ericrisco/rsc-harness / skills/cpp
cpp
VerifiedUse when writing, reviewing, modernizing, building, or debugging C++ - RAII and resource lifetime, smart-pointer ownership, move semantics and the Rule of Zero/Five, target-based CMake with FetchContent, and killing undefined behavior with ASan/UBSan/TSan plus clang-tidy. NOT borrow-checker / Result-Option / cargo memory safety (that is rust).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.5 KB |
| evals/README.md | markdown | 1.1 KB |
| evals/cases.yaml | config | 3.9 KB |
| references/cmake.md | markdown | 5.2 KB |
| references/move-and-templates.md | markdown | 5.2 KB |
| references/undefined-behavior.md | markdown | 5.5 KB |
| scripts/verify.shexecutable | script | 5.8 KB |
evals/README.md
View on GitHub# Eval harness — `cpp` skill
These cases are run by the rsc skill-eval harness (a Claude agent with the full skill catalog
loaded), or read manually. They measure two things: **triggering** — that the `cpp` skill's
description fires on each `should_trigger` prompt and stays quiet on the `should_not_trigger`
near-misses, routing each of those to the named real sibling (`rust`, `security-audit`,
`deployment`, `go`, `harness`) instead; and **capability** — that, with `SKILL.md` and its
references loaded, a graded model's generated C++ satisfies the `capability.must_include` rubric
(RAII over raw resources, smart-pointer ownership, no `new`/`delete`, target-based CMake with
warnings-as-errors, an ASan+UBSan build) and beats the no-skill baseline by a clear margin. Run
3–5 trials per prompt since LLM routing is non-deterministic; a prompt passes on a majority. No
network is needed — the capability rubric is judged by reading the output against the points, and
the verify.sh gate (compile under sanitizers + ctest) is exercised separately against a real
project, not as part of these cases.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |