Claude Skills by chgagne

Use when working with a researcher on a long-running research project across many sessions — opening or closing a session, choosing a direction, method or scope, deciding whether to ask or act, planning what to run next, or writing up a result. Also when a published number failed to reproduce, a session ended with no record, a decision got made unilaterally, a write-up did not land, or the work has drifted from the research questions.

Use when comparing a draft against specific prior work head to head — checking whether a baseline was trained at the same scale, whether protocols match, how many seeds each ran, or what a competitor actually reports. Triggers on "compare this paper to X", "how does our method differ from Y", "is the baseline comparison fair", "did they train at the same scale", or a shortlist of papers from a gap sweep.

Use when a proof or derivation needs to be made explicit step by step — expanding a paper's algebra for a reader without formal mathematical training, producing a worked companion document, or establishing whether a derivation can be justified at all. Triggers on "explain this derivation", "walk me through this proof", "expand the algebra", "I can't follow this step", "make this readable for a non-mathematician", or a referee needing to show why a step does not follow.

Use when asked to review, critique, or assess an academic paper from its LaTeX sources — including pre-submission critique of a student's or collaborator's draft, or a referee report for a venue. Also when the only artifact is a blind PDF with no sources. Triggers on "review this paper", "assess the paper", "read my student's draft", "referee report", a directory holding main.tex/refs.bib/*.cls, a submission PDF to review, or a request to check a paper's claims, figures, bibliography or math.

Use when planning, budgeting, submitting or resuming a multi-job experiment campaign on a Slurm/HPC cluster — sizing walltime, shaping jobs and arrays, deciding what to submit first, or after a job hit its walltime, produced no results, silently ran the wrong configuration, or got the wrong number of GPUs.

Use when finding related work a draft may have missed, checking whether a contribution has already been published, or mapping what a research area looks like. Triggers on "what related work did we miss", "has this been done before", "is our contribution novel", "map this field", "survey the literature on X", or a paper draft whose related-work section looks thin.

Use when working on a Digital Research Alliance of Canada (DRAC, Alliance, formerly Compute Canada) HPC cluster such as Narval, Rorqual, Fir, TamIA, Killarney, Vulcan, Nibi or Trillium — including ssh to *.alliancecan.ca failing with "Permission denied (keyboard-interactive)", sinfo/sacctmgr reporting "command not found" over ssh, submitting or monitoring Slurm jobs (sbatch, squeue, sacct, job arrays, GPU allocations), choosing between clusters, staging data into /project or /scratch, or jobs...

Use when checking a .bib or reference list for incorrect or fabricated entries — wrong titles, invented co-authors, wrong DOI/volume/pages, preprints cited instead of the published venue, or references that do not exist. Triggers on "verify this bibliography", "check my references", "are these citations real", a refs.bib alongside a paper, or suspicion that a bibliography was LLM-generated.

Use when checking the mathematics of a paper rather than its claims — verifying a theorem's proof, an algebraic derivation, a bound, or an appendix full of lemmas. Triggers on "check this proof", "verify the derivation", "is Lemma 3 correct", "does the algebra work", a paper directory containing theorem/proof environments, or a referee asking whether a mathematical argument holds.