Skip to main content
skill CX Codex

context-layer-dreaming — Claude Code skill: what it does and install

The context-layer-dreaming Claude Code skill turns recent organizational activity into lasting context wiki updates. It runs for nightly or incremental refreshes based on completed work and other activity.

no license 148 installs ★ 101 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add PostHog/ai-plugin --skill context-layer-dreaming -a claude-code
Open on GitHub

What context-layer-dreaming does

The skill updates a mounted context wiki with durable facts drawn from recent organizational activity. It reviews Spaces channels, completed tasks, merged pull requests, finished loop runs, and new event or property definitions. Test, demo, abandoned, and unfinished tasks do not count as evidence of organizational decisions.

Before editing, it checks each candidate against the existing page and adds only facts that change durable context. Markdown edits are confined to org/, areas/, decisions/, and existing projects/<project-id>/spaces/ pages. It must leave AGENTS.md, CLAUDE.md, indexes, and scripts/ untouched. The setup requires a mounted wiki with scripts/lint and scripts/publish, plus access to the context layer API.

After validation, the skill writes a run summary to /tmp/dream-summary.md and starts publication. Only publish: landed confirms success; a nonzero exit means the publication failed.

What it helps with

  • turn completed task outcomes into lasting wiki entries
  • refresh context from activity in public Spaces channels
  • filter out test and demo material
  • find wiki gaps that blocked an agent

Example prompts for the agent

  • Run a nightly context wiki refresh from recent organizational activity.
  • Update the context wiki from completed tasks and merged pull requests since the last run.
  • Review recent task conversations for cases where the wiki failed to provide needed context.

How to install context-layer-dreaming

1Skills CLI (Vercel)

npx skills add PostHog/ai-plugin --skill context-layer-dreaming -a claude-code

2Manually: put the files in place

~/.claude/skills/context-layer-dreaming/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/context-layer-dreaming/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about context-layer-dreaming

How do I install context-layer-dreaming in Claude Code?

Run npx skills add PostHog/ai-plugin --skill context-layer-dreaming -a claude-code. The skill file is installed at ~/.claude/skills/context-layer-dreaming/SKILL.md.

What does context-layer-dreaming do?

It selects durable facts from recent organizational activity and uses them to update a mounted context wiki. It validates the edits and prepares a run summary before publishing.

What does context-layer-dreaming need to run?

It needs a mounted context wiki with scripts/lint and scripts/publish, access to activity sources, and the context layer API to send the changes.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set82

The whole set →
creating-box-plot-insights The creating-box-plot-insights Claude Code skill builds box plot insights in PostHog from product analytics or SQL. It runs on requests to chart a numeric distribution, compare medians, or save an insight. CX Codex +1 148installs exploring-mcp-tool-original-user-motive The exploring-mcp-tool-original-user-motive Claude Code skill builds a taxonomy of the goals users had before reaching an MCP tool. It groups session openings and publishes the categories in a PostHog notebook. CX Codex +1 148installs context-layer-consolidation The context-layer-consolidation Claude Code skill keeps a context wiki coherent by working through a deterministic lint report queue. It handles the queue before dream publisher creates its branch and commit. CX Codex +1 148installs building-react-quill-canvases building-react-quill-canvases — a Claude Code skill for building PostHog canvases with React and Quill. It activates when building-canvases routes a dashboard, form, or tool request to a React implementation. CX Codex +1 148installs validating-and-publishing-canvases The validating-and-publishing-canvases skill for Claude Code checks PostHog Canvas source projects and publishes them with version guards. It verifies declared capabilities and handles merge conflicts without data loss. CX Codex +1 148installs analyzing-task-runs analyzing-task-runs — a Claude Code skill that breaks down a completed task run from its log and records the activities. It starts when asked to analyze a run or review an attached log. CX Codex +1 148installs review-hog-resolution-criteria The review-hog-resolution-criteria Claude Code skill resolves open pull request review comments. It makes verifiable changes, explains declines, and hands risky decisions to a person. CX Codex +1 148installs working-with-scouts The working-with-scouts Claude Code skill helps manage PostHog Signals scouts that watch a project and send reports to the Signals inbox. Assign monitoring tasks, review findings, and steer the scouts with feedback. CX Codex +1 148installs

Project sponsors

Companies that keep this analytics open