agentsclimarketplace

Co scientist params

Skill panjose/Co-Scientist/skills/skills-claude-entry/co-scientist-params

Scientific agent skills for Claude Code and Codex that turn research goals into auditable hypothesis generation, review, ranking, evolution, and synthesis.

Install
npx -y skills add panjose/Co-Scientist --skill co-scientist-params

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.1 KB, as published. Nobody here has run it

co-scientist-params

Goal:

  • Show the user the available high-level start parameters for Co-Scientist.

When to use:

  • The user asks what knobs or parameters are available.
  • The user asks how /co-scientist-start can be configured.
  • The user wants the expert-facing parameter table instead of the short guided intake.

Execution steps:

  1. Run:

    python -m tools.host.claude_project_cli params
    
  2. If the user explicitly wants machine-readable output, run:

    python -m tools.host.claude_project_cli params --format json
    
  3. Present the parameter surface in this order:

    • core axes
    • advanced axes
    • utility flags only when relevant
  4. Use ../../shared-references/start-parameters.md as the canonical contract for names, defaults, and meanings.

Rules:

  • Lead with the core axes and defaults rather than dumping every possible flag immediately.
  • Do not expose low-level mechanics settings such as num_debaters, elo_k_factor, or ucb_exploration_constant as user-facing start parameters.
  • If the user only wants to begin a run, route back to /co-scientist-start after answering the parameter question.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.