researchstack

Workflow-first research skill pack for computer systems, networking, and AI papers. Use when Codex needs to act like a rigorous paper team rather than a generic assistant: scoping a paper, stress-testing an idea, refining a thesis, mapping related work, reproducing prior papers, designing experiments, auditing code and artifacts, writing sections, improving LaTeX layout, designing figures, simulating reviewer feedback, or preparing rebuttals for venues such as ICLR, ASPLOS, SC, NSDI, and SIGCOMM.

Reproducibility and evidence-audit skill for research projects. Use when Codex should trace figures and claims back to scripts, configs, datasets, seeds, hardware assumptions, and logs; find missing provenance; or prepare the code and experiment pipeline for submission, open-sourcing, or artifact evaluation.

Research-code review skill for systems, networking, and AI projects. Use when Codex should review experiment code, simulators, training pipelines, benchmarks, data processing, or plotting logic with emphasis on correctness, reproducibility, and whether the implementation really supports the paper's claims.

Experiment-planning skill for research papers in systems, networking, and AI. Use when Codex must design or audit baselines, metrics, workloads, ablations, statistical checks, scaling studies, sensitivity analysis, and failure tests so that a paper's claims are actually supported.

Experimental-process management skill for research projects. Use when Codex should structure runbooks, logging, checkpointing, seed control, result triage, failure analysis, experiment queues, and evidence collection so that the day-to-day experimental workflow stays publication-grade instead of devolving into ad hoc trial-and-error.

Figure and table design skill for research papers. Use when Codex should decide what to visualize, sketch figure plans, critique existing charts, improve captions, structure result tables, or make visual evidence easier for strict reviewers to understand in AI, systems, or networking papers.

Topic-finding skill for research projects in computer systems, networking, and AI. Use when the user has a broad research area, venue target, resource constraint, or personal interest but does not yet have a one-paper thesis. This skill must scan recent papers, generate candidate topics, run each candidate through researchstack-idea-review, and only surface the surviving paper-sized ideas.

Guided idea-refinement skill for research projects that are interesting but not yet submission-ready. Use when Codex should improve a paper idea through structured questioning, narrowing, hypothesis building, contribution shaping, and experimental reframing instead of only approving or rejecting it.

Skeptical review skill for research ideas. Use when Codex should act like a sharp program committee member or senior coauthor and judge whether an idea is novel, important, scoped correctly, and likely to survive strict review at venues such as ICLR, ASPLOS, SC, NSDI, or SIGCOMM.

Intake skill for new research directions in computer systems, networking, and AI. Use when the user has a rough idea, partial implementation, benchmark intuition, or venue target and needs to turn it into a clear paper plan with thesis, hypotheses, workstreams, and next decisions.

Research memory skill for long-lived projects and researcher preferences. Use when Codex should record, inspect, prune, or apply durable knowledge about a paper project, venue strategy, experiment policy, writing weaknesses, reviewer risks, or repeated user preferences so later sessions become more context-aware.

Related-work and positioning skill for CS, networking, and AI papers. Use when Codex needs to map prior work, identify the closest baselines and competing narratives, clarify novelty boundaries, or build a literature matrix that can support idea review, experiment design, or paper writing.

Next-step triage skill for long-running research projects. Use when the user is mid-paper, mid-experiment, mid-writing, or generally stuck and needs a clear recommendation for which researchstack skill to use next, what not to do yet, and why.

LaTeX and presentation-layout skill for research papers. Use when Codex should improve paper structure, section ordering, notation consistency, figure placement, table formatting, captions, appendix organization, or submission compliance while preserving technical precision and readability.

Paper reproduction skill for computer systems, networking, and AI research. Use when the user provides a paper PDF, appendix, or repository and wants Codex to reconstruct the method, extract claims and experiments, identify missing details, plan a faithful reproduction, and judge whether the paper is reproducible, partially reproducible, blocked, or contradicted.

Paper-writing skill for CS, networking, and AI venues. Use when Codex needs to draft or revise titles, abstracts, introductions, method sections, evaluation sections, related work, limitations, or conclusions while keeping claims aligned with evidence and tuned to conference expectations.

Strict conference-style review skill for computer science papers. Use when Codex should simulate expert reviewers for venues such as ICLR, ASPLOS, SC, NSDI, or SIGCOMM, produce a structured review, assign confidence, explain likely acceptance risk, and identify the most damaging objections a real PC member might raise.

Rebuttal and response strategy skill for research submissions. Use when Codex should turn reviewer comments into a disciplined response plan, draft point-by-point rebuttal text, identify which objections need evidence versus wording, and help the user answer tough reviews without overclaiming or sounding defensive.

