원클릭으로 Manus에서 모든 스킬 실행

시작하기

co-scientist-doctor

스타4

포크0

업데이트2026년 6월 11일 02:39

Diagnose the local Co-Scientist host-agent environment from Codex.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

panjose

panjose/Co-Scientist

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

co-scientist-doctor

Goal:

Inspect whether the local project has the required runtime dependencies, skill installation surface, dashboard tooling, and optional bridge configuration.

Execution steps:

Run:

python -m tools.host.project_cli doctor

If structured output is needed, run:

python -m tools.host.project_cli doctor --format json

Report failing and warning checks with the exact recommended command from the doctor payload.

Rules:

Do not guess installed state from memory. Always call the doctor command.
Warnings for optional bridges are not pipeline failures unless a requested feature depends on that bridge.

이 저장소의 다른 Skills

같은 저장소

co-scientist-pipeline

panjose/Co-Scientist

Run the full Co-Scientist pipeline for one research run.

2026-06-114

convergence-check

panjose/Co-Scientist

Evaluate whether a hypothesis newly entered the current top-k set and update the convergence counter deterministically.

2026-06-114

dashboard-snapshot

panjose/Co-Scientist

Assemble a dashboard-ready snapshot from the canonical state.

2026-06-114

evolution-strategy-supervisor

panjose/Co-Scientist

Choose exactly one concrete evolution strategy for the active evolution round.

2026-06-114

hypothesis-deep-verification

panjose/Co-Scientist

Run the assumption decomposition and deep verification review for a hypothesis.

2026-06-114

hypothesis-evolution-loop

panjose/Co-Scientist

Run the iterative evolution loop from the current persisted run state until convergence.

2026-06-114

name	co-scientist-doctor
description	Diagnose the local Co-Scientist host-agent environment from Codex.

co-scientist-doctor

Goal:

Inspect whether the local project has the required runtime dependencies, skill installation surface, dashboard tooling, and optional bridge configuration.

Execution steps:

Run:

python -m tools.host.project_cli doctor

If structured output is needed, run:

python -m tools.host.project_cli doctor --format json

Report failing and warning checks with the exact recommended command from the doctor payload.

Rules:

Do not guess installed state from memory. Always call the doctor command.
Warnings for optional bridges are not pipeline failures unless a requested feature depends on that bridge.