andrej-karpathy

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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

A tight, actionable, well-structured behavioral skill that respects token budget while giving concrete directives and verification-oriented workflows. No bundle files are needed for this single-purpose guideline skill.

Dimension	Reasoning	Score
Conciseness	Lean bullet-driven guidance with no padding or explanation of concepts Claude already knows; every section (Think Before Coding, Simplicity First, etc.) earns its tokens.	3 / 3
Actionability	Concrete, specific directives ('No abstractions for single-use code', 'Remove imports/variables/functions that YOUR changes made unused') plus worked transformation examples make the guidance directly applicable for an instruction-only skill.	3 / 3
Workflow Clarity	The Goal-Driven Execution section provides a sequenced plan template with per-step 'verify: [check]' checkpoints and an explicit loop-until-verified feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the single-file body is well-organized into clear sections (When to Use, four numbered guidelines, Examples, Limitations) with no nested references.	3 / 3
	Total	12 / 12 Passed

Description

92%

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

A strong, third-person description that clearly states purpose and triggers with concrete behavioral actions. Its main weakness is the broad coding trigger, which risks overlapping with other coding skills.

Suggestions

Tighten the trigger to distinguish from generic coding skills, e.g. 'Use when an LLM-assisted code change risks overcomplication or scope creep' to sharpen the niche.

Add a concrete disambiguating phrase such as 'when you want the change to stay surgical and verifiable' to lower conflict risk with general refactor/review skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('reduce common LLM coding mistakes') and lists several concrete behavioral actions: 'avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria'.	3 / 3
Completeness	Explicitly answers both what ('Behavioral guidelines to reduce common LLM coding mistakes') and when (explicit 'Use when writing, reviewing, or refactoring code...') with a clear trigger clause.	3 / 3
Trigger Term Quality	The 'Use when writing, reviewing, or refactoring code' clause surfaces natural terms users actually say, with good coverage of the main coding activities.	3 / 3
Distinctiveness Conflict Risk	The behavioral niche is somewhat specific, but the trigger 'writing, reviewing, or refactoring code' is broad and could overlap with many general coding skills.	2 / 3
	Total	11 / 12 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: sickn33/antigravity-awesome-skills
Commit: 2aaaf59

Reviewed: about 6 hours 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.