Claude Skills by brycewang-stanford

Use when packaging a PLDI artifact for the post-acceptance evaluation — earning the Functional, Reusable, and Available badges, archiving a DOI-stamped snapshot on Zenodo, containerizing toolchains and benchmark suites, and writing a README an evaluator can follow in a fresh VM.

Use when drafting a PLDI author response inside the short February window — triaging reviewer objections about soundness, baselines, and benchmark validity, correcting factual errors with pointers into the submitted PDF, and committing to feasible revisions without promising new systems work.

Use when turning an accepted PLDI paper into its PACMPL Issue PLDI article — de-anonymization, acmsmall journal formatting, ACM rights and open-access handling, delivering every author-response commitment, and coordinating the Zenodo artifact and June conference presentation.

Use when designing or auditing a PLDI evaluation — choosing defensible benchmark suites and baseline compiler configurations, measuring runtime, compile time, and memory with warmup and variance discipline, running ablations that isolate the claimed mechanism, and scoping claims to the platforms measured.

Use when positioning a PLDI paper against the SIGPLAN family and systems neighbors — stating technical deltas per cited line, covering the last few PLDI/POPL/OOPSLA/ICFP cycles, citing PACMPL-era papers in journal form, and verifying every venue attribution on dblp before it ships.

Use when hardening a PLDI paper's measurements against the SIGPLAN Empirical Evaluation Guidelines — warmup and steady-state discipline, variance and confidence reporting, principled benchmark choice, pinned toolchains, cross-platform validity, and a measurement log that survives artifact evaluation.

Use when interpreting PLDI's review pipeline — double-blind HotCRP reviewing by a PL-implementor PC, the February author-response window, March notification, up-to-10% Distinguished Paper selection, and how post-acceptance artifact evaluation and PACMPL publication follow the decision.

Use when auditing a PLDI submission for HotCRP readiness — the single annual November deadline, the 20-pages-of-text-excluding-bibliography cap in single-column acmsmall format, double-blind hygiene across tool names and repositories, dual-submission rules, and summary-rejection triggers before the cutoff.

Use when deciding what accompanies a PLDI submission beyond the 20 text pages — full proofs, extended benchmark data, anonymized code — and how to keep every extra byte double-blind, optional for reviewers, and consistent with the main PDF under summary-rejection formatting rules.

Use when deciding whether a project is PLDI-shaped — implementation insight with benchmark-grade evidence — or better routed inside the PACMPL family to POPL, OOPSLA, or ICFP, or outward to ASPLOS, CGO, CAV, ICSE/FSE, or a systems venue, based on where the claim's evidence actually lives.

Use when planning a PLDI campaign across its annual clock — backward-planning from the November deadline through winter reviewing, the February response window, March notification, post-acceptance artifact evaluation, PACMPL production, and the June conference, with owners for each deliverable.

Use when revising a PLDI draft for the venue's voice — design insight before tool name, mechanisms instead of adjectives, a running example that carries the semantics, honest limitation statements, and prose that fits the single-column acmsmall journal format without padding toward the page cap.

Use to write the PNAS Nexus abstract — a single self-contained paragraph of up to 250 words, with no headings, quantified and accessible to a broad scientific audience. Distinguishes the abstract (what/how/found, for scientists) from the 50–120-word Significance Statement (why-it-matters, for everyone). Late-stage polish.

Use to get PNAS Nexus references right — note that PNAS Nexus accepts references in any readable style at submission (unlike flagship PNAS's strict numbered-by-appearance), so the job is internal consistency, completeness, resolvable in-text citations, and the [dataset] tag for data/software. Prepare a single consistent (preferably numbered) style for production; confirm the final style on acceptance.

Use to build PNAS Nexus's Data and Code Availability — mandatory public-repository deposition of all materials, data, code, and protocols upon publication, retention of raw unprocessed images, accession numbers/DOIs, the [dataset] citation tag, and a compliant availability statement. "Available on request" alone is not sufficient, and failure can be grounds for rejection or retraction.

Use to finalize PNAS Nexus display items — count figures and tables against the graphical-element budget, size to journal column widths, set legible fonts, show-the-data with n and defined error bars, scale bars, colorblind-safe palettes, legend structure, and image integrity (raw, unprocessed images must be retained). Enforces figure rigor before submission.

Use before any writing — as the first gate — to stress-test whether a result fits PNAS Nexus — high-quality, broadly significant, multidisciplinary research across biological/health/medical, physical sciences & engineering, and social & political sciences — and to make the realistic call between PNAS Nexus, flagship PNAS, and a field journal, including the PNAS-to-PNAS-Nexus transfer route.

