David clarifies that his process refers to the software-factory workflow in dzhng/skills. The repository combines exploration, specification, implementation and review Skills, with a focus on independently verifiable parts. This post links the collection as a whole.
dzhng/skills
- Última actividad de origen registrada
- Catálogo de SkillsMP actualizado
- skills recopiladas
- 9
- Estrellas en GitHub
- 967
- Forks en GitHub
- 58
Cargando el README del repositorio…
dzhng/skills: choose a software workflow
This collection brings together feature exploration, specifications, implementation and review, with separate Skills for experiments, visual checks, Skill authoring and evaluation. The README offers a feature workflow as well as individual Skills that can be used on their own.
Uses
For a feature that still needs definition, start with explore-unknowns. Choose auto-research when the next decision needs experimental evidence.
How to use
The README’s installation entry is npx skills add dzhng/skills; add --list to choose individual Skills.
Sources
Publicaciones
Ver todos →Skills en este repositorio
Mostrando 9 de 9 skills recopiladas.
Architecture rules for GPU rendering with TypeGPU/WebGPU — games, data visualisation, canvases, any app that draws with the GPU. Use when adding or changing passes, shaders, buffers, textures, pipelines, frame orchestration, GPU resource lifetimes, or checks…
Idioma del texto original: inglés
Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.
Idioma del texto original: inglés
Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot…
Idioma del texto original: inglés
Compare screenshots to judge which image is less wrong, not to match a baseline. Use when a UI, game, document, render, chart, or generated asset needs objective visual telemetry, side-by-side inspection, crop/zoom review, or a fresh second opinion before…
Idioma del texto original: inglés
Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.
Idioma del texto original: inglés
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the…
Idioma del texto original: inglés
Refactor cleanly instead of layering sediment. Use when a change reveals duplicated concepts, local adapters, obsolete owners, compatibility wrappers, parallel abstractions, an over-large module that has accreted many responsibilities, or "just tack this on"…
Idioma del texto original: inglés
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's…
Idioma del texto original: inglés
Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task…
Idioma del texto original: inglés
Instalar con un asistente de IA
Copia este prompt en el asistente de IA que estés usando.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/dzhng/skills.