resume-claude-herelisted

Recover a prior Claude Code session from natural-language hints, search Claude history by topic/date/project, and import the useful context into the current conversation. Use this for Claude session handoff, transcript recovery, context transfer into Codex or another agent, and continuing after Claude hit a usage or rate limit.
bayeslearner/bayeslearner-skills · ★ 0 · AI & Automation · score 65

Install: claude install-skill bayeslearner/bayeslearner-skills

# Continue Claude Here Use this skill when the user wants to pull forward prior Claude work into the current conversation. Primary outcome: - import the relevant prior session context into the current conversation without switching runtimes Keep the workflow deterministic. Do not guess a session from vibes alone when there are several plausible candidates. Default bias: - Always prefer importing the prior Claude session into the current conversation. - Treat true Claude reopen or CLI resume as an edge path only if the user explicitly insists on that. ## Tools - Use `scripts/claude_session_tool.py search` to discover and rank candidate sessions. - Use `scripts/claude_session_tool.py export` to preview or stage transcript content. - Use the local `claude` CLI only if the user explicitly asks to reopen Claude itself. Read [research-notes.md](./references/research-notes.md) only if you need the exact CLI/session behavior that motivated this workflow. ## Workflow ### 1. Classify the user's intent Pick the primary mode first: - `import-into-current`: The user wants the current conversation to absorb the prior context. - `unclear`: Search first, then ask one concise question only if the top candidates are ambiguous. Unless the user explicitly asks to reopen Claude itself, treat all of these as `import-into-current`: - "continue" - "resume" - "pick up where we left off" - "bring that chat here" - "import the transcript" - "Claude hit the limit" ### 2. Search sessions