Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 437 files from 1 744 authors, of which 61 785 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Search academic literature and generate research hypotheses
Produce an experiment blueprint from a research hypothesis
Draft a LaTeX research paper from all previous stage outputs
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Deploy a Kubernetes GPU cluster with DeepOps (Kubespray + GPU Operator) and prove it schedules GPU pods. Use when asked to deploy or rebuild Kubernetes on GPU servers with this repository.
Deploy a Slurm GPU cluster with DeepOps and prove it works. Use when asked to deploy, install, or rebuild Slurm on one or more GPU servers with this repository.
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
Check whether a DeepOps-deployed Slurm or Kubernetes GPU cluster is healthy and report a machine-readable verdict. Use for health checks, post-deploy verification, "is the cluster working?" questions, and after any node or driver change.
Reviews adk-bot pull requests by validating technical correctness against source code, checking PR states and formatting, and following Google's developer documentation style and ADK docs conventions. Triggers on "review bot PR", "check bot changes", or "verify bot issue".
Creates a new ADK integration documentation page (a Markdown file under docs/integrations/) for a third-party tool, plugin, observability platform, data store, MCP server, or connector. Gathers details, picks the right category template, and drafts a page that follows adk-docs conventions. Triggers on "integration-create", "create integration page", "new integration", "add an integration", "write an integration page".
Reviews an ADK integration documentation page (a Markdown file under docs/integrations/) or an integration pull request for correctness, structure, style, working code, valid links, and catalog conventions. Produces a prioritized review report, a recommended decision (approve, request changes, or close PR), a top-level review response, and draft line-anchored comments; only fixes issues when explicitly asked. Triggers on "integration-review", "review integration page", "review integration PR", "review this integration", "check integration docs".
Audits whether ADK API reference docs and version-pinned strings are up to date across all language SDKs. Compares in-repo versions against upstream releases and package registries, then reports what needs bumping and which process to follow, and emits an executable plan only when asked. Triggers on "audit API reference", "check API ref docs", "are API docs up to date", "bump API doc versions", "check SDK doc versions".
Create new eval suites for the deepagentsjs monorepo. Handles dataset design, test case scaffolding, scoring logic, vitest configuration, and LangSmith integration. Use when the user asks to: (1) create an eval, (2) write an evaluation, (3) add a benchmark, (4) build an eval suite, (5) evaluate agent behaviour, (6) add test cases for a capability, or (7) implement an existing benchmark (e.g. oolong, AgentBench, SWE-bench). Trigger on phrases like 'create eval', 'new eval', 'add eval', 'benchmark', 'evaluate', 'eval suite', 'write evals for'.
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a `.tex` file isn't producing a PDF. Operates on `Slides/*.tex`.
| Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
Stage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "open a PR", "merge to main", "let's commit this", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Runs the standard commit-PR-merge cycle; never force-pushes or skips hooks.
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning Dockerfile, and produces a paste-ready "Computational requirements" block. Use when user says "capture the environment", "snapshot my dependencies", "pin the versions", "make a renv.lock / requirements.txt", "make this byte-reproducible", or before releasing a replication package to openICPSR / the AEA Data Editor.
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Distill the current conversation into a structured note (decisions made, open questions, file pointers with line numbers, next 1–3 actions) and save to `quality_reports/session_logs/` before auto-compression. Differs from `/checkpoint` (explicit stop-point snapshot) and from auto-compaction (which truncates rather than distills). Use when context is approaching auto-compact threshold, when a long pipeline has accumulated many decisions, or when the user says "compress", "distil this session", "before we hit auto-compact", "structured handoff before context resets".
Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says "coauthor brief", "handoff brief", "bring my coauthor up to speed", "what changed since last week", "onboard a collaborator", "write a handoff for [name]", or before sending a co-author the repo. NOT a commit or a checkpoint — it is the cross-machine, cross-person summary `meta-governance.md` only partially covers.
Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a checkpoint file under `quality_reports/checkpoints/`. Optionally proposes `[LEARN]` entries to add to MEMORY.md. Use when user says "checkpoint", "save state", "snapshot before I stop", "where am I", "wrap up the session for handoff", or before a long break / model switch / collaborator handoff. Companion to (NOT replacement for) the narrative session-log workflow.
