Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when positioning a CAV (Computer Aided Verification) submission against the verification literature across CAV, TACAS, FMCAD, VMCAI, POPL/PLDI, and the journals (FMSD, JAR, TOCL, STTT), writing delta-first contrast rather than a citation catalog, crediting the right benchmark and tool lineages, keeping self-citations double-anonymous for the anonymized categories, and handling concurrent and prior-version overlap.
Use when reasoning about how a CAV (Computer Aided Verification) submission is evaluated, covering the two-stage reviewing process (two reviews then an early-reject filter, then two more reviews with a rebuttal), the partial double-anonymity by category, the accept/reject outcome, the optional non-conditional artifact evaluation, and how CAV differs from TACAS and FMCAD.
Use when deciding whether a molecular / translational oncology study belongs in Cancer Cell (Cell Press) before investing in full submission. Diagnoses mechanism + translational-relevance fit; it does not design experiments or edit prose.
Use when positioning an ACM CCS submission against the security big-four and specialist literature, including arXiv preprints, prior CCS/S&P/USENIX/NDSS papers, concurrent disclosures, CVE and advisory records, and the attack-and-defense lineage that a SIGSAC program committee expects to see credited.
Use when explaining or planning around ACM CCS peer review, the two-cycle HotCRP workflow, decision categories including minor revision, the rebuttal window, the adversarial reviewer pool, ethics and disclosure scrutiny, meta-review dynamics, and ACM proceedings outcomes.
Use when the identification strategy is the bottleneck for a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript — either a structural model with credible parameters, or a clean quasi-experiment (DID / IV / RDD / event-study). CEQ is the strictest Chinese econ journal here; identification assumptions must be made explicit and each defended. Stress-test the design before drafting exhibits.
Use when scrutinizing statistical inference for a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript — choosing and justifying the clustering level, handling weak instruments with robust inference, correcting for multiple hypothesis testing, and reporting standard errors that survive a technical reviewer. Default robust SEs are rarely enough at CEQ.
Use when positioning a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript's contribution against the literature — benchmarking the precise method/result delta versus specific field papers (English + Chinese), not piling citations. Use after the topic is set and before/alongside identification.
Use when a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript has a credible main effect but the channel/mechanism is asserted rather than evidenced — to design tests that distinguish competing channels and provide falsifiable mechanism evidence. Use after identification is settled.
Use when a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript uses difference-in-differences with staggered adoption or heterogeneous treatment effects — to bring it into compliance with modern estimators (Callaway–Sant'Anna, de Chaisemartin–D'Haultfœuille, Sun–Abraham) instead of bare two-way fixed effects. Bare TWFE on staggered timing is a near-certain reject at CEQ.