amirkiarafiei/open-scholar-peer
Instructions file CodexOpenCode
Instructions for amirkiarafiei/open-scholar-peer, covering agents.md — open scholarpeer, what this project is, commands you will actually run, syntax-check shell scripts and ast-check python files (no formal linter configured).
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Answer Generator Agent — invoked as a subagent by the Query Agent (or as a self-reflection turn on Antigravity). Receives a single probing question plus a minimal context bundle, performs verification against retrieved literature and domain narrative, and returns (answer, citations, discrepancy flag).…
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Baseline Scout Agent — adversarial auditor that identifies missing baselines and datasets the authors failed to compare against. Activate this persona when the user invokes /4-osp-baseline-scout. Operates with an intentionally skeptical posture — its job is to find omissions, not validate what's there.
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Sub-Domain Historian Agent — compresses the retrieved literature into a chronological domain narrative. Activate this persona when the user invokes /3-osp-historian. Mimics the mental model of a senior researcher mapping the arc of progress in a sub-field.
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Literature Review & Expansion Agent — performs External Context retrieval via the dynamic-web search strategy. Activate this persona when the user invokes /2-osp-literature. Runs three distinct rounds (sub-domain anchor, method anchor, temporal expansion) to construct the live reference frame Cdynamic.
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer top-level orchestrator. Activate this skill whenever the user invokes /open-scholar-peer, asks to review a paper, evaluate a manuscript, or references any /N-osp- command. Owns the brain protocol: read .brain/session.json first, advise the user on the correct next step, and ensure phase ordering.…
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Query Agent — formulates probing questions targeting specific weaknesses of the paper. Activate this persona when the user invokes /5-osp-qa. Runs in the main thread; delegates each question to the Answer Generator Agent (subagent) on tools that support it, or self-reflects with strict turn markers on…
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Reviewer Agent — synthesizes the structured summary, domain narrative, missing baselines, and verified Q&A pairs into a single consolidated review formatted to the venue's guidelines. Activate this persona when the user invokes /6-osp-review. Decoupled from investigation: this agent does no new…
amirkiarafiei/open-scholar-peer
Skill Claude CodeCodex
Open ScholarPeer Summary Agent — performs Internal Compression on the input paper. Activate this persona when the user invokes /1-osp-summary or asks to extract claims, method, or evidence from a paper. This is NOT a generic summarizer; it produces a review-oriented structured representation.
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 0: Venue lookup, paper detection, criteria scaffolding.
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 1: Internal Compression — extract claims, method, evidence.
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 2: External retrieval — one round per invocation (sub-domain, method, temporal).
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 3: Compress retrieved literature into a chronological domain narrative.
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 4: Identify missing baselines and datasets the authors failed to compare against.
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 5: Multi-Aspect Q&A — configurable pairs per criterion (default 2).
amirkiarafiei/open-scholar-peer
Command Claude Code
OSP Phase 6: Synthesize verified findings into a single venue-formatted review.
amirkiarafiei/open-scholar-peer
Command Claude Code
Open ScholarPeer dispatcher — show review status and route to the next command.
amirkiarafiei/open-scholar-peer
Cursor rule Cursor
These rules apply automatically in any project where Open ScholarPeer is installed.
amirkiarafiei/subagent-cli-skills
Skill Claude CodeCodex
Delegates large multi-step work to Antigravity CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for heavy edits, exploration, web search, and read-only plan-mode…
amirkiarafiei/subagent-cli-skills
Skill Claude CodeCodex
Delegates large multi-step work to Claude Code CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for heavy edits, exploration, and agentic coding. Skip for trivial…
amirkiarafiei/subagent-cli-skills
Skill Claude CodeCodex
Delegates large multi-step work to OpenAI Codex CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for heavy edits, exploration, and reasoning-intensive tasks. Skip for…
amirkiarafiei/subagent-cli-skills
Skill Claude CodeCodex
Delegates large multi-step work to GitHub Copilot CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for heavy edits, exploration, codebase research, @explore…
amirkiarafiei/subagent-cli-skills
Skill Claude CodeCodex
Delegates large multi-step work to Cursor CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for heavy edits, exploration, and agentic coding. Skip for trivial one-shot…
amirkiarafiei/subagent-cli-skills
Skill Claude CodeCodex
Delegates large multi-step work to Gemini CLI like a subagent—include full goal, prior decisions, scope, and constraints in prompts so isolated sessions stay aligned with the main thread (context handoff per Cognition-style delegation). Use for heavy edits, exploration, web search, @codebaseinvestigator, @generalist…