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data management plan", "DMP", "DMSP", "NIH data sharing plan", "write the data plan for my grant", or when a grant proposal needs a data-management section. NOT a submission tool — produces a draft the user pastes into the funder portal (DMPTool, NIH ASSIST, Horizon Europe portal).
Create a new Beamer lecture `.tex` from source papers and materials, with notation consistency checks and the project's preamble wired in. Use when user says "create a lecture on X", "new lecture from these papers", "start a deck on topic Y", "scaffold a new Beamer file", "build me a lecture from these PDFs". Scaffolds the full deck — NOT for compiling existing `.tex` (use `/compile-latex`).
Root-cause a failing or wrong empirical result with a disciplined reproduce → minimise → hypothesise → instrument → fix loop, instead of guessing-and-poking. Use when the user says "why is my regression wrong", "this number changed", "my script errors out", "the result won't reproduce", "debug this", "this estimate looks wrong", or "it worked yesterday". Tuned for research code (R/Stata/Python): type coercion, NA/merge blow-ups, factor levels, clustering/SE choices, weighting, collinearity/convergence, seeds, package-version drift. Use `--no-fix` to localize the root cause without editing shared or load-bearing files.
Render Quarto `.qmd` slides to HTML and sync to `docs/` for GitHub Pages. Use when user says "deploy", "publish the slides", "ship to pages", "push the lecture live", "render and publish", or after Quarto edits that need to go public. NOT for local Quarto render only — use `quarto render` directly for that.
End-to-end R data analysis pipeline — exploration → cleaning → regression → publication-ready tables and figures. Use when user says "analyze this dataset", "run a regression on X", "explore this CSV", "full analysis workflow", "get me summary stats and a regression", or points at a `.csv`/`.rds`/`.dta` and asks for empirical results. Produces numbered R scripts in `scripts/R/` and outputs to `scripts/R/_outputs/`.
Run a staggered difference-in-differences / event-study analysis to the Sant'Anna practitioner standard — drives the canonical packages (R `did`/`DRDID`/`didFF`/`contdid`; Stata `csdid`/`drdid`), enforces the doubly-robust default, a mandatory diagnostic + sensitivity suite, uniform-band inference, replicate-and-verify-against-source discipline, and ends in a graded credibility verdict. Use when user says "run a DiD", "event study", "staggered adoption", "Callaway Sant'Anna", "att_gt", "csdid", "did with multiple periods", or points at panel data with a treatment-timing variable. NEVER reimplements an estimator.
| Deep consistency audit of the entire repository infrastructure. Launches 4 parallel specialist agents to find factual errors, code bugs, count mismatches, and cross-document inconsistencies. Then fixes all issues and loops until clean. "audit", "find inconsistencies", "check everything".
Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation. Use when user says "devil's advocate", "poke holes in this deck", "push back on my slides", "stress-test the design", "what would a skeptical student ask?". Read-only; surfaces questions to force rethinking. Lighter than `/pedagogy-review`.
Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an `/interview-me` spec, delegates the data-management plan to `/data-management-plan` and the facilities statement to `/capture-environment`, and emits a funder-requirements checklist. Use when user says "draft a grant", "write a proposal", "NSF proposal", "NIH aims", "ERC application", "foundation grant", "specific aims", or "scaffold a grant proposal". NOT a submission tool — produces a draft the user uploads to the sponsor's portal themselves.
Extract TikZ diagrams from Beamer `.tex` source, compile each to a standalone PDF, and convert to SVG with 0-based indexing. Use when user says "extract the tikz", "regenerate the diagrams", "rebuild the SVGs", "sync tikz to quarto", or after editing TikZ blocks in a Beamer deck that also has a Quarto mirror.
| Extract reusable knowledge from the current session into a persistent skill. Use when you discover something non-obvious, create a workaround, or develop a multi-step workflow that future sessions would benefit from.
Pre-screen analysis outputs (tables, figures, logs) built on restricted or confidential data for statistical-disclosure-limitation problems before any release. Scans for small cell counts, complementary-suppression gaps, dominance (p-percent / (n,k)), re-identifiable exact counts, PII leakage, and unrounded sensitive statistics; classifies each finding CRITICAL / WARNING / OK and gates on any CRITICAL. Use before depositing or sharing restricted-data results, or when the user says "disclosure check", "SDL scan", "is this output safe to release", "check for small cells", "disclosure avoidance", "pre-screen for the RDC", or "can I export this from the enclave".
Interactive interview that formalizes a fuzzy research idea into a structured spec (RQ, hypotheses, identification, data needs, empirical strategy). Use when user says "interview me", "help me think through this idea", "I have a half-baked idea", "formalize this into a project", "walk me through framing a study". Multi-turn Q&A; saves spec to disk. NOT for lit review (`/lit-review`) or ideation from scratch (`/research-ideation`).
Structured literature search + synthesis with citation extraction, thematic clustering, and gap identification. Use when user says "find papers on X", "do a lit review", "what's the literature on...", "summarize what we know about...", "where's the gap in this field", "review recent work on Y". Produces a written review with BibTeX-ready citations. Uses WebSearch/WebFetch for recent work.
Read-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplate transitions ("Moreover", "Furthermore", "It is important to note that"), AI-cliché lexicon ("delve", "navigate the complexities", "tapestry", "robust framework"), em-dash overuse, symmetric paragraph shapes, tricolon abuse, hedging stacking, "not only X but also Y" frames, and formulaic openers. Produces a report; does NOT rewrite. Use when user says "humanize", "does this sound like AI?", "check for AI tells", "de-AI this draft", "remove AI voice", "audit my prose for sycophancy", or before journal submission / posting a working paper.
Scaffold a new TikZ diagram from the snippet gallery with prevention rules pre-applied (explicit node dimensions, coordinate map, directional edge labels). Compiles standalone, invokes tikz-reviewer with citations from tikz-measurement.md, and loops on revisions until APPROVED.
Scaffold a new skill that follows this repo's conventions — interviews for purpose, trigger phrases, and tool needs, then writes `.claude/skills/<name>/SKILL.md` from the skill template with frontmatter and body that pass the integrity gates on first try. Use when user says "write a skill", "scaffold a skill", "create a new skill", "I keep doing X, make it a skill", "new slash command", or "turn this workflow into a skill". NOT for capturing a one-off session discovery — that is `/learn`.
Compute statistical power, required sample size, and minimum detectable effect (MDE) for a study design, then write a registry-ready power section. Handles two-arm RCTs (with clustering / ICC and unequal allocation), multiple-arm corrections, and a simulation-based power option for non-standard designs (DiD/event-study, IV, panel). Use when user says "power analysis", "power calculation", "MDE", "minimum detectable effect", "how big a sample do I need", "is my study powered", "power for an RCT", or when /preregister needs a power section for an experiment. Produces a power/MDE table, power curves, and a methods paragraph to paste into a preregistration.
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.
Holistic pedagogical review of a lecture deck (`.qmd` or `.tex`). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before teaching a deck for the first time. Read-only; produces a report.
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.
Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when user says "preregister", "draft a preregistration", "OSF preregistration", "AsPredicted", "AEA RCT registry", "PAP", "preanalysis plan", or before launching an experiment / data collection / analysis on data the analyst has not yet seen. NOT a registry submission tool — produces a document the user uploads to OSF / AsPredicted / AEA themselves.
Adversarial Quarto-vs-Beamer parity QA. A critic agent compares the Quarto HTML render to the Beamer PDF benchmark for content/visual parity; a fixer agent applies fixes; loops until APPROVED (max 5 rounds). Use when user says "qa the quarto", "check parity", "does the html match the pdf?", "quarto matches beamer?", or after a translate-to-quarto run. Requires both the `.qmd` rendered and a `.pdf` benchmark.
Review candidate `[LEARN]` entries in `.claude/state/personal-memory.md` (gitignored) and run them through a five-critic council in parallel: generality, staleness, redundancy, evidence, format. Majority vote (3+ of 5) promotes the entry to MEMORY.md. Use when user says "promote memory", "review my learnings", "what should graduate to MEMORY.md", "five-critic council", or as monthly memory maintenance.
Run the full R package release gate — regenerate docs, run the test suite, run R CMD check --as-cran, and triage every ERROR / WARNING / NOTE against CRAN policy before a release or submission. Use when the user says "check my R package", "R CMD check", "is this package CRAN-ready", "run devtools::check", "prepare for CRAN submission", or points at a directory containing a DESCRIPTION file. Produces a check report + CRAN-submission checklist in `quality_reports/`.
Assemble a submission-ready replication package to the AEA Data and Code Availability Standard (DCAS) / openICPSR / Social Science Reproduction Platform expectations — standard replication README, dataset manifest, computational-requirements capture, a Table/Figure → script:line map, and a confidential-data deposit plan. Use when user says "build the replication package", "prepare the openICPSR deposit", "make the AEA data and code package", "DCAS compliance", "assemble the deposit for the journal", or after a paper is accepted and the journal's data editor needs the package. NOT a numeric verifier — it calls /audit-reproducibility to confirm claims reproduce before packaging.
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the syllabus and slide decks. Use when user says "respond to my evals", "what do these course evaluations tell me", "turn my teaching feedback into a plan", or after a semester's evals arrive.
Generate structured research questions, testable hypotheses, and candidate empirical strategies from a topic, phenomenon, or dataset description. Use when user says "give me research ideas on X", "brainstorm questions about Y", "what could I study with this data?", "I'm looking for a paper idea on...", "generate hypotheses for...". One-shot generation, not multi-turn. For idea-refinement use `/interview-me`.
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; reviewer-disposition variance reporting via --peer --variance N. Auto-invokes /review-r + /audit-reproducibility on referenced scripts unless --no-cross-artifact.
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.
Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when an R file is touched as part of a paper submission. NOT for running the code — pair with `/audit-reproducibility` for numeric verification.
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key", "build a graded assignment on topic Y". Emits a clean student set plus a separate solution key — NOT for grading submissions or auto-checking student answers.
Scaffold and run a reproducible Monte Carlo simulation study in R — parameterized DGP, an estimator grid, a seeded replication loop, and a summary of bias, RMSE, empirical SE, coverage, size/power with Monte Carlo standard errors. Use when the user says "run a Monte Carlo simulation", "simulation study", "check the bias/coverage of an estimator", "compare estimators in simulation", "size and power simulation", "Monte Carlo experiment", or wants to demonstrate an estimator's finite-sample properties. Produces a numbered R script in `scripts/R/` and saves per-replication raw results + a summary table to `scripts/R/_outputs/`.
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.
End-to-end Stata replication pipeline — scaffolds numbered `.do` files in `scripts/stata/`, executes them via the `stata-mcp` MCP server, captures logs and outputs to `scripts/stata/_outputs/`, and produces publication-ready tables (esttab) and figures (graph export). Mirrors `/data-analysis` for R-first projects. Use when user says "stata replication", "set up Stata pipeline", "scaffold the .do files", "run Stata analysis", "AEA replication package in Stata", or when a project's analysis language is Stata not R.
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for a single lens, use `/visual-audit`, `/pedagogy-review`, or `/proofread` directly.
Generate the submission-time disclosure block for a manuscript — the AI-use disclosure statement matched to the target journal's policy, CRediT author-contribution roles, conflict-of-interest statement, and data-availability statement. Use when the user says "AI disclosure", "disclosure statement", "do I need to disclose Claude", "CRediT roles", "conflict of interest statement", "data availability statement", or is preparing a submission package. NOT statistical-disclosure screening of restricted-data outputs — that is /disclosure-check.
Build or restructure a course syllabus from a topic list or reading list — course description + prerequisites, week-by-week schedule (topic → readings → deliverables), measurable learning objectives, an assessment scheme + rubric, standard policies (late work, AI use, academic integrity, accessibility), and a per-week work-list to hand to `/create-lecture`. Use when user says "build a syllabus", "structure my course", "turn this reading list into a schedule", "draft a course outline", "make a syllabus for Econ 7xx", or "map weeks to lectures". Economics-aware (PhD metrics/micro/macro sequences, undergrad); generic enough for any field.
Claude Skills — questions
Answers built from the skills we actually parsed.