chenlu-hung/my-skills

chatgpt-bridge

Ask the ChatGPT desktop app a question from the command line and read the answer on stdout, through the `chatgpt-ask` CLI. The answer is billed to the ChatGPT conversation allowance rather than to the Codex quota that `codex exec` spends, so it is the way to…

Idioma del texto original: inglés

llm-council

Convenes a multi-model "council" to answer a question, then synthesizes a single best answer — inspired by Karpathy's llm-council. Each member runs through its own subscription/sign-in CLI, not an API key: Codex (ChatGPT sub), Gemini (Antigravity `agy`), and…

Idioma del texto original: inglés

handoff

Manages context transfer between AI coding sessions. Creates a compact handoff document so a fresh agent can continue work. Use when user says "handoff", "hand off", "resume", "continue later", "pick up where we left off", "transfer context", or when wrapping…

Idioma del texto original: inglés

action

Schedule a one-shot Claude Code task to start at a specific wall-clock time and run headless/unattended, so work that has to happen while the user is asleep or away actually happens. Two main uses. First, unattended watch-and-wrap-up on remote work — wake at…

Idioma del texto original: chino

write-register

Picks the right writing register per output segment, automatically. Chat answers stay dense without going telegraphic; text destined for a file reads as deliberately written rather than as compressed chat or formulaic AI prose; code and structured data are…

Idioma del texto original: inglés

dispatch

Delegates coding tasks to external agent CLIs as if they were subagents — Codex (ChatGPT sub), Gemini (Antigravity `agy`), and DeepSeek (opencode, free) — each through its own subscription/sign-in CLI, not an API key. Workers get write access and can run in…

Idioma del texto original: inglés

review-me

Sends your own plan, diff, or design out to independent external models (Codex, Gemini, optionally a fresh Claude) to find what you MISSED — the failure mode of a single strong model working alone. Reviewers read the real repo read-only, so they can catch…

Idioma del texto original: inglés

fable-advisor

Formalizes the Anthropic-recommended architect/implementer split — the strongest model (Fable 5, this session) grills the user via the grill-me skill, designs the architecture, and writes it to a self-contained doc; an implementer subagent (default Opus,…

Idioma del texto original: inglés

project-map

Builds and maintains a compact, on-demand "project map" so coding agents remember a codebase's structure and spend fewer tokens during maintenance. Combines deterministic ctags indexing with short LLM-written module summaries, committed to the repo. Use when…

Idioma del texto original: inglés

grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree — then turn the agreed plan into a task list and dispatch the parallelizable work to model subagents. Use when user wants to…

Idioma del texto original: inglés