Skills for Real Engineers. Straight from my .agents directory.
39 skills
context-engineering
Agent skill from
Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on demand, sizing an install or an always-loaded file, fixing an agent that drifts, repeats itself, or forgets constraints mid-task, planning compaction or summarization, deciding single-agent versus subagents, engineering handoffs between agents, or picking a tool loadout. NOT for rewording a prompt's tone, choosing which model to pin, or debugging business logic — those are adjacent moments this skill does not serve. Historical 2024–2025 snapshot; not normative for present-day frontier models — see the Status section.
How to install context-engineering
install context-engineering
# install the openrig pack with the skills CLI
npx skills add mvschwarz/openrig# or add only this skill to Claude Code: copy the folder
skills/_canonical/process/context-engineering/
# into
~/.claude/skills/context-engineering/ (all projects)
.claude/skills/context-engineering/ (one project)
1# Traditional Context Engineering — 2024–2025 Snapshot23## Status: provisional historical research snapshot45This skill is a provisional historical research snapshot of context-engineering practice as6published in 2024–2025. It is NOT normative. Do not apply it prescriptively to current frontier7models without re-verification. On any conflict, OpenRig current skills, explicit user rulings,8and directly measured OpenRig practice PREVAIL over this document. Treat these areas as9particularly suspect pending re-verification: compaction/summarization guidance, minimal-upfront10versus broad orientation, just-in-time lookup assumptions, fixed context ceilings, and11single-agent versus multi-agent advice.1213Curated distillation of the best publicly available expertise on context engineering for coding14agents, drawn from primary sources at Anthropic, OpenAI, and leading practitioners (Manus,15Cognition, Chroma, LangChain, Drew Breunig, and others). Load on the moments the description16names; it is deliberately not part of any base walk.1718---1920## 1. The mental model: what context engineering is2122**Definition.** Context engineering is "the set of strategies for curating and maintaining the23optimal set of tokens (information) during LLM inference" — everything that lands in the window:24system instructions, tool definitions, retrieved data, message history, and tool outputs, not25just the prompt text (Anthropic, *Effective context engineering for AI agents*). Andrej26…
Excerpt shown under the repository's Apache-2.0 license.
More skills in openrig
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills