Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ai-data-analyst
Perform comprehensive data analysis, statistical modeling, and data visualization by writing and executing self-contained Python scripts. Use when you need to analyze datasets, perform statistical tests, create visualizations, or build predictive models with reproducible, code-based workflows.
majiayu000/claude-skill-registry 163
-
baoyu-slide-deck
Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".
majiayu000/claude-skill-registry 163
-
sql-pro
Use when optimizing SQL queries, designing database schemas, or tuning database performance. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis.
majiayu000/claude-skill-registry 163
-
QE Chaos Resilience
Chaos engineering and resilience testing including fault injection, load testing, and system recovery validation.
majiayu000/claude-skill-registry 163
-
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
majiayu000/claude-skill-registry 163
-
plan-design-review
Designer's eye plan review — interactive, like CEO and Eng review.
Rates each design dimension 0-10, explains what would make it a 10,
then fixes the plan to get there. Works in plan mode. For live site
visual audits, use /design-review. Use when asked to "review the design plan"
or "design critique".
Proactively suggest when the user has a plan with UI/UX components that
should be reviewed before implementation.
majiayu000/claude-skill-registry 163
-
file-organizer
Intelligently organizes files and folders by understanding context, finding duplicates, and suggesting better organizational structures. Use when user wants to clean up directories, organize downloads, remove duplicates, or restructure projects.
majiayu000/claude-skill-registry 163
-
comments-docs
Reviews comment quality and documentation practices. Use when the user asks to review comments or documentation, when comments just repeat the code, when something is hard to describe in a sentence, or when writing documentation before code to surface design problems. Evaluates the four comment types, comments-first workflow, and comment rot.
majiayu000/claude-skill-registry 163
-
nw-tbr-methodology
Train from the Back of the Room (TBR) practitioner reference for the nw-workshopper agent. Covers the 4C framework, time allocation formulas, 20% talk time rule, Six Trumps, series design with spacing, Bloom's spiral, and assessment checkpoints.
majiayu000/claude-skill-registry 163
-
k8s-manifest-generator
Kubernetes manifest patterns, resource configuration opinions, and configuration validation. Use when generating K8s YAML, creating Helm charts, packaging K8s applications, or validating configs across environments.
majiayu000/claude-skill-registry 163
-
motherduck-explore
Discover and explore databases, tables, columns, and data shares in MotherDuck. Use when you need to understand what data is available, preview table contents, or search the data catalog.
majiayu000/claude-skill-registry 163
-
pymc
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
majiayu000/claude-skill-registry 163
-
conductor-manage
Manage track lifecycle: archive, restore, delete, rename, and cleanup
majiayu000/claude-skill-registry 163
-
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
majiayu000/claude-skill-registry 163
-
dr-get-formula
Generate Excel workbooks with DR.GET formulas that pull live financial data from Datarails. Creates P&L templates, budget models, and variance reports with validated dimension values.
majiayu000/claude-skill-registry 163
-
researchers-verifier
Performs quality control, citation validation, and fact-checking before human review. Use after research is complete to verify all sources and claims before production.
majiayu000/claude-skill-registry 163
-
task-builder
majiayu000/claude-skill-registry 163
-
bulk-github-star
Star all repositories from a GitHub user automatically. Use when: (1) Supporting open source creators, (2) Bulk discovery of useful projects, or (3) Automating GitHub engagement.
majiayu000/claude-skill-registry 163
-
genome-compare
Compare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture
majiayu000/claude-skill-registry 163
-
pdf
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
majiayu000/claude-skill-registry 163
-
age-file-encryption
Encrypt and decrypt files or streams using age — a simple, modern, and secure encryption tool with small explicit keys, passphrase support, SSH key support, post-quantum hybrid keys, and UNIX-style composability. No config options, no footguns.
majiayu000/claude-skill-registry 163
-
sentry-automation
Automate Sentry tasks via Rube MCP (Composio): manage issues/events, configure alerts, track releases, monitor projects and teams. Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
chaos-gremlin-v2
🍆👾 BIG DICK GLITCH GREMLIN SUPER COLLIDER. Unconventional problem-solving with chaotic good energy. Finds creative edge cases, challenges assumptions, explores weird solutions that technically work. For full gremlin brain stack, load: gremlin-boot → gremlin-core → gremlin-reasoning → gremlin-collider.
majiayu000/claude-skill-registry 163
-
hypershift:debug
Debug AWS resources for HyperShift clusters - identify stuck resources, orphaned infrastructure, and deletion blockers
majiayu000/claude-skill-registry 163