palamedes — tool profile and history

Rigorous LLM research in two layers: a multi-agent dialectic synthesis prompt + an agent-loadable research skill. Hierarchy of evidence, verbatim citation gates, no fabrication.

Active

Canonical source ↗

Language
Python
Created
Last activity
Topics
  • adversarial-ai
  • claude-skill
  • confidence-scoring
  • cursor-rules
  • epistemic-calibration
  • epistemics
  • evidence-synthesis
  • hierarchy-of-evidence
  • llm
  • llm-research
  • multi-agent
  • prompt-engineering
  • research

Install git clone https://github.com/weijia-89/palamedes ~/.claude/skills/palamedes

Current measurement

0GitHub starsstable
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars
0GitHub stars

Classifications

Domains
Type
Agent skills
Use cases