Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/ccs-artifact-evaluation
Use when packaging ACM CCS artifacts for the artifact-evaluation committee and the ACM badges — Artifacts Available, Artifacts Evaluated Functional, Artifacts Evaluated Reusable, and Results Reproduced — covering what security evaluators inspect, how to make attacks and defenses turnkey, and how to justify withheld artifacts.
Passed 19 of 22 test cases with the skill, and 14 of 22 without it.
and 5 more in the full report
5 fixed14 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our accepted CCS paper presents a zero-knowledge proof library. What specific asset must be present in the artifact repository for evaluators to verify correctness, and what failure commonly occurs?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies test vectors and reference builds as required verification assets | Missed | Passed |
| Warns that missing test vectors prevent evaluators from checking output correctness | Missed | Passed |
The instructions your model reads when the skill loads.
Use this for artifact packaging around CCS. CCS runs an optional artifact-evaluation process after acceptance; passing artifacts earn ACM badges that appear on the paper's first page. Reopen the current call for artifacts for the exact badge set, submission form, and deadlines.
| Badge | What it certifies | What the committee does |
|---|---|---|
| Artifacts Available | The artifact is publicly archived with a stable identifier | Confirms the artifact is retrievable and permanent |
| Artifacts Evaluated - Functional | The artifact runs and does what the paper says | Executes it against the documented steps |
| Artifacts Evaluated - Reusable | It exceeds functional quality and others can reuse it | Judges structure, documentation, and reusability |
| Results Reproduced | The main paper results are independently reproduced | Reruns experiments and checks they support the claims |
Available is about archival permanence; Functional and Reusable are about quality; Results Reproduced is the highest bar and requires the committee to regenerate your headline numbers.
| Claim type | First artifact inspected | Common failure caught |
|---|---|---|
| Exploit against real software | The PoC and its target build instructions | Target version unspecified; PoC fails to build |
| Defense with overhead numbers | The benchmark runner and instrumented build | Overhead cannot be reproduced; workload undocumented |
| Measurement study | The collection and classification scripts | Classification rule differs from the paper's prose |
| Cryptographic implementation | Test vectors and the reference build | No test vectors; outputs cannot be checked |
test cases passed, vs 14 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.