yulonglin/dotfiles

spawn-session

Spawn a detached tmux session running Claude Code in a chosen directory, seeded with an initial prompt, optionally reachable by Remote Control.

原文の言語: 英語

catalog

A human-facing index of every skill and agent in this repo, grouped by category, with a one-line trigger for each. Use only when the user explicitly asks "what skills do I have", "what can you do", "is there a skill for X", or invokes `/catalog` directly —…

原文の言語: 英語

pastelplot

House plot styling — pastel matplotlib defaults + annotation helpers. Use when making publication-quality figures, when the user asks to "style my plots", "use house style", "use pastelplot/anthroplot", or when generating any matplotlib figure for reports,…

原文の言語: 英語

wrap-up

Drives a stalled session to a terminating end state - land the work, state the blocker, or take one step (dotfiles trial, manual-only)

原文の言語: 英語

verification-planning

Use when about to verify, validate, or confirm anything in this repo — reproducibility checks, data validation, statistical analysis, integration or regression testing, or confirming a bug fix. Verification is a design problem, so plan how you'll verify…

原文の言語: 英語

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or says "grill me", "grill this plan", "poke holes in this", or "play devil's advocate."

原文の言語: 英語

chronicle

View the user's screen and recent history to resolve ambiguity. Use when the user says "what was I just doing", "what app was that", "what did I have open earlier", or when a request doesn't specify which document/app/error is meant. Also use for any question…

原文の言語: 英語

commit

Commit currently staged/unstaged changes with a formatted message. Use when the user says "commit this", "commit these changes", or "save my work" — for combined commit+push+sync, use commit-push-sync instead.

原文の言語: 英語

merge-worktree

Merge current worktree branch into the original branch, resolve conflicts with AI, then mark worktree for cleanup. Use when the user says "merge this worktree", "merge my branch back", or "finish this worktree."

原文の言語: 英語

setup-channel

Set up project-local messaging channels (Telegram, iMessage, Things Cloud) so Claude can send/receive messages and read tasks for this project. Use when the user asks to "set up Telegram", "connect iMessage", or "enable Things Cloud sync" for this repo.

原文の言語: 英語

diagnosing-bugs

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. Prefer this over systematic-debugging for diagnosis — it forces a red-capable feedback loop and 3-5…

原文の言語: 英語

writing-great-skills

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

原文の言語: 英語

grill-me

A relentless interview to sharpen a plan or design.

原文の言語: 英語

server-storage-tiering

Relieve a full root disk and organize storage on a server/cloud box (Hetzner, RunPod, bare-metal GPU) that has an attached volume. Use when `/` is near 100%, when you need to expose a volume at `/workspace`, or when deciding what lives on fast local NVMe vs.…

原文の言語: 英語

marp-deck

Build research slide decks from Markdown with Marp (marp-cli). Use when the user wants to "build slides", "make a marp deck", "create a presentation", export Markdown to HTML/PDF/PPTX slides, or embed matplotlib/anthroplot figures into a deck. Verified…

原文の言語: 英語

modal

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

原文の言語: 英語

commit-push-sync

This skill should be used when the user asks to "commit and push", "commit push", "sync changes", "push changes", "commit and sync", or "update remote". Handles the full workflow of committing changes, pulling with rebase, and pushing to remote.

原文の言語: 英語

sweep-ai-safety

Sweep recent AI safety research from curated sources (Anthropic alignment science / red team, OpenAI, GDM, Apollo, Redwood, METR, FAR AI, Truthful AI, alphaxiv, arXiv) and surface items matching tracked topic terms (inoculation prompting, reward hacking,…

原文の言語: 英語

anthropic-style

Anthropic visual style for plots, diagrams, slides, and web. Use when creating any visual output that should have Anthropic's look-and-feel — matplotlib charts, TikZ diagrams, HTML/CSS, or presentations.

原文の言語: 英語

check-bib-references

Catch LLM-fabricated citations in BibTeX files. Verifies arXiv/OpenReview entries against live metadata (titles, first authors), then guides manual verification of authorless prose claims. Use before submitting papers, after any LLM-assisted citation…

原文の言語: 英語

use-spark

Use the spark CLI to access the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, and view team info. Use when the user asks about their emails, calendar, contacts, meetings, or…

原文の言語: 英語

check-prose-claims

Fact-check prose claims in slides, reports, PDFs, and papers — statistics, comparatives, attributions, causal claims, quotes. Two-pass extract-then-verify protocol with strict numerical precision and a doc-only mode. Use when the user asks to "check the…

原文の言語: 英語

log-gap

Log a one-line knowledge gap to the project's gaps.md file. Use when the user is surprised by Claude's answer, says "I didn't know that", "wait what", or wants to record a misconception they just discovered. Format "I assumed X but actually Y". Personal…

原文の言語: 英語

recall-feedback

Resurface a random sample of feedback memories for spaced-repetition review — "still true? changed? promote to global rule?". Use when user asks for feedback retrospective, weekly memory review, or to audit accumulated coaching corrections. Also good for…

原文の言語: 英語

mv-repo

Move a repo to a new directory. Handles venv, Claude Code project state, path references, and tmux sessions.

原文の言語: 英語

jobs

Submit experiments or agent jobs with resource limits, check queue status, pause/resume workloads, troubleshoot slow machine

原文の言語: 英語

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

原文の言語: 英語

agent-teams

Orchestrate agent teams for parallelizable multi-faceted tasks. Use when work requires inter-agent communication, competing hypotheses, or multi-file parallel implementation.

原文の言語: 英語

custom-compact

Compact current work with optional focus using agent-context-summariser

原文の言語: 英語

externalise-handover

Externalise important parts of the current conversation into an .md file for handover.

原文の言語: 英語

my-insights

Run custom usage analytics on all Claude Code sessions

原文の言語: 英語