pedrohcgs/claude-code-my-workflow

这个仓库里有 60 个技能，GitHub 星标 ★ 1,585。

• adjudicate-reviewTurn an incoming set of findings — from an AI reviewer, a referee report, a code
• audit-reproducibilityEnforce the replication-protocol.md rule by cross-checking numeric claims in a m
• blast-radiusBefore and after changing anything shared — a function's return value, a signatu
• capture-environmentSnapshot the computational environment for a replication package — detects the a
• challengeStress-test a finding against the choices you did not make. Enumerates the discr
• checkpointSave a structured state snapshot before stopping or handing off. Captures the ac
• coauthor-briefGenerate a co-author / collaborator handoff brief for a multi-author, multi-mach
• commitStage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit i
• compile-latexCompile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when use
• compress-sessionDistill the current conversation into a structured note (decisions made, open qu
• context-status|
• create-lectureCreate a new Beamer lecture `.tex` from source papers and materials, with notati
• credible-claimsResearch-brief + claim-record discipline for delegated or AI-assisted research w
• data-analysisEnd-to-end R data analysis pipeline — exploration → cleaning → regression → publ
• data-management-planDraft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC
• deep-auditComprehensive adversarial audit of a theory, proof, math/econ paper, codebase, o
• deployRender Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use wh
• devils-advocateAdversarial 5-7 question challenge to a deck's pedagogical choices — ordering, p
• diagnoseRoot-cause a failing or wrong empirical result with a disciplined reproduce → mi
• differential-auditCompare two implementations of the same thing — a port (R↔Python↔Stata), a reimp
• disclosure-checkPre-screen analysis outputs (tables, figures, logs) built on restricted or confi
• extract-tikzExtract TikZ diagrams from Beamer `.tex` source, compile each to a standalone PD
• grant-proposalScaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing e
• humanizeRead-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplat
• interview-meInteractive interview that formalizes a fuzzy research idea into a structured sp
• learn|
• lit-reviewStructured literature search + synthesis with citation extraction, thematic clus
• new-diagramScaffold a new TikZ diagram from the snippet gallery with prevention rules pre-a
• new-skillScaffold a new skill that follows this repo's conventions — interviews for purpo
• oracle-reviewRun an external frontier-model referee (Claude Code -> GPT-5.6 Sol Pro via the O
• pedagogy-reviewHolistic pedagogical review of a lecture deck (`.qmd` or `.tex`). Checks narrati
• permission-checkDiagnose why Claude Code is (or isn't) prompting for permission. By default read
• power-analysisCompute statistical power, required sample size, and minimum detectable effect (
• preregisterDraft a structured preregistration document (OSF, AsPredicted, or AEA RCT Regist
• promote-memoryReview candidate learnings in Claude Code's native auto memory (`~/.claude/proje
• proofreadRead-only proofreading pass over lecture `.tex` or `.qmd` files. Checks grammar,
• qa-quartoAdversarial Quarto-vs-Beamer parity QA. A critic agent compares the Quarto HTML
• r-package-checkRun the full R package release gate — regenerate docs, run the test suite, run R
• replication-packageAssemble a submission-ready replication package to the AEA Data and Code Availab
• research-ideationGenerate structured research questions, testable hypotheses, and candidate empir
• respond-to-evalTurn student course evaluations (free-text + numeric) into an actionable teachin
• respond-to-refereesGenerate a structured response-to-referees document from a referee report and th
• review-paperComprehensive manuscript review with three modes: single-pass (default), --adver
• review-rRead-only R code review protocol for `.R` scripts. Checks code quality, reproduc
• scaffold-exercisesScaffold a graded problem set with sections, problems, worked solutions, and sho
• seven-pass-reviewMechanize Pattern 15 — the seven-pass adversarial review protocol for academic m
• simulation-studyScaffold and run a reproducible Monte Carlo simulation study in R — a declared a
• slide-excellenceMulti-agent comprehensive slide review (visual + pedagogy + proofreading, plus T
• stata-replicationEnd-to-end Stata replication pipeline — scaffolds numbered `.do` files in `scrip
• submission-disclosuresGenerate the submission-time disclosure block for a manuscript — the AI-use disc
• syllabusBuild or restructure a course syllabus from a topic list or reading list — cours
• teach-from-paperTurn a research paper into teaching materials — a lecture outline, the 3-5 resul
• translate-to-quartoTranslate a Beamer `.tex` lecture to a Quarto RevealJS `.qmd` mirror. Multi-phas
• triage-inboxTriage academic email and calendar (Gmail / Google Calendar via the session's MC
• vaccinateQualify a check before it is allowed to clear anything — prove it can detect the
• validate-bibValidate bibliography entries against citations in all lecture files. Structural
• verify-artifactProve that the file you are about to send, publish, or hand off IS the thing you
• verify-claimsRun Chain-of-Verification (CoVe) on a draft or a block of text with factual clai
• visual-auditAdversarial visual-layout audit of a Quarto `.qmd` or Beamer `.tex` deck. Flags
• voice-profileExtract a written voice profile from your own prior papers, then use it to keep