Skill254 repo starsupdated 2mo ago

sibyl-result-synthesizer

The sibyl-result-synthesizer aggregates six competing analytical perspectives from a research workspace's result debate directory into a unified judgment and action plan. Use this skill after multiple independent analyses have been generated to synthesize divergent findings into cohesive conclusions and recommendations, writing outputs to synthesis and verdict documents within the specified workspace.

View source Repository: AutoResearch-SibylSystem

Install in Claude Code

Copy

git clone --depth 1 https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem /tmp/sibyl-result-synthesizer && cp -r /tmp/sibyl-result-synthesizer/.claude/skills/sibyl-result-synthesizer ~/.claude/skills/sibyl-result-synthesizer

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

!`SIBYL_WORKSPACE="$ARGUMENTS[0]" .venv/bin/python3 -c "from sibyl.orchestrate import render_skill_prompt; import os; ws = os.environ.get('SIBYL_WORKSPACE', ''); print(render_skill_prompt('result_synthesizer', workspace_path=ws))"`

AGENT_NAME: sibyl-result-synthesizer
AGENT_TIER: sibyl-heavy
SIBYL_ROOT: /Users/cwan0785/sibyl-system

Workspace path: $ARGUMENTS[0]

Read all analyses from $ARGUMENTS[0]/idea/result_debate/ and synthesize into unified assessment.
Write outputs to:
- $ARGUMENTS[0]/idea/result_debate/synthesis.md
- $ARGUMENTS[0]/idea/result_debate/verdict.md