixing bugs, or making code changes' are extremely generic and would conflict with virtually any coding-related skill. There is nothing that carves out a distinct niche.	1 / 3
	Total	6 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a comprehensive set of coding principles, constraints, and validation requirements but reads more like a policy document than an actionable implementation guide. Its strengths are in defining clear boundaries (300 LOC, zero tolerance for errors, multi-environment requirements) and listing useful MCP resources. Its weaknesses are the lack of concrete executable examples, the absence of a clear step-by-step implementation workflow with explicit validation checkpoints, and some verbosity in stating principles Claude already understands.

Suggestions

Add a concrete step-by-step implementation workflow (e.g., '1. Load context → 2. Review existing code → 3. Implement changes → 4. Validate: run tests → 5. If failures: fix and re-validate → 6. Code review via git diff') with explicit validation checkpoints and feedback loops.

Include at least one concrete example for the CODEMAP.md format showing the expected markdown structure, and a sample shell script for the background service start/stop pattern.

Remove or compress well-known principle acronyms (KISS, SOLID, SRP, DRY, YAGNI, MECE) into a single line — Claude knows these — and use the saved tokens for actionable examples.

Consider splitting the detailed file format specifications (CODEMAP.md, DEPENDENCIES.md, TECHSTACK.md) into a separate reference file to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes some redundancy and concepts Claude already knows (KISS, SOLID, DRY, YAGNI are well-known acronyms that don't need listing). The documentation file specifications (CODEMAP.md format) add value, but some bullet points are verbose or repeat ideas (e.g., 'no cheating, no pre-existing excuses' is vague padding).	2 / 3
Actionability	Provides concrete checklists and specific constraints (300 LOC limit, validation order, file naming conventions) but lacks executable code examples or copy-paste-ready commands. The validation methodology describes an order (databases → APIs → Web → Mobile) but doesn't give concrete command examples. The CODEMAP.md format description is specific but would benefit from a concrete example.	2 / 3
Workflow Clarity	The validation checklist and validation methodology provide a clear sequence (databases → APIs → Web → Mobile), and there's mention of checking logs and cleaning up. However, the overall implementation workflow lacks explicit step-by-step sequencing with validation checkpoints — it's more a collection of rules than a clear workflow. The feedback loop for error recovery is implicit ('all tests MUST succeed') rather than explicit (validate → fix → retry).	2 / 3
Progressive Disclosure	References to other skills (debugging, planning, tech-specs) and MCP tools are well-signaled in the resources section. However, there are no bundle files to support the references, and the content is somewhat monolithic — the core_concepts section is dense and could benefit from splitting detailed file format specifications into separate reference files. The XML-like structure provides some organization but sections like core_concepts mix multiple concerns.	2 / 3
	Total	8 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: griddynamics/rosetta
Commit: ade2cc5

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.