What a compiler and an ABI actually decide: compilation phases and where diagnostics come from, the distinction between language semantics and target behaviour, undefined behaviour and what it licenses the optimizer to do, the ABI as a binding contract for layout and calls, name mangling and symbol resolution, linking static versus dynamic and symbol visibility, and the written toolchain record. It explains how translation and linkage constrain code; it never recommends a compiler and never promises a binary outcome. Use when asking "undefined behavior", "ABI compatibility", "name mangling", "static versus dynamic linking", "symbol visibility", "linker errors", "compilation phases", "calling convention", "why does this work in debug but not release", "why is this struct size different". Not for build-system wiring and caching (ac-monorepo-and-build-systems), not for language runtime and concurrency (ac-async-and-concurrency), not for binary format design on disk (ac-binary-formats).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-compilers-and-abis .claude/skills/clawhub install anoscranel-ac-compilers-and-abisCapabilities 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