Use to settle PNAS Nexus's open-access decisions — confirm the gold-OA model and the article processing charge (APC), check eligibility for waivers/discounts (low-/middle-income countries, Read & Publish, membership) and funder compliance, and choose the license (CC BY vs CC BY-NC). This is PNAS Nexus's signature pre-submission decision; it replaces flagship PNAS's Direct/Contributed track choice (PNAS Nexus has no such track).

Use after PNAS Nexus reviews arrive to triage the decision, prioritize experiments, and draft a point-by-point response that is respectful, evidence-led, and honest about limits. Covers the case where reviews were carried over from a PNAS transfer. Do not run before the main text is actually revised.

Use to write the PNAS Nexus Significance Statement — between 50 and 120 words, in plain language for a broad scientific audience, explaining why the work matters. Required for Research Reports and Stage 2 Registered Reports. Distinct from the abstract. One of the highest-value PNAS Nexus front-matter artifacts.

Use to enforce PNAS Nexus's statistics and reproducibility reporting — n and replication, test choice and assumptions, effect sizes with uncertainty, multiple-comparison control, randomization/blinding, sample-size justification, and reproducible code. Also covers whether a Registered Report (Stage 1/2) is the right route for confirmatory work.

Use as the final preflight before submitting to PNAS Nexus — a complete checklist across fit, open access/APC/license, article type & length, Significance Statement, abstract, classification, figures, statistics, data/code, references, and required files. Covers the PNAS-transfer case and bundles a checklist and cover-letter template. Emits GO/NO-GO.

Use when deciding which pnasnexus-* sub-skill to invoke next, or when sequencing a manuscript from scope/significance test through reviewer rebuttal for PNAS Nexus (the fully open-access sibling journal of PNAS, published by Oxford University Press for the U.S. National Academy of Sciences). Routes — it does not replace — the specialized skills.

Use to choose the PNAS Nexus article type, structure the main text, and hold the page-based length budget — Research Report / Brief Report / Perspective / Review / Registered Report — keep Materials and Methods in the main text, and select the required research-area classification at submission.

Use when an author expects an artifact-evaluation or badge track at ACM PODC and needs redirecting — PODC has NO artifact track and no ACM badges. This skill converts artifact-culture instincts into what PODC actually evaluates: proof-appendix completeness, model/assumption rigor, and the honest, optional role of any simulation.

Use when writing an ACM PODC rebuttal/author response, if the cycle runs one — covering how to correct a proof misreading, supply a missing lemma or bound within the anonymity envelope, prioritize soundness questions over taste, and behave correctly given that PODC has no revision round to fall back on.

Use when preparing an accepted ACM PODC paper for the proceedings — de-anonymizing after lightweight double-blind, compressing to the 10-page two-column ACM proceedings format without losing the proof map, completing ACM rights/eRights metadata and CCS concepts, and posting the synchronized full version with all proofs to arXiv.

Use when building the evidence for an ACM PODC paper — where "evidence" is a proof, not a benchmark. Covers matching upper and lower bounds, tightness arguments, model and assumption stress-tests, adversary-strength calibration, and the honest, clearly-optional role of any simulation in a distributed-computing-theory paper.

Use when writing the related-work and positioning of an ACM PODC paper — covering the distributed-computing literature lanes (PODC/DISC/SPAA and the JACM / Distributed Computing journals), writing a model-and-bound-precise delta over prior results, distinguishing your model from neighboring ones, and keeping self-citation safe under lightweight double-blind review.

Use when making an ACM PODC paper's result independently checkable — reproducibility for a proofs venue, not an artifact venue. Covers a self-contained proof appendix, an explicit and checkable model/assumption box, honest handling of any optional simulation, and keeping the full version (with proofs) in sync with the 10-page camera-ready.

Use when reasoning about how an ACM PODC submission is evaluated — covering lightweight double-blind review, a program committee that reads proofs, the accept/reject decision with no journal-style revision round, the Brief Announcements track's lighter bar, and how PODC's process differs from DISC, SPAA, and the sequential-theory venues STOC/FOCS/SODA.

Use when auditing an ACM PODC submission for HotCRP readiness, covering the two-step abstract-registration then full-paper deadline, the ACM Master template with the 10-page-merits budget and unbounded full version, lightweight double-blind anonymization, the regular-paper-vs-Brief-Announcement choice, and desk-risk triage before the AoE cutoff.

Use when deciding what goes in the first 10 read-guaranteed pages of an ACM PODC submission versus the full version / appendix, and when choosing between a regular paper and a Brief Announcement — so that nothing which decides acceptance lives past page 10 and every deferred proof remains reachable.

Use when deciding whether a distributed-computing result belongs at ACM PODC or should be routed to DISC, SPAA, OPODIS/SIROCCO/SSS, STOC/FOCS/SODA, a systems venue (ICDCS/DSN/OSDI/NSDI), a blockchain-theory venue (AFT/FC), or a journal (JACM / Distributed Computing) — and how to avoid the PODC-vs-PODS naming trap by reasoning about the distributed model and the cost measure.

