메뉴
Search past conversations with Claude Code and Codex CLI. Finds matching excerpts across all sessions with metadata (date, project, agent). Use when looking for a past discussion, decision, or piece of context from any previous session.
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
Generate EXECUTION_PLAN.md and scoped AGENTS.md files for a feature. Use after /feature-technical-spec to create the task breakdown.
Generate the greenfield execution plan plus root and scoped AGENTS.md files. Use after /technical-spec to create the phased task breakdown.
Guide discovery and discussion to determine how an AI coding agent can autonomously run and verify a specific user flow end to end. Use when the user asks what would be needed to test a flow, prove an app works, create an E2E/self-test harness, make agent verification repeatable, or evaluate whether an existing test setup lets the agent verify behavior. This skill is for shaping the verification approach before implementation: read the repo's product docs and existing verification contracts, identify the real user flow and channel under test, uncover missing controllable state or external dependencies, ask focused questions, and produce a concrete agent-runnable verification plan only after the flow is understood.
Exploratory conversation before /product-spec. Asks one question at a time, runs background research for open-source/off-the-shelf alternatives, and writes DISCOVERY_NOTES.md. Use when the user has an idea but hasn't scoped it yet.
Define feature requirements (problem, users, scope, acceptance criteria) through guided Q&A and write FEATURE_SPEC.md. Use when starting a new feature.
Define technical approach (architecture, integration points, data model) for a feature through guided Q&A and write FEATURE_TECHNICAL_SPEC.md. Use after /feature-spec.
| name | search-chats |
| description | Search past conversations with Claude Code and Codex CLI. Finds matching excerpts across all sessions with metadata (date, project, agent). Use when looking for a past discussion, decision, or piece of context from any previous session. |
| argument-hint | <query> [--agent claude|codex] [--project <name>] [--days <N>] |
| allowed-tools | Read, Bash, Glob |
Search past conversation transcripts across Claude Code and Codex CLI sessions.
@shared/SESSION_PARSING.md
Parse the user's input for:
--agent claude|codex — restrict to one agent (default: both)--project <name> — filter to sessions whose project path contains this string--days <N> — only search sessions modified in the last N days (default: 30)Use Bash to find JSONL files, filtered by recency:
# Claude Code sessions
find ~/.claude/projects -name "*.jsonl" -not -path "*/subagents/*" -mtime -${DAYS} -type f
# Codex CLI sessions
find ~/.codex/sessions -name "*.jsonl" -mtime -${DAYS} -type f
If --project is set, pipe through grep -i "<project>" to filter paths.
If --agent is set, skip the other source entirely.
For each session file, use Bash with grep -i to check if the query appears before reading the full file.
Only parse files that match.
For matched files, read and extract:
Claude Code files:
-Users-ben-shoemaker-Projects-myapp → myapp)timestamp field from first user event, or file mtimeclaudeCodex CLI files:
session_meta.payload.cwd basenamerollout-YYYY-MM-DDTHH-MM-SS-...codexSort results by date (newest first). For each match:
## [DATE] PROJECT (AGENT)
Session: SESSION_ID
> **User:** [matching user message excerpt]
> **Assistant:** [matching assistant response excerpt]
---
Truncate long messages to ~300 chars with ... continuation marker.
If no results found:
No matches for "QUERY" in the last DAYS days.
Try broadening the search: fewer keywords, more days (--days 90), or drop the project filter.
End with a one-line count: Found N matches across M sessions.