Mexregkan

Mexregkan/claude-for-researchers

Agent Claude Code

Audits a project code THROUGH its Pipeline/ doc — reads a pipeline .md and its code together, then hunts for genuine bugs (correctness, sign/normalization, convention violations) and concrete optimizations (redundant recomputation, missing memoization, complexity blow-ups). Use to review a documented code for…

Mexregkan/claude-for-researchers

Hook Claude Code

One of 3 in settings.json

Runs before the context is compacted, executing pre-compact.sh via bash. From Mexregkan/claude-for-researchers.

Mexregkan/claude-for-researchers

Hook Claude Code

One of 3 in settings.json

Runs when the agent finishes a response, executing promise-checker.sh and reap-wolfram.sh via bash (2 commands). From Mexregkan/claude-for-researchers.

Mexregkan/claude-for-researchers

Settings file Claude Code

One of 3 in settings.json

Agent settings declaring 7 hook events (comment, PreCompact, commentposttooluse, commentposttoolusewolfram) and 2 allowed tools.

Mexregkan/claude-for-researchers

Skill Claude Code

The write-side inverse of /check-pipeline and the pipeline-auditor — read a Pipeline/ doc (and/or an audit report) and EDIT the code accordingly: apply an optimization the pipeline describes, correct code the pipeline (backed by your authoritative notes) shows is wrong, or bring the code in line with the documented…

Mexregkan/claude-for-researchers

Skill Claude Code needs its repo

Check that a code and its Pipeline/ .md are still compatible — that every symbol, cell number, data file, and data-flow claim in the pipeline doc still matches the current code (drift detection). Use after editing a documented notebook/engine/script, before trusting a pipeline doc, or on request ("does the pipeline…

Mexregkan/claude-for-researchers

Skill Claude Code

Format a result, derivation, or numerical value for independent verification by a second model. Use when you want a cross-check on an important or contested result.

Mexregkan/claude-for-researchers

Skill Claude Code

Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…

Mexregkan/claude-for-researchers

Skill Claude Code

Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.

Mexregkan/claude-for-researchers

Skill Claude Code

Sync a local git clone of a shared Overleaf project: pull collaborators' latest, check whether Overleaf has moved ahead, or (only on explicit request) publish your local edits back — without ever erasing collaborators' work.

Mexregkan/claude-for-researchers

Skill Claude Code

Re-derive a contested or pushed-back claim in isolation from the definitions, to catch sycophantic capitulation. Use when a result is disputed or you suspect you changed an answer only because the user pushed back.

Mexregkan/claude-for-researchers

Skill Claude Code

Propagate load-bearing changes from workbook.tex to brief.tex.

Mexregkan/claude-for-researchers

Skill Claude Code

Propagate a change made in a Wolfbook .wb notebook into the paired .nb notebook so the two stay identical. Use immediately after every .wb edit.

Mexregkan/claude-for-researchers

Skill Claude Code

Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation.

Mexregkan/claude-for-researchers

Skill Claude Code

Playbook for the Wolfbook MCP tools — driving the LIVE Wolfram kernel and a .wb/.nb notebook in VS Code from Claude Code (read/search/edit/run cells, evaluate expressions, checkpoint/restore kernel state, step-debug, look up symbols, find paclets, search INSPIRE/arXiv papers). Use whenever working through the Wolfbook…

Mexregkan/claude-for-researchers

Skill Claude Code

Run heavy Wolfram Language (wolframscript) computations from Claude Code reliably, and diagnose the misleading "The product exited because of a license error". Use whenever invoking wolframscript on a non-trivial computation, when a wolframscript job dies with a "license error" despite a valid license, or when Wolfram…

Mexregkan/claude-for-researchers

Skill Claude Code

Write (or refresh) a Pipeline/ .md that documents the calculation-and-code pipeline of ANY large code in the project — a notebook (.wb/.nb/.ipynb), an engine, or a script. Use when a load-bearing code has no pipeline doc yet, when a new main code is added, or when the user asks to "write the pipeline" for a file.…

Mexregkan/claude-for-researchers

Agent Claude Code

Adversarially audits a result against the artifacts that produced it — a script, a log, a data file — and reports the WEAKEST statement those artifacts support. Spawn it with the artifacts and the drafted claim and NOTHING ELSE: no session history, no reasoning, no hoped-for conclusion. Use before a result leaves the…

Mexregkan/claude-for-researchers

Agent Claude Code

Read-only fresh-context adversary for ONE claim of a project document. Given only the bare claim, its location and the evidence paths — never the caller's verdict — it reads the passage, the cited script / log / output and the sibling records, and returns the weakest statement the evidence supports, ranked breaks…

Mexregkan/claude-for-researchers

Agent Claude Code

Read-only first pass over ONE section or line range of a project document (workbook section, strategy map, big picture, handoff, paper, primer) that extracts every checkable claim into ledger rows — id, location, falsifiable statement, type as written, load class, proposed check — and deliberately produces NO…

Mexregkan/claude-for-researchers

Agent Claude Code

Commits and pushes for this project. Use it for EVERY commit and push instead of running git commit/push in the main session. Give it an explicit file list, the target repo, and the commit message. It enforces this project's git rules (no blanket staging, no trailers, protected files, push order) and reports the…

Mexregkan/claude-for-researchers

Agent Claude Code

Decides whether the last round of work actually advanced the project, and specifies the single next task if it did not. Detects loops — the same residual renamed, a weaker check repeated, an escalation after a failed simple case. Spawn it with the last round's result, the audit of that result, and enough recent…

Mexregkan/claude-for-researchers

Skill Claude Code

Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…

Mexregkan/claude-for-researchers

Skill Claude Code

Evaluate one project document in detail — a workbook section, big picture, strategy map, handoff message, paper, brief, or primer — without editing it. Runs the mechanical lint, builds a claim ledger, types every headline against the eight claim statuses in CLAUDE.md, traces cited evidence to the scripts and logs that…