Previous Conversations
Productivityprevious-conversationsPrevious Conversations is an Agent Skill for productivity published in the boldsoftware/shelley repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use when the user references a previous conversation, asks you to continue earlier work, or you need to look up what was discussed before.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/boldsoftware/shelley/blob/HEAD/skills/builtin/previous-conversations/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/previous-conversations, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Shelley stores conversation history in a SQLite database.
First, locate the database:
DB="${SHELLEY_DB:-$HOME/.config/shelley/shelley.db}"
List recent conversations
sqlite3 "$DB" "SELECT conversation_id, slug, datetime(created_at, 'localtime') as created, datetime(updated_at, 'localtime') as updated FROM conversations ORDER BY updated_at DESC LIMIT 20;"
Get messages from a conversation
Replace CONVERSATION_ID with the actual ID:
sqlite3 "$DB" "SELECT CASE type WHEN 'user' THEN 'User' ELSE 'Agent' END, substr(json_extract(llm_data, '$.Content[0].Text'), 1, 500) FROM messages WHERE conversation_id='CONVERSATION_ID' AND type IN ('user', 'agent') AND json_extract(llm_data, '$.Content[0].Type') = 2 AND json_extract(llm_data, '$.Content[0].Text') != '' ORDER BY sequence_id;"
Search conversations by slug
sqlite3 "$DB" "SELECT conversation_id, slug FROM conversations WHERE slug LIKE '%SEARCH_TERM%';"