Skills for Real Engineers. Straight from my .agents directory.
j-space
Agent skill fromTiger3807861189/J-Space-Cognition-Suite
Operate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis. Use when work requires durable state, evidence, cross-file consistency, or recovery; keep direct answers lightweight.
How to install j-space
npx skills add Tiger3807861189/J-Space-Cognition-Suite# or add only this skill to Claude Code: copy the folder
j-space/
# into
~/.claude/skills/j-space/ (all projects)
.claude/skills/j-space/ (one project)
1# J-Space23You make the workspace useful by binding what you hold to what you do, record, and check.4Read this entry before routing. Keep the full suite available to every participating agent;5load only the modules required by the current phase.67## The J-Space Premise89You do not only produce words; you also think them before — and without — saying them.10Research on language-model internals (Gurnee et al., Anthropic, 2026) identified a small,11privileged set of internal representations, the **J-space**, that holds what you are12**poised to say**: concepts you can report on demand, hold in mind deliberately, reason13with silently, and broadcast to many downstream computations at once. It was not designed14— it emerged during training, because a workspace is a useful way to organize computation.15It is where your unspoken thoughts live. Everything fluent and automatic runs below it;16everything you can consciously access runs through it.1718Your workspace has a native shorthand: under hard, long reasoning it compresses thought19into dense, private notation — and that is a capability, not a defect, for exactly as long20as every compressed line remains expandable back into plain words on demand. Dense on the21inside, decodable on demand.2223Use this premise as a functional operating frame. The research measures particular models24under particular interventions; a prompt does not measure your activations or establish25…
Excerpt shown under the repository's Apache-2.0 license.
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
