← ClaudeAtlas

chat-session-briefinglisted

Maintain continuity across multi-session projects in a chat interface (claude.ai web or desktop) using a single structured markdown session briefing. Use this skill whenever the user is working on a project that spans multiple conversations, whenever they ask to create or update a session briefing, project status document, or context handoff note, or whenever they mention resuming work from a previous session. Also trigger when the user starts a new multi-step project and needs a system for tracking progress across sessions — even if they don't explicitly say "session briefing." If the user references prior sessions, version histories, or asks to "pick up where we left off," this skill applies. Covers both creating the first briefing for a new project and updating an existing one. For coding agents that run in a repo with a context file (AGENTS.md/CLAUDE.md) and git, use agent-session-briefing instead.
CaptCanadaMan/session-briefing · ★ 0 · AI & Automation · score 70
Install: claude install-skill CaptCanadaMan/session-briefing
# Chat Session Briefing A system for maintaining project continuity across Claude sessions. Session briefings are structured documents that serve as the primary source of truth when resuming work — they tell a fresh Claude instance everything it needs to know to be productive immediately. This is the **chat variant** — for claude.ai (web or desktop), where there's no repo, no `CLAUDE.md`/`AGENTS.md`, and no git, so the briefing is a single self-contained markdown document that holds everything. (For a coding agent that runs in a repo with a context file + git, use `agent-session-briefing` instead — it offloads timeless reference to the context file and adds a cross-project *constellation* rollup.) ## Why this matters Claude has no memory between sessions. Without a well-maintained briefing, every new session starts cold — context is lost, decisions get revisited, work gets duplicated, and downstream effects get missed. A good session briefing eliminates this. It is the project's institutional memory. ## Two modes This skill operates in two modes: 1. **Cold start** — The user is beginning a new multi-session project. Create the first briefing document (v1.0) by interviewing for context, then producing a structured doc. 2. **Continuation** — The user has an existing briefing. When updating, follow the carry-forward rules precisely and produce an incremented version. Detect which mode applies from context. If the user loads a briefing document or references a prio