code execution skills

67 tagged code execution, measured the same way as everything else here.

Browse within: Autonomous Agents 57clinical-data 57clinical-research 57clinical 22system 7

verify

01

BitMiracle-AI/Dormice

Skill Claude CodeCodex

Drive Dormice's built daemon over its public HTTP and E2B surfaces.

935 18d ago A 1 tokens original Apache-2.0

dormice

02

BitMiracle-AI/Dormice

Skill Claude CodeCodex

Operate Dormice self-hosted agent sandboxes — acquire a sandbox, run commands, move files, tune lifecycle policy — through the official E2B SDKs, the native HTTP API and SDK, or the dor CLI. Use when connecting to a Dormice server, running untrusted or AI-generated code in a sandbox, giving an agent a persistent…

935 18d ago A 85 tokens original Apache-2.0

mitos-sandboxes

03

mitos-run/mitos

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…

89 1mo ago C 97 tokens original Apache-2.0

codeact

04

gradion-ai/ipybox

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.

73 2mo ago A 30 tokens original Apache-2.0

zotero-mcp-code

05

kerim/zotero-code-execution

Skill Claude CodeCodex

Search Zotero library using code execution for efficient multi-strategy searches without crash risks. Use this skill when the user needs comprehensive Zotero searches with automatic deduplication and ranking.

59 7mo ago A 43 tokens original MIT

hype

06

gopherguides/hype

Skill Claude CodeCodex

Write and maintain documentation using the Hype content generation tool with dynamic code execution, snippets, and includes.

56 5mo ago A 23 tokens original MIT

hannesill/m4

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.

43 1mo ago A 0 tokens original MIT

hannesill/m4

Skill Claude CodeCodex

Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.

43 1mo ago A 59 tokens original MIT

hannesill/m4

Skill Claude CodeCodex

Start a structured clinical research session. Use when users describe research goals, want to analyze cohorts, investigate hypotheses, or need a rigorous research plan. Interviews the user, then produces a research protocol.

43 1mo ago A 44 tokens original MIT

bug-fix

10

nightona-co/nightona

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.

9 8d ago A 47 tokens AGPL-3.0