groundnuty
UserGitHub template with sane Claude Code defaults for autonomous work. Four profiles: info / research / paper / code.
Categories
Indexed Skills (11)
checkpoint
Write a committed, cross-machine handoff snapshot - active plan, decisions made, file pointers with line numbers, open questions, and the next 1-3 concrete actions - to `.claude/session-reports/`. Use when the user says "checkpoint", "save state", "snapshot before I stop", "where am I", "wrap up for handoff", or before a long break, a model switch, or handing the repo to a collaborator. Auto-memory is machine-local and `/rewind` is in-session undo; the checkpoint is the artifact that travels with the repo.
respond-to-referees
Generate a structured response-to-referees document from a referee report and the revised manuscript. Maps each referee comment to the specific revision, classifies coverage (addressed / partially / deferred / disagreement), and drafts polite but firm responses. Use during the R&R (revise-and-resubmit) stage of paper revision.
seven-pass-review
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review isn't enough.
permission-check
Diagnose why Claude Code is (or isn't) prompting for permission. By default reads only repo-local layers (CLI project, CLI project-local, VSCode workspace). Host-global layers (CLI user `~/.claude/`, VSCode user settings) are read ONLY when the user explicitly confirms — those files may contain unrelated paths or secrets. Use when user says "why is it asking me to approve?", "permission check", "why am I getting prompts?", "bypass isn't working", "check my permissions". Read-only diagnostic.
tikz
Audit and fix residual TikZ visual collisions in a .tex file. A downstream repair tool — not a safety net. Use /tikz when labels overlap arrows, text sits on boxes, or arrows cross each other. Applies mathematical gap calculations and Bézier depth formulas — no eyeballing. ALSO invoke BEFORE writing any new TikZ figure — Step 0 loads the prevention rules (PREVENTION.md); writing safe TikZ beats repairing it.
validate-bib
Validate bibliography entries against citations in all paper/manuscript files. Structural checks (missing/unused entries, malformed fields) by default; `--semantic` adds citation-drift detection, DOI verification, existence + retraction checks, and style-consistency checks.
analyze-paper
Analyze a research paper PDF and create structured notes for state-of-the-art positioning. Use when analyzing papers for literature review.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
proofread
Read-only proofreading pass over lecture `.tex` or `.qmd` files. Checks grammar, typos, overflow, terminology consistency, and academic writing quality; produces a report without editing. Use when user says "proofread", "check for typos", "look for grammar issues", "copy-edit this", "any writing errors?", or before a lecture release.
review-paper
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via --peer --stress. Reviews referenced analysis scripts and runs /audit-reproducibility on them unless --no-cross-artifact.
verify-claims
Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a forked (fresh) context so it never sees the draft — then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check the claims in X", "did I hallucinate anything", "fact-check this draft", "run CoVe on this", or after any text generation that asserts facts about papers, datasets, or numerical results. NOT for style/grammar review (use `/proofread`) or substance review (use `/review-paper`).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.