kimsanguine

kimsanguine/AI_PM

Command

A guided course for learning Claude Code through hands-on exercises rather than reading alone.

kimsanguine/AI_PM

Command

A weekly product-management status report command that summarizes work for the week.

kimsanguine/AI_PM

Command

A daily product-management briefing command that organizes the day's urgent and ongoing work.

kimsanguine/llm-brain

Plugin Claude Code

Plugin marketplace listing 1 plugin: llm-brain.

kimsanguine/llm-brain

Plugin Claude Code

A personal knowledge system that turns raw notes into an organised, searchable wiki and can export them in an open format. It also keeps separate layers for tasks, experiences, concepts, procedures and system information.

kimsanguine/llm-brain

Instructions file

A set of Claude Code instructions for llm-brain, a system that turns source files into a searchable wiki and answers questions from it.

kimsanguine/llm-brain

Command

Command "curate" from kimsanguine/llm-brain, covering 인자 파싱, step 1: curate 스크립트 실행, step 2: distill 실행 (--distill 또는 --all 일 때), step 3: reweave 실행 (--reweave 일 때) and step 3.5: 모순 후보 화해 (wiki/contradictionqueue.md 존재 시).

kimsanguine/llm-brain

Command

A diagnostic command for checking and, when requested, repairing an llm-brain installation. It also offers read-only profiles for demo, private use, or preparing a shareable setup.

kimsanguine/llm-brain

Command

A command that gathers related wiki pages and drafts content from them. It supports blog posts, lecture slides, weekly or monthly summaries, and in-depth reports.

kimsanguine/llm-brain

Command

A command for adding information to a file-based knowledge wiki from web pages, files, or text notes. It classifies the material, updates or creates wiki pages, and adds links between related pages.

kimsanguine/llm-brain

Command

Command "okf" from kimsanguine/llm-brain, covering 인자 파싱, 기본 private export, 🔴 share-ready gate (외부 공유 전 one-way door), legacy step 1: private dry-run 검토 and legacy step 2: private export.

kimsanguine/llm-brain

Command

Command "query" from kimsanguine/llm-brain, covering step 1: index.md 검색, step 2: persisted claim ledger 로드, step 3: wiki 기반 답변 and step 4: 연결 요약 출력.

kimsanguine/llm-brain

Command

A local web interface for searching and viewing a project’s Markdown wiki. It also shows links between pages and can optionally provide AI answers.

kimsanguine/hplan

Plugin Claude Code

34 skills · 12 commands across 5 plugins for PMs who decide what, why, and how to build AI agents — evidence gate (hplan) → discovery → architecture → delivery → operations. Skills are consolidated via mode/check/type/step routing (e.g. prd --mode roadmap, ask-team --mode review, orchestration --pattern router), with…

kimsanguine/hplan

Instructions file

Instructions for kimsanguine/hplan, covering claude.md — hplan project rules (adk l1: memory), hplan context, 9 behavioral rules, rule 1 — think before coding and rule 2 — simplicity first.

kimsanguine/hplan

Plugin Claude Code

Architect scalable, defensible AI agent systems — orchestration patterns (Sequential, Parallel, Router, Hierarchical/3-tier 계층 오케스트레이션 포함), business models, and competitive moats. Use when designing agent architecture, choosing orchestration patterns, planning memory systems, or analyzing competitive positioning.

kimsanguine/hplan

Skill Claude CodeCodex

A two-step process for documenting a product’s visual direction and design rules. It first gathers and filters design references into a brief, then turns that direction into reusable design tokens such as colors, spacing, and typography choices.

kimsanguine/hplan

Skill Claude CodeCodex

Design an agent memory system — working memory, episodic memory, semantic memory, and procedural memory. Use when building agents that need to remember context across sessions, learn from interactions, or maintain persistent knowledge. Covers storage strategy, retrieval patterns, and context management.

kimsanguine/hplan

Skill Claude CodeCodex

Select and design the right orchestration pattern for multi-agent systems. Evaluate Sequential, Parallel, Router, and Hierarchical patterns against your use case requirements. The Router pattern covers both agent selection (classify input to the right specialist) and model selection (route tasks to the right LLM by…

kimsanguine/hplan

Skill Claude CodeCodex

A combined guide for business-model design, competitive-position analysis, and growth-loop planning for an AI product. A growth loop is a repeatable cycle in which product use helps attract users or improve the product.

kimsanguine/hplan

Plugin Claude Code

Spec, build, and ship AI agents — PRD templates (prd --mode roadmap for roadmaps), instruction design, prompt engineering, sprint planning, context budget, stakeholder mapping, build-execution scaffolding (harness-design, parallel-team worktrees, build-loop), prompt-level progress tracking (velocity, estimate, blocker.

kimsanguine/hplan

Command

A command for writing a 15-section product requirements document, or PRD, covering users, their jobs, decisions, scope, agent details, metrics, hypotheses, and quality checks. It can also create roadmaps and design variants from an existing PRD.

kimsanguine/hplan

Skill Claude CodeCodex

A setup workflow for configuring a coding agent and documenting a project for it. It can define the agent's identity, tools, limits, and failure cases, and create or improve CLAUDE.md or AGENTS.md project guidance files.

kimsanguine/hplan

Skill Claude CodeCodex

An asynchronous channel for asking people questions, collecting their replies, and connecting the results to planning work. It can use Gmail, Notion, Zoom, and Slack through connected tools, but it does not send messages automatically.