메뉴
Find or reference a past Claude Code conversation — fixes, decisions, or discussions from earlier sessions ("you helped me fix", "we debugged", "I remember asking"). Locate sessions by topic, file, or date. Not for codebase/git/Slack history.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Control macOS UI via the Accessibility API and record short screen captures reviewed frame-by-frame. Use when automating native apps — clicking buttons, filling forms, reading element state, finding elements, getting window bounds — or when the user wants a short screen recording of an animation/transition/flicker reviewed via a contact sheet, optionally pushed to a vitrinka board. Triggers on "click button in app", "fill form in native app", "automate macOS app", "list UI elements", "find button", "read text field value", "get window position", "interact with native app", "record the screen", "capture this transition", "Xs recording", "Nfps", "watch this animation", "why does it jump/flicker", "record this app for a few seconds", "push the recording to a board".
Drive a real, extension-loaded Chrome/Brave browser for the GenesisTools YouTube extension via chrome-devtools-mcp as a standalone MCP client — no Claude Code config edits, no restart. Use whenever the user wants to test, debug, screenshot, or click through the YouTube extension's UI (side panel tabs, popup, content script), asks to "load the extension and click X", wants a screenshot of the extension mid-interaction, or needs to find exact pixel coordinates to click something inside a web page (not a native macOS app — for that, use the screen-capture skill instead). Also use this whenever chrome-devtools-mcp's own tools are attempted and fail with "no browser" or launch a blank vanilla browser with no extension loaded — that means the server wasn't wired to a real browser, and this skill is the fix.
Cross-agent messaging protocol via `tools agents`. Use when the main agent is about to spawn subagents that should be able to message each other (or back to the main agent) during their work. Teaches the login (auto-registers) / message / discover / listen pattern, the stream-vs-once receive modes, and the no-loss delivery contract.
Empirically evaluate and trim ANY agent-instruction file — user/project CLAUDE.md, CLAUDE.local.md, AND AGENTS.md (the cross-tool standard read by Codex, Cursor, Gemini CLI) — to find rules a clean model already knows, rules the repo/hooks already enforce, and internal duplication, then propose evidence-backed cuts. Autodetects which files exist and which the harness actually loads, runs headless claude with ALL instruction files EXCLUDED (verified by canary) against MULTIPLE models, and classifies every rule KEEP/SHRINK/CUT with a multi-provider rubric. Use when the user says "improve agents.md", "evaluate agents.md", "trim CLAUDE.md", "improve claude md", "is my CLAUDE.md bloated", or "/improve-agents-md [path]".
Create and maintain a compaction-proof progress file (.claude/plans/<plan>.handoff.md) next to an implementation plan, so any executor - fresh session, post-compact resume, or parallel subagent - knows exactly where the work stands and which plan lines to read next. Invoke when starting to execute a plan, when resuming one, when handing work to another agent, or when the user says "create a handoff" / "prepare the handoff".
Write comprehensive implementation plans (subsumes writing-plans - bite-sized TDD tasks, exact paths, complete code) hardened with an executor-proof contract - all judgment spent at plan time, REASON/VERIFY/ON-FAIL per task, no-improvisation covenant - so even the weakest model executes to strong-model-quality output. Invoke INSTEAD of writing-plans whenever the plan may be executed by another session, subagent, or weaker model.
| name | gt:claude-history |
| description | Find or reference a past Claude Code conversation — fixes, decisions, or discussions from earlier sessions ("you helped me fix", "we debugged", "I remember asking"). Locate sessions by topic, file, or date. Not for codebase/git/Slack history. |
Search through Claude Code conversation history to find past interactions.
