63 tagged code-execution, measured the same way as everything else here.
Browse within: agents 59Autonomous Agents 57clinical-data 57clinical-research 57clinical 22system 7
Skill Claude CodeCodex
Use when an agent needs isolated, forkable compute, running untrusted or model-written code safely, or exploring several attempts in parallel (best-of-N) and keeping the winner. Mitos boots Firecracker microVMs and forks a running VM via copy-on-write snapshots, so a fan-out is cheap and each attempt is…
Skill Claude CodeCodex
Generate and execute code for acting with Python tools. Activate when user explicitly requests to "use the codeact skill" or similar phrases.
Skill Claude CodeCodex
The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.
Skill Claude CodeCodex
Reproduce a GitHub issue with a failing test, implement the minimal fix, verify tests pass, and open a pull request. Use this skill when given an issue number and a working checkout of the target repository.
Skill Claude CodeCodex
Use when about to state a number, claim two programs are equivalent, claim a speedup, or state a complexity — codecalc computes these exactly instead of estimating them, and this file says when calling is mandatory and how results must be reported.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: