Skip to main content
weikinhuang
GitHub creator profile

weikinhuang

Repository-level view of 40 collected skills across 1 GitHub repository.

skills collected
40
repositories
1
updated
Oct 23, 2026
repository explorer

Repositories and representative skills

memory-first
unclassified

Persist durable user preferences, validated approaches, project conventions, and reference pointers via the `memory` tool. Save when the user corrects your approach, expresses a preference, validates a non-obvious decision, or references an external system.…

Oct 23, 2026
notes-decision-tree
unclassified

WHAT: Choose between the three notes-ish tools - `scratchpad` (turn-to-turn free-form carry-over), `todo` (a typed multi-step plan), and `memory` (durable cross-session facts) - by scope and content kind. WHEN: You are about to jot something down to remember…

Oct 23, 2026
verify-before-claim
unclassified

WHAT: Before telling the user a code change is done, actually run a verification command (tests, lint, a smoke invocation) and paste the pass output into the reply. WHEN: Any multi-file edit, new script, rename, bug fix, or refactor where the user expects…

Oct 21, 2026
plan-first
unclassified

Plan multi-step work up front with the `todo` tool so it survives context compaction and stays visible every turn. Use when the user's request has two or more distinct steps, touches multiple files, mixes change + verify phases (e.g. "fix the bug and add a…

Oct 21, 2026
subagent-background
unclassified

Run subagents asynchronously with `run_in_background: true` and manage them with `subagent_send` (status / wait / steer / abort). Use when you want to fan out work, hide latency behind other steps, or keep the parent responsive while a long child runs. Pairs…

Oct 21, 2026
subagent-delegation
unclassified

Delegate discovery, planning, and scoped edits to a `subagent` (agent types `explore` / `plan` / `general-purpose`) whenever the next steps would pollute the parent's context with intermediate tool output you won't reuse. Use `modelOverride` to push grunt…

Oct 21, 2026
minimax-h3-prompting
unclassified

Prompting rules for the open-weight **MiniMax H3** audio-video model on the comfyui `minimax-h3-fl2va-t2i` (still image), `minimax-h3-ref2va-edit` (reference still / edit), and `minimax-h3-ref2va-spectrum` (reference video with native audio) workflows. Use…

Oct 17, 2026
moss-image-prompting
unclassified

Prompting rules for the OpenMOSS **MOSS-Image** text-to-image model on the comfyui `moss-image`, `moss-image-fast`, `moss-image-reference` (SFT checkpoint) and `moss-image-base*` workflows. Use when the user asks to generate / draw / render an image on a…

Oct 17, 2026
Showing 8 of 40 collected skills.
Showing 1 of 1 repository
All repositories loaded