phuongnz

@phuongnz source repo

9 skills
0 followers
10 hours ago last updated

▌
Explain Repo · phuongnz bundle
Build a durable, navigable atlas of a code repository — structure, functional blocks, tech stack, history, CI/CD, strengths and weaknesses, and a "continue development" playbook — plus a distilled summary that bootstraps a future agent. Use when the user wants to understand, onboard to, document, take over, or keep building an unfamiliar codebase, asks for a repo overview / architecture map / codebase walkthrough, or wants to find good issues and PRs to contribute to a public repo.

0
installs
▌
Context Manager · phuongnz bundle
Analyze, reduce, and monitor Claude Code session context against a healthy "smart zone" (default 150k tokens, where quality stays high before context rot sets in). Use when the user wants to see how much of the smart zone is loaded at startup and the biggest consumers, decide whether to clean up (/clear vs /compact) or trim what loads every session (MCP servers, skills, memory, CLAUDE.md), pick/configure a status line, or set their own healthy window size. Triggers include "analyze startup context", "why is my context so big", "clean up context", "reduce context usage", "status line template", "configure statusline", "set healthy window", "smart zone size".

0
installs
▌
Teach Me Anything · phuongnz bundle
Tutor the user through a topic they want to master, across many sessions, inside a self-contained learning workspace with a spaced-review engine that resurfaces past material before it fades. Use when the user asks to be taught, coached, or walked through a subject or skill over time — languages, programming, fitness, music, a craft — and wants the learning to accumulate rather than evaporate after one chat.

0
installs
▌
Discover AI Use Cases · phuongnz bundle
Discover high-impact, personally-relevant AI use cases for a knowledge worker through a guided interview, producing a dated, prioritized report. Use when someone asks what they could actually use AI for in their job, feels their AI use is stuck on Q&A/summaries/images and wants real impact, or wants to audit their workday for automation and augmentation opportunities.

0
installs
▌
Design Agentic Architecture · phuongnz bundle
Design an agentic AI architecture from a use case and produce a dated design document. Use when the user wants to design or architect an agent or multi-agent system, decide single vs multi-agent, choose where to place memory, human-in-the-loop, or evaluation, or asks how to build an agent for a specific use case.

0
installs
▌
Design Agentic Infrastructure · phuongnz bundle
Consult on a complete agentic *coding* setup — the AI coding agents, workflow, and tools a developer builds software *with* — and recommend three designs across a floor-to-ceiling band, each with a live-priced cost estimate. Use when the user wants to choose a coding-agent architecture, workflow, and tools together for building a software project, match requirements/budget/tech-stack/business constraints to a coding-setup design, compare a light-vs-heavy build by cost, or asks what to build *with* and what it will cost. This designs the build setup, not the product itself — and not the runtime the product *runs on* in production; for that, see the sibling skill `design-product-infrastructure`, and to design both planes together, the bridge skill `design-full-stack-infrastructure`.

0
installs
▌
Design Product Infrastructure · phuongnz bundle
Consult on a complete product runtime infrastructure — the compute, data, delivery, and observability a software product *runs on* in production — and recommend three designs across a floor-to-ceiling band, each with a live-priced cost estimate. Use when the user wants to choose hosting/compute, a datastore and state layer, a release-and-rollback path, and observability together for a product; match requirements/traffic/budget/tech-stack/business constraints to a runtime design; compare a light-vs-heavy runtime by cost; or asks what to run the product *on* and what it will cost. This designs the product's runtime, not the AI setup it is built *with* — for that, see the sibling skill `design-agentic-infrastructure`, and to design both planes together, the bridge skill `design-full-stack-infrastructure`.

0
installs
▌
Run Devops With Orch Impl Rev · phuongnz bundle
Run a GitHub-native agentic delivery loop — a local orchestrator drives impl-bot and review-bot subagents through a label state machine with triage gates.

0
installs
▌
Design Full Stack Infrastructure · phuongnz bundle
Orchestrate a full-stack infrastructure design — BOTH the AI coding setup a product is built *with* AND the runtime infrastructure it *runs on* — by composing the two sibling skills (`design-agentic-infrastructure` for the coding plane, `design-product-infrastructure` for the product plane) and reconciling their shared substrate (durable execution, datastores, observability, flags, identity) into one deployment sized to the higher demand. Use when the user wants both planes designed together, asks how the coding-agent infrastructure and the product runtime should share components, or wants one combined cost view across build and run. For one plane alone, use the sibling skill directly — this bridge adds value only where the planes meet.

0
installs

9 published skills