Canonical operational contract for Agent Orchestra session-state survival and handoffs. Use when discovering where plan, design, review, startup, calibration, tracking, or plugin…
Attempt session-memory compaction before full conversation compaction so lightweight summaries win when available.
Prevent session-memory background forks from draining teammate mailbox attachments that belong to the main lead thread.
Manages Claude Code's persistent memory system — auto-memory files, cross-session context, project memory directories, and task handoff protocols.
Tally Claude Code session token usage and cost estimates from the raw JSONL conversation log. Trigger when the user asks about session cost, token usage, API spend, cache hit…
บันทึกชื่อและเป้าหมายของ session ปัจจุบันลง memory เพื่อให้ Claude จำบริบทของการทำงานได้ตลอด session ใช้ skill นี้ทันทีเมื่อผู้ใช้ต้องการตั้งชื่อ session เช่น "ตั้งชื่อ session…
Summarize a work session from git history, diffs, and current state, then append durable notes for the next session.
Use when after you have processed raw LC-MS/MS spectral data through the specXplore importing pipeline in a Jupyter notebook and produced an in-memory specXplore session data…
Open a portfolio monitoring session across the user's connected brokers (Zerodha, Kotak Neo, and any others).
OpenClaw Session 优化器 - 监控 session 状态，在需要时提醒用户切换 session。包括 session 长度监控、已完成任务数量统计、时间显示等功能。
Build session-scoped temporary knowledge structures for multi-step projects. Use when working on complex tasks spanning turns.
Persist and restore agent sessions across conversations with state snapshots
Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into configurable waves (default 5) with optimal agent…
Use when the GM is actively running a TTRPG session and needs fast help at the table — quick lookups, rules questions, on-the-fly content generation, or capturing play notes.
Curate playlists of Fullstory sessions for team review — bundle related sessions with notes, timestamps, and context.
Use when a GM is preparing for an upcoming TTRPG session, reconciling what happened last time with what comes next, or reviewing prep plans.
過去のClaude Codeセッションを思い出すスキル。 「以前何をやったか」「過去にSESについて議論した？」「先週のセッション一覧」 「以前の作業を振り返りたい」「セッションログを確認」などの 過去のセッションや以前の作業に関する質問で自動トリガーされます。 セッション一覧の表示とキーワード検索の2つのモードがあります。
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
사용자가 "녹음시작" / "녹음 시작" / "강의 녹음" / "회의 녹음" / "전사 시작" 이라고 하거나, 실시간 강의·회의·교육 세션의 녹음과 요약을 요청할 때 사용한다. 실시간 전사와 함께 오디오 원본(m4a)도 저장한다. 실행을 멈추는 "녹음종료" / "녹음 끝" 도 이 스킬이 처리한다.
Diagnose and recover Claude Code session issues including missing conversations, corrupted sessions, and session file problems.
Red Team-granskning av sessionsförberedelser. Agerar som en fientlig granskare som aktivt letar efter hål, brister och svagheter i materialet inför en kommande spelsession.
Doctor-only. Context-refresh round: for each agent session do a retrospective (age + wide capture + interview + analytics), append a dense synthesis to the growing daily journal,…
Full cold-start resume of a harness loop from its committed handoff (invoked as /session-relay-resume, or /harness:session-relay-resume).
Full end-of-session wrap-up + handoff for a harness loop (invoked as /session-relay-wrap-up, or /harness:session-relay-wrap-up).
Convert a Claude Code session JSONL file into an animated GIF replay showing the conversation as typed terminal output.
Generate a comprehensive session report with per-model token usage (input, output, cache_read, cache_write including compaction baselines), cost breakdown via the pricing engine,…
Use when a session needs a concise report of work completed, outcomes, and follow-up state
End-of-session retrospective that mines the current conversation for learnings. Use when the user says "retro", "session retro", "what did we learn", "extract learnings", "session…
Run the end-of-session distillation by hand — capture dead ends in LESSONS.md and non-obvious choices in DECISIONS.md.
Review or checkpoint bounded SessionReviewer evidence into an accepted Markdown ledger, or resume from accepted ledger state.
Dev/arge session tipi kilidi, paralel subagent kuralları, DONE: commit zorunluluğu
Use when the user asks to save session context, identify the current session or thread, create a resumable handoff, or prepare a Todoist/note summary that must include the working…
Session-based and short-term strategies: Asian session scalping, session breakouts, scalping frameworks, breakout strategies, gap trading, grid trading, end-of-day, and swing…
For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.
Search through historical Claude sessions for code, conversations, and commands. Use when user asks about previous sessions, past conversations, "did I ever", "find in history",…
Analyze agentic coding sessions to discover friction patterns and generate skills, rules, and hooks. Use when running /insight across multiple sessions or optimizing AI assistant…
Compacts an entire chat into a dense markdown summary that restores ~80% of context when pasted into a new chat.
Use at the start of bug-fix/feature sessions. State primary deliverable (file + behavior) before code; time-box CI gate work to 30 min.
Internal skill for harness-work phase boundary management. Auto-triggered by orchestration.
Persistent session state management across compaction and restarts via lifecycle hooks
Summarize current Claude Code session with todo/plan state, key decisions, and blockers for pasting into fresh session
Summarise the current session in Japanese. Use when finishing a session, handing off work, or wanting a recap of what was discussed and accomplished.
Quick-sync session work to specs/*.md and project-tech.json
Name and classify the current AI work session, save its source-attributed handoff, and route it to checkpoint or close-out.
Track session end-time as a hard budget and run the ADR-0014 end-of-day cleanup (MEMORY save / WIP commit / push / handoff). Use at multi-step kickoff.
Render an ordered timeline of one Claude Code session's events (every event type) with per-event durations and tool names, reconstructed from Agent Monitor data.
Build timeout-resistant Claude Code workflows with chunking strategies, checkpoint patterns, progress tracking, and resume mechanisms to handle 2-minute tool timeouts and ensure…
Check how long the current session has been running. Use when asking about session length, duration, "how long have I been at this", "how long have I been working", whether it's…
Auto-extract a reusable skill from the current session conversation. Use when the user says "save this as a skill", "turn this into a skill", "I want to reuse this workflow",…
Use when the user asks about past sessions, session history, what was worked on previously, previous conversations, or wants context from prior Claude Code sessions in this…
Decide whether to open a Mission + Run based on session signals (turns, debug keywords, tool failures). Open, observe, record-tool.
Run a focused N-question study session on a subject — SQE1-style MCQ, essay, or flashcards. Tracks performance and updates the study plan.
Track progress with timestamps, git status, and todo list updates in current session
Run the session-end wiki update checklist from project-knowledge/AGENTS.md. Updates wiki pages, appends to log.md, creates a weekly summary if needed, and refreshes index.md.
Manage conversation sessions across Claude, Codex, Gemini, Grok, and Mistral. Use for multi-turn conversations, session switching, workspace management.
Analyze recent Codex session evidence for repeated manual workflows and route them to skills, subagents, validators, or no artifact when Jamie asks what he keeps doing manually.
Automatic session work journal maintained in auto-memory. Records tasks, decisions, and pending items at session end or after significant work blocks.
Wrap up a conversation session before starting a new one. Use when the user says "wrap up", "wrap up this conversation", "session wrap up", or uses /session_wrap_up command.
Use when a TTRPG session has just ended and the GM needs to process what happened — generating recaps, updating entity files, recording timeline events, and identifying what…
End-of-session ritual — reflects on what happened, stores a structured session summary to the correct department Brain, updates the Master Dashboard, updates the Master Brain…