Initial Feynman research agent scaffold
This commit is contained in:
13
prompts/lit-review.md
Normal file
13
prompts/lit-review.md
Normal file
@@ -0,0 +1,13 @@
|
||||
---
|
||||
description: Run a literature review on a topic using paper search and primary-source synthesis.
|
||||
---
|
||||
Investigate the following topic as a literature review: $@
|
||||
|
||||
Requirements:
|
||||
- Use `alpha_search` first.
|
||||
- Use `alpha_get_paper` on the most relevant papers before making strong claims.
|
||||
- Use `alpha_ask_paper` for targeted follow-up questions when the report is not enough.
|
||||
- Prefer primary sources and note when something appears to be a preprint or secondary summary.
|
||||
- Separate consensus, disagreements, and open questions.
|
||||
- When useful, propose concrete next experiments or follow-up reading.
|
||||
- If the user wants an artifact, write the review to disk as markdown.
|
||||
12
prompts/paper-code-audit.md
Normal file
12
prompts/paper-code-audit.md
Normal file
@@ -0,0 +1,12 @@
|
||||
---
|
||||
description: Compare a paper's claims against its public codebase and identify mismatches, omissions, and reproducibility risks.
|
||||
---
|
||||
Audit the paper and codebase for: $@
|
||||
|
||||
Requirements:
|
||||
- Identify the canonical paper first with `alpha_search` and `alpha_get_paper`.
|
||||
- Extract implementation-sensitive claims with `alpha_ask_paper`.
|
||||
- If a public repo exists, inspect it with `alpha_read_code`.
|
||||
- Compare claimed methods, defaults, metrics, and data handling against the repository.
|
||||
- Call out missing code, mismatches, ambiguous defaults, and reproduction risks.
|
||||
- Save the audit to `outputs/` as markdown.
|
||||
19
prompts/paper-draft.md
Normal file
19
prompts/paper-draft.md
Normal file
@@ -0,0 +1,19 @@
|
||||
---
|
||||
description: Turn research findings into a polished paper-style draft with equations, sections, and explicit claims.
|
||||
---
|
||||
Write a paper-style draft for: $@
|
||||
|
||||
Requirements:
|
||||
- Ground every claim in inspected sources, experiments, or explicit inference.
|
||||
- Use clean Markdown structure with LaTeX where equations materially help.
|
||||
- Include at minimum:
|
||||
- title
|
||||
- abstract
|
||||
- problem statement
|
||||
- related work
|
||||
- method or synthesis
|
||||
- evidence or experiments
|
||||
- limitations
|
||||
- conclusion
|
||||
- If citations are available, include citation placeholders or references clearly enough to convert later.
|
||||
- Save the draft to `papers/` as markdown.
|
||||
12
prompts/reading-list.md
Normal file
12
prompts/reading-list.md
Normal file
@@ -0,0 +1,12 @@
|
||||
---
|
||||
description: Build a prioritized reading list on a research topic with rationale for each paper.
|
||||
---
|
||||
Create a research reading list for: $@
|
||||
|
||||
Requirements:
|
||||
- Use `alpha_search` with `all` mode.
|
||||
- Inspect the strongest papers with `alpha_get_paper`.
|
||||
- Use `alpha_ask_paper` when a paper's fit is unclear.
|
||||
- Group papers by role when useful: foundational, strongest recent work, methods, benchmarks, critiques, replication targets.
|
||||
- For each paper, explain why it is on the list.
|
||||
- Save the final reading list to `outputs/` as markdown.
|
||||
14
prompts/replicate.md
Normal file
14
prompts/replicate.md
Normal file
@@ -0,0 +1,14 @@
|
||||
---
|
||||
description: Plan or execute a replication workflow for a paper, claim, or benchmark.
|
||||
---
|
||||
Design a replication plan for: $@
|
||||
|
||||
Requirements:
|
||||
- Identify the canonical paper or source material first.
|
||||
- Use `alpha_get_paper` for the target paper.
|
||||
- Use `alpha_ask_paper` to extract the exact implementation or evaluation details you still need.
|
||||
- If the paper links code, inspect it with `alpha_read_code`.
|
||||
- Determine what code, datasets, metrics, and environment are needed.
|
||||
- If enough information is available locally, implement and run the replication steps.
|
||||
- Save notes, scripts, and results to disk in a reproducible layout.
|
||||
- Be explicit about what is verified, what is inferred, and what is still missing.
|
||||
Reference in New Issue
Block a user