Skill

knowledge-base

Deep knowledge layer - project-specific library quirks, stack recipes, dependency notes. Auto-loaded when working with knowledge files or when implement/debug discovers something worth preserving.

npx claudepluginhub littlelingo/context-engine --plugin context-engine

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Project-specific technical knowledge that persists across sessions. Three tiers:

SKILL.md

Similar Skills

cache-components

139.3k

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

canvas-design

124.2k

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

20 files

anthropics-skills-13

Stats

Stars1

Forks0

Last CommitMar 29, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Deep Knowledge Layer

Project-specific technical knowledge that persists across sessions. Three tiers:

Storage Structure

.context/knowledge/
  LEARNINGS.md              Quick insights (2-3 sentences each)
  libraries/                Per-library deep reference
    TEMPLATE.md             Copy for new libraries
    [library-name].md       Quirks, workarounds, patterns
  stack/                    Integration recipes
    TEMPLATE.md             Copy for new recipes
    [recipe-name].md        Multi-tool config patterns
  dependencies/
    PINS.md                 Version pins and upgrade blockers

When to Capture (Hybrid Model)

Auto-Capture (implement + debug phases)

The implementer and debugger agents write to knowledge automatically when they:

Discover a library behaves unexpectedly (-> libraries/[name].md)
Find a version-specific bug or incompatibility (-> dependencies/PINS.md)
Resolve a bug caused by tool integration (-> stack/[recipe].md)
Hit any "aha moment" that took > 5 minutes to figure out (-> LEARNINGS.md)

Manual Capture (research + plan phases)

Use /learn to manually route knowledge:

/learn library quirk: React Query v5 onSuccess removed, use onSettled
/learn stack recipe: Next.js + Prisma + tRPC setup
/learn dependency pin: Tailwind pinned to 3.x, 4.x breaks PostCSS
/learn insight: Our API rate limiting needs per-user, not per-IP

How to Read Knowledge

Before implementing or debugging, check relevant knowledge:

LEARNINGS.md - scan for relevant quick insights
libraries/[name].md - if working with a specific library
stack/[name].md - if touching an integration point
dependencies/PINS.md - before upgrading or adding dependencies

Promotion Rules

Quick insight in LEARNINGS.md that grows to 5+ lines -> promote to libraries/ or stack/
Same library appearing 3+ times in LEARNINGS.md -> create dedicated libraries/[name].md
Copy from TEMPLATE.md when creating new deep reference files

Knowledge vs Other .context/ Files

What	Where	Why
Error signatures + fixes	`.context/errors/`	Greppable by exact error text
Code conventions	`.context/patterns/`	Style rules, not library-specific
Architecture decisions	`.context/decisions/`	"We chose X over Y because..."
Library quirks	`.context/knowledge/libraries/`	"X behaves unexpectedly when..."
Config recipes	`.context/knowledge/stack/`	"To set up X + Y together, do..."
Version constraints	`.context/knowledge/dependencies/`	"Pinned to vX because..."
Quick insights	`.context/knowledge/LEARNINGS.md`	Everything else worth remembering