CLI tool to explore and inspect past Claude Code and Codex conversation histories. Use this skill when: - You need to catch up on a previous conversation that ran out of context - You want to review what was discussed or accomplished in past sessions - You need to search across conversation history for specific topics - You want to generate a summary of past work to paste into a new session - The user asks about their Claude Code or Codex conversation history - The user wants to resume work from a previous session and needs context --- # Agent History CLI A unified tool to explore past Claude Code (`~/.claude/projects/`) and Codex (`~/.codex/sessions/`) conversations from a single interface. ## Installation ```bash pip install agent-history # Install the skill (default: ~/.claude/skills/) agent-history install-skill ``` ## Source Tagging
Complete GitHub workflow for Claude Code on the web. ALL GitHub operations MUST use REST API (never gh CLI). Includes branch naming (claude/*-sessionId), push retry logic, PR/issue management via API, and complete workflows. Use for all GitHub interactions in Claude Code web environment.
Launch Claude Code via mclaude in headless (non-interactive) mode, bypassing the TUI. Use this skill when the user asks to run Claude Code with a specific provider, when automating Claude Code invocations, or when scripting with mclaude. Also use when the user asks how to use mclaude from the command line without the TUI, or wants to know available providers and models.
每日复盘。根据 Claude Code 本地对话记录，生成结构化的每日工作复盘报告。支持当天、昨天、近 3 天、近 7 天。 当用户说"复盘"、"agent review"、"/agent-review"、"/复盘"时触发。 --- # 每日复盘 ## 启动横幅 技能启动时，**必须**在执行任何操作之前，先输出以下横幅： ``` ═══════════════════════════════════════════════════════════════ ▌ 每日复盘 ▐ 根据 Claude Code 本地对话记录，生成结构化的每日工作复盘报告 ═══════════════════════════════════════════════════════════════ 磊叔 │ 微信：AIRay1015 │ github.com/akira82-ai ─────────────────────────────────────────────────────────────── - 支持 4 种时间范围：今天 / 昨天 / 近 3 天 / 近 7 天 - 自动提取对话记录、工具调用统计、Git 提交记录 - 生成结构化报告：概要 / 工作量统计 / 成功与进展 / 困难与卡点 / AI 自评 - 报告自动保存至当前工作目录 ═══════════════════════════════════════════════════════════════ ``` ## 参数处理 如果用户没有指定时间范围，用 AskUserQuestion 询问，选项为： - 今天 - 昨天 - 近 3 天 - 近 7 天 不提供其他选项。根据用户选择，计算对应的日期范围（当天、前 1 天、前 3 天、前 7 天），时间戳使用 UTC 时区。 ## 数据提取步骤 ### 第 1 步：从 history.jsonl 获取消息列表 用 Bash 执行 Python 脚本，读取 ~/.claude/history.jsonl，按时间戳筛选指定日期范围内的所有记录。 每条记录包含：display（用户输入内容）、timestamp（Unix 毫秒）、project（项目路径）、sessionId。 统计精确的消息条数。 如果选择了多天（近 3 天、近 7 天），按天分别统计。 ### 第 2 步：获取涉及的 session 列表 从第 1 步中提取不重复的 sessionId 和对应的项目路径。 ### 时间戳格式说明（重要） 两个数据源的时间戳格式不同，脚本中**必须**统一处理： 1. `history.jsonl` 的 timestamp 字段是 **int**（Unix 毫秒），如 `1770288337219` 2. 项目 JSONL 文件的 timestamp 字段是 **ISO 8601 字符串**，如 `"2026-03-31T04:24:20.514Z"` 在脚本开头定义统一的解析函数： ```python def to_ms(ts): if isinstance(ts, (int, float)): return ts if isinstance(ts, str): dt = datetime.datetime.fromisoformat(ts.replace('Z', '+00:00')) return int(dt.timestamp() * 1000) return 0 ``` 后续所有时间戳比较和过滤都使用 `to_ms()` 转换后再比较。 ### 第 3 步：从项目 JSONL 文件中提取详细内容 使用技能自带的 `extract.py` 脚本提取数据，确保时间戳处理稳定可靠。 **调用脚本**： ```bash python ~/.claude/plugins/marketplaces/airay-skills/skills/airay-agent-review/scripts/extract.py --start_ms <start_ms> --end_ms <end_ms> ``` **脚本返回的数据结构**： ```json { "sessions": [...], "total_messages": N, "tool_calls": {"Bash": 36, "Read": 2, "Write": 2, ...}, "tool_errors": {...}, "files_touched": ["path/to/file1", "path/to/file2", ...], "projects": ["/path/to/project1", "/path/to/project2"], "user_messages":
- 📄 com.cc-books.daily.plist
- 📄 daily-cron.sh
- 📄 generate.sh
今日のClaude Codeセッションログから振り返り本（FlipBook）を自動生成して開く
Create an empty Claude plugin with basic structure and files.
Persistent memory for Claude across conversations. Use when starting any task, before writing or editing code, before making decisions, when user mentions preferences or conventions, when user corrects your work, or when completing a task that overcame challenges. Ensures Claude never repeats mistakes and always applies learned patterns.
Check and act on Apple Reminders — reads Claude Inbox for pending tasks and Claude Output for results. Automatically dispatches agents for new inbox items. Use when user says /reminders, "check reminders", "what came in", or to start the watcher via /loop.
Reference note for the Claude Code adapter surface; the active Claude bootstrap now lives in `/.claude-plugin`, `/hooks`, and the repository `skills/` directory.
- 📁 agents/
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Vibe Memory，简称 vbm。用于为 Codex 与 Claude Code 初始化 .ai 项目记忆层、追加受控规则、启用全局引导，并在开发任务中读写已验证记忆。
Scan running Claude sessions to see what other agents are working on. Use when asked "what are the other agents doing", "check other sessions", "what's running", "scan agents", "who's working on what", or before picking up new work to avoid overlap. --- # Agents: Scan Running Claude Sessions Runs `scan.sh` to inspect all tmux sessions running Claude and report what each is doing. ## Usage ```bash bash ~/.claude/skills/agents/scripts/scan.sh # all sessions bash ~/.claude/skills/agents/scripts/scan.sh floom # only floom/* sessions bash ~/.claude/skills/agents/scripts/scan.sh openpaper # only openpaper/* sessions ``` ## What It Shows
- 📁 scripts/
- 📄 README.md
- 📄 SKILL.md
Check context usage and session info for any Claude Code session. Use when the user asks about context usage, token count, session info, or wants to list/inspect Claude sessions.