Use when planning an ACM PODC campaign end to end — running the single annual cycle backward from the February deadline through abstract registration, lightweight double-blind review, the late-April notification, the May camera-ready, and the arXiv full version — and coordinating the regular-paper-vs-Brief-Announcement decision along the way.

Use when drafting or revising the body of an ACM PODC paper — building the distributed-theory skeleton (an explicit model box, the result stated as a theorem up front, a proof architecture the reader can navigate, and the 10-page-merits discipline) so the merits case lands within the first 10 pages a PODC committee is guaranteed to read.

Use for the PODS analogue of artifact evaluation — there is no systems artifact track at this theory symposium, so this skill covers formal-claims verification instead: a complete at-submission proof appendix, a claim-to-proof mapping reviewers can check, the full-version-on-arXiv norm, and, only when a paper claims practicality, an honest optional code artifact.

Use when drafting ACM PODS author responses, covering the short ~48-hour double-anonymous rebuttal that corrects misreadings of proofs and definitions, and — distinctively — the shepherded revision cover letter that maps every required item to a concrete change in the resubmitted paper and survives the shepherd's second read.

Use when preparing an accepted ACM PODS paper for its PACMMOD-track camera-ready, covering de-anonymization, the final acmsmall format and PACMMOD journal metadata (DOI, ORCID, CCS concepts), integrating shepherd-required revision items without overclaiming, posting and DOI-linking the arXiv full version, and confirming registration and presentation.

Use when designing or auditing the analytical "evidence" of an ACM PODS paper — worst-case and average-case analyses, matching upper and lower bounds, dichotomy completeness, correct complexity assumptions, and the occasional empirical validation when a theory paper claims practicality — matching the rigor to the shape of each theoretical claim.

Use when positioning an ACM PODS submission against the database-theory literature across PODS, ICDT, LICS, and the journals (TODS, LMCS, JACM, VLDBJ), writing delta-first contrast that compares results rather than cataloging citations, keeping self-citations double-anonymous, and handling concurrent, arXiv-preprint, and prior-version overlap.

Use when strengthening the verifiability of an ACM PODS paper — a complete claim-to-proof map, self-contained proofs in the at-submission appendix (no external appendices), correctly stated assumptions, honest scope and open cases, the full-version-on-arXiv norm, and consistency between what the paper claims and what the proofs actually establish.

Use when reasoning about how an ACM PODS submission is evaluated, covering lightweight double-anonymous review, the multi-cycle-per-year calendar, the two reviewing rounds within a cycle, the 48-hour rebuttal, the accept/reject/revision decision with a shepherded revision, PACMMOD-track publication, and how PODS differs from SIGMOD's rounds and ICDT's process.

Use when auditing an ACM PODS research submission for EasyChair readiness, covering the chosen cycle's abstract-then-paper deadlines, the acmsmall[review,anonymous] format and 15-page budget, the at-submission proof appendix, lightweight double-anonymity, the declared conflicts of interest, PACMMOD-track publication, and desk-risk triage before the AoE cutoff.

Use when deciding what belongs in an ACM PODS paper body versus its at-submission appendix, covering the acmsmall 15-page budget, the rule that PODS forbids online/external appendices so all proofs ship with the submission, the body/appendix split for a theory paper, and double-anonymous supplementary hygiene.

Use when deciding whether a data-management project belongs at ACM PODS (the database-theory symposium) or should be routed to SIGMOD/VLDB/ICDE (systems), ICDT (its sister theory venue), LICS/ICALP/STOC (pure theory), or a journal (TODS/LMCS/JACM), by contribution shape, the result-swap test, and the PODS-vs-ICDT community fit.

Use when planning an ACM PODS project timeline across its multiple submission cycles per year, from venue fit through the EasyChair abstract-then-paper deadlines, the 48-hour rebuttal, the accept/reject/revision decision and shepherded revision round, PACMMOD-track publication, the arXiv full version, and presentation — with backward-planning offsets for a theory paper and honest handling of cycle choice.

Use when revising an ACM PODS paper for a precise model and result on the first page, exact theorem statements with matching bounds, complete and self-contained proofs (body plus at-submission appendix), honest assumptions and open cases, double-anonymous wording, and disciplined use of the acmsmall 15-page budget.

Use when packaging a POPL artifact — above all a mechanized proof development in Rocq/Coq, Lean, Agda, or Isabelle — for the post-conditional-acceptance evaluation, satisfying the no-admit/no-sorry completeness rule, mapping paper theorems to proof files, pinning toolchains, and earning the Functional, Reusable, and Available badges.

Use when drafting a POPL author response during the optional multi-day window — triaging soundness objections against misread definitions, answering "what does Theorem 3 actually assume" questions with pointers rather than new material, staying concise per the CFP, and protecting the path to conditional acceptance.