serpro69/claude-toolbox-dependency-handling
|
npx skills add https://github.com/serpro69/claude-toolbox --skill dependency-handling
<!-- codex: tool-name mapping applied. See .codex/scripts/session-start.sh -->
Mandatory order — lookup before usage. Do not write, modify, or recommend any call, import, config key, or version specifier involving the dependency until you have completed the lookup cascade below. Guessing a signature or API version and fixing it after the fact is the failure mode this skill exists to prevent.
kk:lang-idioms and kk:project-conventions for previously indexed knowledge about this dependency.kk:lang-idioms and kk:project-conventions for previously indexed knowledge about the dependency.kk:lang-idioms so the next agent doesn't pay the lookup cost again.The cascade rule (capy-first, context7-second, web-last) applies uniformly to all dependency categories — libraries, SDKs, frameworks, APIs, IaC API versions, CRDs, Helm charts, and container images. Per-domain lookup targets (which context7 library to query, which local command to run, which registry to consult) live in each profile's overview.md under a "Looking up dependencies" heading. When the k8s profile is active, consult ../../profiles/k8s/overview.md under the ## Looking up Kubernetes dependencies heading for Kubernetes API versions, third-party CRDs, Helm chart versions, and container image targets.
Take serpro69/claude-toolbox-dependency-handling from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.