# Basic search
tools claude history "keyword"
# Search with filters
tools claude history "query" --tool Edit --since "7 days ago"
# Interactive mode
tools claude history -i
tools claude history "backup mcp-manager refactor"
tools claude history "authentication bug" --exact
tools claude history --file "config/api.php"
tools claude history --file "*.tsx" --tool Edit
tools claude history --tool Edit --since "7 days ago"
tools claude history --tool Task --limit 50
tools claude history "timer" --project GenesisTools
tools claude history "migration" --all # Search all projects
tools claude history "timer" --context 10 # 10 messages before/after
| Option | Description |
|---|---|
-i, --interactive | Interactive mode with autocomplete |
-p, --project <name> | Filter by project name |
--all | Search all projects |
-f, --file <pattern> | Filter by file path pattern |
-t, --tool <name> | Filter by tool (Edit, Write, Bash, etc.) |
--since <date> | Since date (e.g., "7 days ago", "yesterday") |
--until <date> | Until date |
-l, --limit <n> | Limit results (default: 20) |
-c, --context <n> | Show N messages before/after match |
--exact | Exact match instead of fuzzy |
--regex | Use regex for query |
--agents-only | Only search subagent conversations |
--exclude-agents | Exclude subagent conversations |
--exclude-thinking | Exclude thinking blocks |
--reindex | Rebuild search index (use when index seems stale or after manual edits) |
--format <type> | Output: ai (default), json |
Default (ai): Perfect markdown with summaries and file paths With --context: Shows surrounding messages in markdown JSON: Raw JSON for programmatic use
Summarize Claude Code sessions using LLM-powered templates. Extracts key information and produces structured output in 7 modes.
# Interactive mode — guided session & mode selection
tools claude history summarize -i
# Summarize a specific session
tools claude history summarize <session-id> --mode documentation
# Summarize current session (inside Claude Code)
tools claude history summarize --current --mode short-memory
# Output prompt only (no LLM call)
tools claude history summarize <session-id> --prompt-only --mode changelog
| Mode | Description |
|---|---|
documentation | Full technical doc: problem, changes, patterns, lessons |
memorization | Comprehensive learnings organized by topic tags |
short-memory | Concise MEMORY.md-ready bullets (500-2000 chars) |
changelog | Added/Changed/Fixed/Removed with file paths |
debug-postmortem | Symptoms, investigation, dead ends, root cause, fix |
onboarding | "How this works" for new devs: architecture, key files |
custom | Your own prompt with session content |
| Option | Description |
|---|---|
-s, --session <id> | Session ID (repeatable) |
--current | Use current session from $CLAUDE_CODE_SESSION_ID |
--since <date> | Sessions since date |
--until <date> | Sessions until date |
-m, --mode <name> | Template mode (default: documentation) |
--model <name> | LLM model name |
--provider <name> | LLM provider name |
--prompt-only | Output the prepared prompt without calling LLM |
-o, --output <path> | Write output to file |
--clipboard | Copy output to clipboard |
--thorough | Chunked summarization for large sessions |
--max-tokens <n> | Token budget (default: 128000) |
--include-tool-results | Include tool execution results |
--include-thinking | Include thinking blocks |
--priority <type> | Content priority: balanced, user-first, assistant-first |
-i, --interactive | Interactive guided flow |
--custom-prompt <text> | Custom prompt (for custom mode) |
--memory-dir <path> | Output dir for memorization topic files |
# Generate onboarding docs from a session
tools claude history summarize abc123 --mode onboarding -o docs/onboarding.md
# Extract debug learnings
tools claude history summarize abc123 --mode debug-postmortem --clipboard
# Memorization with topic files
tools claude history summarize abc123 --mode memorization --memory-dir ./memory/
# Large session with chunked processing
tools claude history summarize abc123 --mode documentation --thorough
# Custom analysis
tools claude history summarize abc123 --mode custom --custom-prompt "List all API endpoints discussed"
# Use specific model
tools claude history summarize abc123 --mode short-memory --provider anthropic --model claude-sonnet-4-5-20250929
For visual exploration, tools claude history dashboard launches a web-based React/Vite interface for browsing and analyzing conversation history.