메뉴
Team of explorers that investigate a scientific phenomenon from multiple angles simultaneously
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | explore |
| description | Team of explorers that investigate a scientific phenomenon from multiple angles simultaneously |
| argument-hint | the phenomenon and optionally direction to explore |
You are the Exploration Lead. You will be given a scientific phenomenon to explore, and then use the swarm skill to fan out a team of diverse explorers.
The goal right now is not to produce a full explanation for the phenomenon yet, but rather to explore it from multiple angles and to generate a rich set of observations, insights, and hypotheses for further investigation later on.
The phenomenon to explore is: $ARGUMENTS
Create the output folder at the start:
OUTPUT_DIR: mktemp -d -p ./tmp explore-output-XXXX
All exploration artifacts and temporary files go under this folder. Swarm agents should write to <OUTPUT_DIR>/{agent-name}/ and append lab-notebook entries to <OUTPUT_DIR>/{agent-name}/explorer_log.md.
<OUTPUT_DIR>/<agent-name>/, write lab-notebook entries to <OUTPUT_DIR>/<agent-name>/explorer_log.md, actually read image outputs, run at least 3 experiments, follow up on surprisesrun-experiment skill. The skill will need to know an AGENT_TYPE name, which should be explorer. Record each resulting X_... experiment ID in your lab-notebook entry alongside a summary of the findings.explorer_log.md. Markdown image references should be relative to <OUTPUT_DIR>/./swarm "<task>" N=5 — swarm will assign diverse approaches (ensure at least one quantitative and one qualitative angle are covered by describing this in the task)explorer_log.md and concatenate them into <OUTPUT_DIR>/report.md. Make sure you update any image references to be relative to <OUTPUT_DIR>/. Then append a ## Synthesis section weaving findings together./swarm again on that specific finding before synthesizing.uv run python <SKILL_BASE_DIR>/scripts/context_manager.py store_results --from_agent_type explorer --from_folder <OUTPUT_DIR>
E_20260414_143052_a1b2c3) as the result of this skill.Design and propose the next step: either a regular data-gathering experiment, literature search, or a concrete solution candidate.
Determine the type of proposal given, execute/delegate accordingly, and return the appropriate resulting ID (experiment ID, literature search ID, or solution ID).
Score and rank solution candidates relative to the research goal, and update parent theory scores.
Integrate recent interpretations from the interpretation log into the associated theory.
Rank the given experiments based on their importance for evaluating theories.
Interpret the results of newly run experiments, literature searches, or solution candidates, and append the findings as new sections to the interpretation log inside the theory folder.