Back to list
FWFsoft

remember

by FWFsoft

A game engine for developing 2D isometric ARPG and RTS games

0🍴 0📅 Jan 23, 2026

SKILL.md


name: remember description: Search through past conversation histories to recall previous discussions, decisions, and context. Use when you need to reference what was discussed or decided in previous sessions.

Conversation History Search

Search through past conversation histories stored in ~/.claude/projects/*/*.jsonl to help recall previous discussions, decisions, code explanations, and context from earlier sessions.

Instructions

  1. Run the search command with a query string:

    uv run python .claude/skills/remember/remember.py "<query>"
    
  2. Optionally include agent conversations (sub-tasks):

    uv run python .claude/skills/remember/remember.py "<query>" --include-agents
    

Features

  • Searches both user and assistant messages
  • Finds discussions about specific topics, features, or files
  • Shows conversation context with timestamps
  • Groups results by session for easy navigation
  • Sorts by recency (most recent first)
  • Skips agent conversations by default (use --include-agents to include them)
  • Case-insensitive substring matching

Examples

Search for discussions about networking:

uv run python .claude/skills/remember/remember.py "networking"

Find conversations about a specific file:

uv run python .claude/skills/remember/remember.py "DESIGN.md"

Look for combat system discussions:

uv run python .claude/skills/remember/remember.py "combat system"

Search including agent conversations:

uv run python .claude/skills/remember/remember.py "ENet" --include-agents

When to Use This Skill

  • Need to recall why a design decision was made
  • Want to find previous discussions about a feature
  • Looking for context about how something was implemented
  • Trying to remember what was decided in a past conversation
  • Need to reference code explanations from earlier sessions

Notes

  • Searches conversation histories in ~/.claude/projects/*/
  • By default, excludes agent conversations (background tasks)
  • Results are truncated to 200 characters for readability
  • Shows file path and line number for reference
  • Groups results by session to see conversation flow
  • Displays up to 50 most recent matches by default

Score

Total Score

50/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon