phucbm
- 24 skills
- 0 followers
- 16 hours ago last updated
- ▌
- ▌ Audit Blocks · phucbmFast structural audit of all blocks — checks required files, wrapper attributes, fields.json timestamp, preview.png. No AI, runs instantly via script.
- ▌ Create Block · phucbmScaffold a new ACF Gutenberg block with block.json, fields.json, and render.php
- ▌ Audit Blocks Deep · phucbmDeep AI audit of all blocks — runs structural checks first, then uses AI to review content quality, descriptions, grammar, admin render justification, wrapper usage, and empty-state messages.
- ▌ Add Block · phucbmScaffold one or more ACF Gutenberg blocks from GitHub issues, a markdown brief, or interactive prompts. Generates block.json, fields.json, render.php, and optional view.js.
- ▌ Plan Block · phucbmDiscuss a new block's purpose and requirements with the user, then create a GitHub issue with a structured breakdown ready for /wp-acf-blocks:add-block.
- ▌ Revise Block · phucbmFast structural audit of all blocks or specific blocks — checks required files, wrapper attributes, fields.json timestamp, previewImage, viewScript. No AI, runs instantly via script.
- ▌ Revise Block Deep · phucbmDeep AI audit of all blocks or specific blocks — runs structural checks first, then uses AI to review content quality, descriptions, grammar, admin render justification, wrapper usage, and empty-state messages.
- ▌ RAG · phucbmBuild a RAG (Retrieval-Augmented Generation) pipeline — chunk data, embed, store in vector DB, query at inference, inject into system prompt. Use when adding a custom knowledge base to an AI chatbot.
- ▌ Groq · phucbmIntegrate GROQ LLM streaming into a project. Use when the user wants to add GROQ, set up GROQ streaming, or use a GROQ model in their app.
- ▌ Learn · phucbmScan the current codebase, compare against existing phucbm/skills knowledge, and suggest new skills to save or existing skills to update. Use when the user says "learn from this repo", "what can I save from here", or "run learn".
- ▌ Pinecone · phucbmSet up Pinecone as the vector DB in a RAG pipeline — index config, batch upsert, semantic query, metadata filters. Use when the user is adding Pinecone or debugging vector search.
- ▌ Claskit · phucbmAutonomous Claude Code task runner — write task specs as Markdown files, run claskit, and Claude implements them one by one. Use when setting up claskit in a project, writing task specs, scheduling autonomous runs, or understanding the todo/done task lifecycle.
- ▌ Dexie · phucbmDexie.js usage in a local-first Next.js + React + TypeScript app (IndexedDB wrapper, useLiveQuery, schema versioning, migrations)
- ▌ Add Skill · phucbmAdd a new skill or knowledge entry to phucbm/skills repo. Use when the user says "add this to my skills", "save this as a skill", "push this knowledge to phucbm/skills", or wants to preserve a pattern from the current project.
- ▌ Update Skill · phucbmUpdate an existing skill or knowledge entry in phucbm/skills. Use when the user says "update my X skill", "update X knowledge", or "add this change to my X skill/knowledge".
- ▌ Counterapi · phucbmTrack simple hit counters (page visits, installs, etc.) via counterapi.dev v2 — a lightweight alternative to GA4, PostHog, or Umami when you only need a few numeric counters.
- ▌ Publish NPM · phucbmSet up a GitHub Actions workflow to publish an npm package on release — using either a long-lived npm token or OIDC trusted publishing (no stored secret). Use when adding CI publish automation to a package repo, wiring up phucbm/publish-npm-action, switching to OIDC, or debugging publish failures in Actions.
- ▌ Vercel AI Gateway · phucbmSet up Vercel AI Gateway (@ai-sdk/gateway) for multi-provider AI access. Use when adding the gateway, switching AI providers, handling reasoning/thinking models, or mocking AI in tests.
- ▌ Github As DB · phucbmUse a GitHub repo as a zero-infra, anonymous-friendly data store — JSON files as records, GitHub App bot as the write layer, build-time index compilation as the read layer. No auth service, no database, no backend required. Covers CRUD via Octokit, community contribution via PR flow, and build-time index generation to avoid API rate limits. Use when building community data repos, personal low-frequency data stores, open-source projects that need structured data without a database, or any "submit to repo" feature from a browser app where users don't need a GitHub account.
- ▌ Cloudflare Pages · phucbmUse when deploying a Next.js app to Cloudflare Pages, migrating from Vercel to Cloudflare, troubleshooting edge runtime errors, or evaluating whether a Next.js project is viable on Cloudflare's free or paid plan.
- ▌ Wp Acf Blocks · phucbm bundleScaffold, revise and manage custom ACF Gutenberg blocks for WordPress with Tailwind CSS. Use when the user wants to create a new block, revise/audit blocks, or set up a WordPress blocks project.
- ▌ Discord As Backend · phucbmUse Discord as a lightweight backend for web apps — read a Forum channel as a structured database (bookmarks, link store) or push form submissions into a Discord channel via webhook. Trigger when the user wants zero-infra persistence using Discord, or wants a no-database form submission inbox.
- ▌