f5570b4e5a
- Rename project config dir from .pi/ to .feynman/ (Pi supports this via piConfig.configDir) - Rename citation agent to verifier across all prompts, agents, skills, and docs - Add website with homepage and 24 doc pages (Astro + Tailwind) - Add skills for all workflows (deep-research, lit, review, audit, replicate, compare, draft, autoresearch, watch, jobs, session-log, agentcomputer) - Add Pi-native prompt frontmatter (args, section, topLevelCli) and read at runtime - Remove sync-docs generation layer — docs are standalone - Remove metadata/prompts.mjs and metadata/packages.mjs — not needed at runtime - Rewrite README and homepage copy - Add environment selection to /replicate before executing - Add prompts/delegate.md and AGENTS.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1.2 KiB
1.2 KiB
description, args, section, topLevelCli
| description | args | section | topLevelCli |
|---|---|---|---|
| Plan or execute a replication workflow for a paper, claim, or benchmark. | <paper> | Research Workflows | true |
Design a replication plan for: $@
Workflow
- Extract — Use the
researchersubagent to pull implementation details from the target paper and any linked code. - Plan — Determine what code, datasets, metrics, and environment are needed. Be explicit about what is verified, what is inferred, and what is still missing.
- Environment — Before running anything, ask the user where to execute:
- Local — run in the current working directory
- Virtual environment — create an isolated venv/conda env first
- Cloud — delegate to a remote Agent Computer machine via
/delegate - Plan only — produce the replication plan without executing
- Execute — If the user chose an execution environment, implement and run the replication steps there. Save notes, scripts, and results to disk in a reproducible layout.
- Report — End with a
Sourcessection containing paper and repository URLs.
Do not install packages, run training, or execute experiments without confirming the execution environment first.