Workflow-first research skill pack for computer systems, networking, and AI papers. Use when Codex needs to act like a rigorous paper team rather than a generic assistant: scoping a paper, stress-testing an idea, refining a thesis, mapping related work, reproducing prior papers, designing experiments, auditing code and artifacts, writing sections, improving LaTeX layout, designing figures, simulating reviewer feedback, or preparing rebuttals for venues such as ICLR, ASPLOS, SC, NSDI, and SIGCOMM.

Final submission-readiness skill for research papers. Use when Codex should decide whether a paper is ready for submission, identify the top rejection risks, check venue fit, find missing evidence or writing gaps, and recommend whether to submit now, delay, or retarget to another conference.

Experiment-planning skill for research papers in systems, networking, and AI. Use when Codex must design or audit baselines, metrics, workloads, ablations, statistical checks, scaling studies, sensitivity analysis, and failure tests so that a paper's claims are actually supported.

Topic-finding skill for research projects in computer systems, networking, and AI. Use when the user has a broad research area, venue target, resource constraint, or personal interest but does not yet have a one-paper thesis. This skill must scan recent papers, generate candidate topics, run each candidate through researchstack-idea-review, and only surface the surviving paper-sized ideas.

Guided idea-refinement skill for research projects that are interesting but not yet submission-ready. Use when Codex should improve a paper idea through structured questioning, narrowing, hypothesis building, contribution shaping, and experimental reframing instead of only approving or rejecting it.

Skeptical review skill for research ideas. Use when Codex should act like a sharp program committee member or senior coauthor and judge whether an idea is novel, important, scoped correctly, and likely to survive strict review at venues such as ICLR, ASPLOS, SC, NSDI, or SIGCOMM.

Intake skill for new research directions in computer systems, networking, and AI. Use when the user has a rough idea, partial implementation, benchmark intuition, or venue target and needs to turn it into a clear paper plan with thesis, hypotheses, workstreams, and next decisions.

Related-work and positioning skill for CS, networking, and AI papers. Use when Codex needs to map prior work, identify the closest baselines and competing narratives, clarify novelty boundaries, or build a literature matrix that can support idea review, experiment design, or paper writing.

Paper-writing skill for CS, networking, and AI venues. Use when Codex needs to draft or revise titles, abstracts, introductions, method sections, evaluation sections, related work, limitations, or conclusions while keeping claims aligned with evidence and tuned to conference expectations.

Strict conference-style review skill for computer science papers. Use when Codex should simulate expert reviewers for venues such as ICLR, ASPLOS, SC, NSDI, or SIGCOMM, produce a structured review, assign confidence, explain likely acceptance risk, and identify the most damaging objections a real PC member might raise.

Final submission-readiness skill for research papers. Use when Codex should decide whether a paper is ready for submission, identify the top rejection risks, check venue fit, find missing evidence or writing gaps, and recommend whether to submit now, delay, or retarget to another conference.

Next-step triage skill for long-running research projects. Use when the user is mid-paper, mid-experiment, mid-writing, or generally stuck and needs a clear recommendation for which researchstack skill to use next, what not to do yet, and why.

Reproducibility and evidence-audit skill for research projects. Use when Codex should trace figures and claims back to scripts, configs, datasets, seeds, hardware assumptions, and logs; find missing provenance; or prepare the code and experiment pipeline for submission, open-sourcing, or artifact evaluation.

Research-code review skill for systems, networking, and AI projects. Use when Codex should review experiment code, simulators, training pipelines, benchmarks, data processing, or plotting logic with emphasis on correctness, reproducibility, and whether the implementation really supports the paper's claims.

Experimental-process management skill for research projects. Use when Codex should structure runbooks, logging, checkpointing, seed control, result triage, failure analysis, experiment queues, and evidence collection so that the day-to-day experimental workflow stays publication-grade instead of devolving into ad hoc trial-and-error.

Figure and table design skill for research papers. Use when Codex should decide what to visualize, sketch figure plans, critique existing charts, improve captions, structure result tables, or make visual evidence easier for strict reviewers to understand in AI, systems, or networking papers.

Research memory skill for long-lived projects and researcher preferences. Use when Codex should record, inspect, prune, or apply durable knowledge about a paper project, venue strategy, experiment policy, writing weaknesses, reviewer risks, or repeated user preferences so later sessions become more context-aware.

LaTeX and presentation-layout skill for research papers. Use when Codex should improve paper structure, section ordering, notation consistency, figure placement, table formatting, captions, appendix organization, or submission compliance while preserving technical precision and readability.

Paper reproduction skill for computer systems, networking, and AI research. Use when the user provides a paper PDF, appendix, or repository and wants Codex to reconstruct the method, extract claims and experiments, identify missing details, plan a faithful reproduction, and judge whether the paper is reproducible, partially reproducible, blocked, or contradicted.

Rebuttal and response strategy skill for research submissions. Use when Codex should turn reviewer comments into a disciplined response plan, draft point-by-point rebuttal text, identify which objections need evidence versus wording, and help the user answer tough reviews without overclaiming or sounding defensive.