lqf0624
- 42 skills
- 0 followers
- 4 hours ago last updated
- ▌ Researchstack 2 · lqf0624 bundleWorkflow-first research skill pack for computer systems, networking, and AI papers. Use when Codex needs to scope a paper or multi-paper program, design methods within a fixed topic, test novelty, map literature, plan and audit experiments, write and visualize results, simulate review, or prepare a submission and rebuttal for systems and AI venues.
- ▌ Researchstack Learn 2 · lqf0624 bundleResearch 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.
- ▌ Researchstack Next Step 2 · lqf0624 bundleNext-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.
- ▌ Researchstack Lab Intake 2 · lqf0624 bundleIntake 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.
- ▌ Researchstack Code Review 2 · lqf0624 bundleResearch-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.
- ▌ Researchstack Idea Finder 2 · lqf0624 bundleProblem-discovery skill for systems, networking, and AI research. Use when the user has a broad area and is willing to choose among paper-sized problems. Do not use it to force a topic change when the user has fixed the topic and needs a new method; use method-synthesis instead.
- ▌ Researchstack Idea Refine 2 · lqf0624 bundleGuided repair skill for research ideas that are important but not yet submission-ready. Use to strengthen a thesis, method, mechanism, predictions, evidence path, and scope while preserving a user-chosen topic whenever possible.
- ▌ Researchstack Idea Review 2 · lqf0624 bundleSkeptical but generative review for systems, networking, and AI ideas. Use to judge topic significance, method novelty, mechanism plausibility, evidence burden, scope, and venue fit without treating a crowded topic as automatic rejection.
- ▌ Researchstack Paper Write 2 · lqf0624 bundlePaper-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.
- ▌ Researchstack Peer Review 2 · lqf0624 bundleStrict 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.
- ▌ Researchstack Program Map 2 · lqf0624 bundleResearch-program planning skill for computer systems, networking, and AI. Use when a durable topic or grant direction should support several non-duplicative papers, with explicit shared infrastructure, distinct theses, dependencies, evidence paths, and stop conditions rather than repeated topic switching or salami slicing.
- ▌ Researchstack Paper Layout 2 · lqf0624 bundleLaTeX 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.
- ▌ Researchstack Figure Studio 2 · lqf0624 bundleFigure 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.
- ▌ Researchstack Artifact Audit 2 · lqf0624 bundleReproducibility 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.
- ▌ Researchstack Experiment Ops 2 · lqf0624 bundleExperimental-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.
- ▌ Researchstack Literature Map 2 · lqf0624 bundleRelated-work and mechanism-positioning skill for systems, networking, and AI papers. Use to map competing methods, assumptions, signals, decisions, claims, and evidence; identify established solutions; and define topic and method innovation boundaries with traceable source coverage.
- ▌ Researchstack Rebuttal Coach 2 · lqf0624 bundleRebuttal 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.
- ▌ Researchstack Submission Gate 2 · lqf0624 bundleFinal 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.
- ▌ Researchstack Method Synthesis 2 · lqf0624 bundleMethod-design skill for computer systems, networking, and AI research. Use when the topic is fixed or prior work already studies a similar problem, but the user needs genuinely different mechanisms, algorithms, interfaces, or system designs rather than another topic suggestion or superficial novelty claim.
- ▌ Researchstack Experiment Design 2 · lqf0624 bundleExperiment-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.
- ▌ Researchstack Paper Reproduction 2 · lqf0624 bundlePaper 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.
- ▌ Researchstack · lqf0624 bundleWorkflow-first research skill pack for computer systems, networking, and AI papers. Use when Codex needs to scope a paper or multi-paper program, design methods within a fixed topic, test novelty, map literature, plan and audit experiments, write and visualize results, simulate review, or prepare a submission and rebuttal for systems and AI venues.
- ▌ Researchstack Learn · lqf0624 bundleResearch 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.
- ▌ Researchstack Next Step · lqf0624 bundleNext-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.
- ▌ Researchstack Lab Intake · lqf0624 bundleIntake 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.
- ▌ Researchstack Code Review · lqf0624 bundleResearch-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.
- ▌ Researchstack Idea Finder · lqf0624 bundleProblem-discovery skill for systems, networking, and AI research. Use when the user has a broad area and is willing to choose among paper-sized problems. Do not use it to force a topic change when the user has fixed the topic and needs a new method; use method-synthesis instead.
- ▌ Researchstack Idea Refine · lqf0624 bundleGuided repair skill for research ideas that are important but not yet submission-ready. Use to strengthen a thesis, method, mechanism, predictions, evidence path, and scope while preserving a user-chosen topic whenever possible.
- ▌ Researchstack Idea Review · lqf0624 bundleSkeptical but generative review for systems, networking, and AI ideas. Use to judge topic significance, method novelty, mechanism plausibility, evidence burden, scope, and venue fit without treating a crowded topic as automatic rejection.
- ▌ Researchstack Paper Write · lqf0624 bundlePaper-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.
- ▌ Researchstack Peer Review · lqf0624 bundleStrict 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.
- ▌ Researchstack Program Map · lqf0624 bundleResearch-program planning skill for computer systems, networking, and AI. Use when a durable topic or grant direction should support several non-duplicative papers, with explicit shared infrastructure, distinct theses, dependencies, evidence paths, and stop conditions rather than repeated topic switching or salami slicing.
- ▌ Researchstack Paper Layout · lqf0624 bundleLaTeX 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.
- ▌ Researchstack Figure Studio · lqf0624 bundleFigure 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.
- ▌ Researchstack Artifact Audit · lqf0624 bundleReproducibility 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.
- ▌ Researchstack Experiment Ops · lqf0624 bundleExperimental-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.
- ▌ Researchstack Literature Map · lqf0624 bundleRelated-work and mechanism-positioning skill for systems, networking, and AI papers. Use to map competing methods, assumptions, signals, decisions, claims, and evidence; identify established solutions; and define topic and method innovation boundaries with traceable source coverage.
- ▌ Researchstack Rebuttal Coach · lqf0624 bundleRebuttal 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.
- ▌ Researchstack Submission Gate · lqf0624 bundleFinal 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.
- ▌ Researchstack Method Synthesis · lqf0624 bundleMethod-design skill for computer systems, networking, and AI research. Use when the topic is fixed or prior work already studies a similar problem, but the user needs genuinely different mechanisms, algorithms, interfaces, or system designs rather than another topic suggestion or superficial novelty claim.
- ▌ Researchstack Experiment Design · lqf0624 bundleExperiment-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.
- ▌ Researchstack Paper Reproduction · lqf0624 bundlePaper 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.