Designing a client library other people will depend on: surface area and what to hide, error types that callers can act on, retry and timeout defaults that are safe to inherit, configuration precedence and credential handling, semantic versioning and the deprecation of a published method, language idiom and packaging, and the written SDK record. It explains how a client earns trust; it never recommends a language ecosystem and never promises stability. Use when asking "SDK design", "client library", "public API surface", "error types", "default retry in SDK", "semantic versioning for libraries", "deprecating a method", "credential handling in SDK", "why do people hate our SDK". Not for public HTTP API contracts (ac-api-design), not for package publishing logistics (ac-ci-and-release), not for client-side application architecture (ac-architecture).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-sdk-and-client-library-design .claude/skills/clawhub install anoscranel-ac-sdk-and-client-library-designCapabilities below are detected automatically by an open-source scanner that reads the skill's text and scripts (see how this is computed). Not measured means the scanner couldn't make a confident call — it is NOT a green check, and you should treat it as a possible red flag until a human or a stronger scanner has measured it.
read_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
We did not find any well-known hosted services in this skill's text or scripts. This does NOT mean the skill is local-only — it might use services we don't yet recognize, or talk to them through code paths our scanner can't reach. A complete dependency list (every package, library, and binary, with integrity hashes) is on the roadmap; today we only show recognized hosts.
No one has audited this skill yet. That is different from “audited and clean” — it just means no professional reviewer (a security firm, the CryptoSkill team, or a verified independent researcher) has signed off on it. There are no audit reports to read. How reviewer levels work →
SKILL.md → SOURCE.md → TRUST.auto.yaml → Browse directory →
Auto-generated by cryptoskill/extract-capabilities/0.3.1 · hosted-service list version 2026-09-06 · how this is computed