Applies strict, modern language practice (typed errors, exhaustive match, tests that can fail) for Python, Rust, TypeScript, JavaScript, and Go. Use for work on .py, .rs, .ts, .js, or .go files, and whenever a test or spec file is written, reshaped, reviewed, or deleted: the four-question test authoring gate and the junk-test classes live here.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads the skill's own reference files, the user's repository code, tests, and manifests, but a dependency upgrade directs the agent to read upstream package changelogs (SKILL.md line 175), which are third-party maintainer text the agent fetches on its own initiative rather than text an outsider can force into the workflow.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The inbound boundary is the setup-time `go install mvdan.cc/gofumpt@latest` instruction in bootstrap.md, which fetches and builds code from an individual maintainer's module (unofficial, but a stable, attributable, reputable project), so it is a common/reputable unofficial dependency, tier medium.
code-yeongyu/lazycodex
7e2aae8
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.