codesmith

Expert code writer - produces clean, production-ready code

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/codesmith/SKILL.md

Quality

Content

46%Weight 40%Scale 1-5

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

The body is a well-structured but generic persona brief padded with widely-known programming principles, rescued partially by two concrete code examples and a delivery checklist that provide some actionable and workflow value.

Suggestions

Cut the explanatory definitions of DRY/SOLID and the generic language-feature lists, keeping only guidance that is non-obvious or project-specific to improve conciseness.

Complete the TypeScript example (replace '// Implementation' with real method bodies) and add a runnable Python example that demonstrates the error-handling pattern end-to-end.

Tighten the delivery checklist into an explicit validate-then-fix workflow with a feedback loop so the workflow sequence earns a higher clarity score.

Dimension	Reasoning	Score
Conciseness	Large portions restate concepts Claude already knows ('DRY: Don't Repeat Yourself', 'SOLID: Follow SOLID principles', 'PEP 8 compliance', 'ES6+ features') with no novel information, though the two code examples prevent a score of 1.	2 / 5
Actionability	Two concrete code examples are present, but the TypeScript 'Clean Structure' example is incomplete ('// Implementation') and most of the body is abstract principle lists rather than executable guidance.	3 / 5
Workflow Clarity	A pre-delivery 'Code Quality Checklist' provides a light verification sequence, but there is no real multi-step workflow with explicit checkpoints or feedback loops; it fits the 'steps listed but validation gaps' anchor.	3 / 5
Progressive Disclosure	No bundle files exist and the single file is well-organized into clear sections, which is appropriate for a persona skill; minor organization gaps (inline language-expertise lists) keep it below 5.	4 / 5
	Total	12 / 20 Passed

Description

25%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a generic persona tagline that names the code-writing domain but provides no concrete actions, no natural trigger terms, and no use-when guidance, making it indistinguishable from many coding skills.

Suggestions

Replace quality adjectives with concrete actions, e.g. 'Implements features, refactors existing code, and fixes bugs across Python and TypeScript projects.'

Add an explicit 'Use when...' clause naming natural trigger phrases users would say, such as 'implement a function', 'refactor this module', or 'write production code'.

Narrow the niche to reduce conflict risk, e.g. by scoping to specific languages, task types, or integration contexts.

Dimension	Reasoning	Score
Specificity	The phrase 'Expert code writer' names the domain but 'produces clean, production-ready code' is a quality claim rather than concrete actions like write, refactor, or debug, matching the 'names domain but actions minimal/generic' anchor.	2 / 5
Completeness	It offers a vague 'what' (expert code writer) with no 'when' or Use-when clause at all; per the missing-trigger cap this stays low and the what itself is vague, matching the 'vague what and no when' anchor.	2 / 5
Trigger Term Quality	'code writer' is a descriptor rather than a natural user utterance, and the description lacks common synonyms users actually say (implement, build, refactor), fitting the 'one or two generic keywords' anchor.	2 / 5
Distinctiveness Conflict Risk	'code writer' is very broad and would overlap with virtually any implementation skill, matching the 'very broad; high overlap risk' anchor rather than the entirely-generic score 1.	2 / 5
	Total	8 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: TurnaboutHero/oh-my-antigravity
Path: skills/codesmith/SKILL.md
Commit: f73e1ff

Reviewed: 15 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.