phd-skills
claudeCatch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.
12 skills · 6 commands · 2 agents · hooks
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.
12 skills · 6 commands · 2 agents · hooks
Build Modelence apps with correct framework patterns: rules, working examples, and Modelence docs access.
2 skills · 2 MCP servers
Behavioral guidelines to reduce common LLM coding mistakes: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution
1 skill
Stretchtext replies for Claude Code: short by default, each phrase grows in place when you click it
1 command
AI code review agent for GitHub and GitLab. View and resolve Greptile's PR review comments, run reviews on your working branch, and search your organization's knowledge base and coding patterns, directly from Claude Code.
2 skills · 1 MCP server
CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.
5 skills · hooks
Extract RedNote (小红书) posts into concise Obsidian notes with video transcription
4 skills
Maps IaC to compliance controls, generates policies, collects evidence, reviews PRs
7 skills · 19 commands
Editable draw.io diagram patterns for GRC system boundaries, evidence flows, control maps, risk treatment, audits, crosswalks, TPRM, POA&M, data flows, RACI, and operating models.
13 skills · 13 commands
Build and deploy a professional portfolio website for GRC engineers — certifications, frameworks, audit experience, and AWS hosting.
7 skills · 7 commands
131 battle-tested skills for Claude Code. Session memory, git workflows, database migrations, security scanning, deployments, and more.
87 skills · hooks
5 skills: reels from talking videos · 3D motion explainers · podcasts · beat-synced montage · covers & thumbnails
6 skills
Pair programming protocol for marimo notebooks
2 skills
Lightweight Station integration with skills and slash commands - guides Claude through Station operations
2 skills · 1 command · 1 MCP server
Bridge Claude Code and Codex through a shared daemon, push channel delivery, and reply/get_messages tools.
1 command · 1 MCP server · hooks
Full Station integration with pre-configured subagent - autonomous Station operations via dedicated expert agent
1 agent · 1 MCP server
2x the effective context with smart weight-loss for Claude Code — prune bloated sessions, protect agent teams from compaction, monitor token usage with MCP tools
5 skills · 1 MCP server · hooks
MCP tool-catalog compression for Claude Code. Compresses the tool discovery payload from 71,929 to 581 tokens (-99.2%). Auto-installs the zero-dependency mcptoon CLI (/mcptoon-setup), wires the serve bridge, and teaches the agent when to compress. MCP 2026-07-28 stateless-first bridge included.
1 skill · 1 command · 1 MCP server · hooks
Comprehensive security rules for AI coding agents
1 skill
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work: big refactors, multi-file migrations, codebase-wide audits, and bulk generation. Pick an army size and power level; includes git checkpoints, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
1 skill
Not sure which skill or subagent fits the task? Scout reads the conversation and recommends the best skills and subagents, explains why, and lays out how to chain them.
1 skill
A deeper skill navigator: maps the whole conversation, verifies which skills you actually have installed, designs multi-skill chains, and keeps a local log of which recommendations worked so it gets better over time.
1 skill
Dexter language server for Elixir (.ex, .exs, .heex)
Backtest Taiwan and US stock strategies on real market data with the FinLab Python package: data access, backtesting, factor research, and 60+ strategy examples.
1 skill
Git-native project memory for AI coding agents, with deterministic local recall, evidence gates, and layered delivery that quotes, points, or abstains.
3 skills
HEY integration for Claude Code. Read email, manage todos, track time.
1 skill · hooks
Original editorial illustrations where a recurring mascot performs the idea — fourteen bundled looks, custom characters, palettes from your own site's colors.
1 skill
Make a showreel-grade product film (landing loop, launch video, promo) in Remotion, built on the product's own design system.
1 skill
Frame research arguments, plan and revise connected paragraphs, and review academic evidence. Progressive section and domain guides cover abstracts, supplements, references and reviewer responses, with checks scoped to a passage, section or revision package.
6 skills
Royal Navy agent coordination framework — sailing orders, battle plans, action stations, and a captain's log
1 skill · 1 agent · hooks