Source

dzhng/skills

24 skills · 3.3K combined installs

Skills from this source

#

Skill

Source

8W Activity

Installs

explore-unknowns Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work…

refactor-clean Refactor cleanly instead of layering sediment. Use when a change reveals duplicated concepts, local adapters, obsolet…

implement-spec Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoin…

codex Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a secon…

close-spec When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), a…

write-docs Write and edit project docs (README/markdown) as a glossary of principles, not a mirror of the code. Use when creatin…

compare-screenshots Compare screenshots to judge which image is less wrong, not to match a baseline. Use when a UI, game, document, rende…

eval-skills Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each …

screenshot-critique Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user…

write-skills Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, imp…

write-spec Break large features into independently verifiable, human-reviewable slices under specs/<feature>/. Use for risky or …

preview-shots Open image shots (screenshots, snapshot baselines, montages, renders) in ONE macOS Preview window so the user can eye…

renderer Build, debug, or review WebGPU renderer work — three.js/TSL scene layers, node materials, or raw WGSL passes and comp…

implement-spec-with-codex Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, in…

claude Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent…

write-tests Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when addin…

eli5 Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and ev…

code-review Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing i…

review Closeout pass on a finished substantive change — sequence refactor-clean (shape), code-review (diff), and write-docs …

audit-choices Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history …

audit-performance Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find perfor…

marketing-pages Best-practice rulebook for a marketing site's pages, organized by page class — campaign landers, product pages, progr…

feature-slicing Break large features into independently verifiable, human-reviewable slices under specs/<feature>/. Use for risky or …

find-skills Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is…