菜单
Use when the user wants to review an opencode session for quality — analyzes a specified session (or the most recent non-active one) for prompting effectiveness, agent performance, and environment gaps, producing actionable recommendations
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | review-session |
| description | Use when the user wants to review an opencode session for quality — analyzes a specified session (or the most recent non-active one) for prompting effectiveness, agent performance, and environment gaps, producing actionable recommendations |
Review a single opencode session transcript for quality and produce actionable findings.
opencode CLI must be available on PATH (provides opencode session list and opencode export).ed3d-conversation-reviewer agent and the writing-opencode-directives skill must be available (the reviewer loads that skill).scripts/reduce-transcript.py (its absolute path is shown in the file list when this skill loads).The user may ask to:
ses_…) or by titleList the current project's sessions:
opencode session list
Session IDs match ses_[A-Za-z0-9]+.
Never export the active session — a session still being written can truncate mid-write. The active session is the most recently updated one (its title matches the running conversation).
Export the session, then run scripts/reduce-transcript.py (shipped with this skill; its absolute path is shown in the file list when this skill loads) to produce a token-efficient version:
mkdir -p /tmp/session-review
opencode export <sessionID> > /tmp/session-review/session.json
python3 scripts/reduce-transcript.py /tmp/session-review/session.json /tmp/session-review/reduced.txt
Tell the user you're reducing the transcript for analysis.
Create a temporary output path for findings:
/tmp/session-review/findings.md
Dispatch the ed3d-conversation-reviewer agent with:
task:
subagent_type: ed3d-conversation-reviewer
description: Review session transcript
prompt: |
Review the reduced opencode session transcript.
Transcript path: /tmp/session-review/reduced.txt
Write your findings to: /tmp/session-review/findings.md
Read the transcript, analyze it, and write your findings following your output format.
Once the reviewer completes, read /tmp/session-review/findings.md and present the findings to the user.
Present the full findings — do not summarize or truncate. The reviewer has already calibrated the length to be proportional to what's interesting.
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic review subagents, and a final Summarizer subagent with task tracking and failure recovery
Use to decide what kind of basic agent you should use
Use when creating a new opencode plugin or setting up plugin structure - provides complete file organization, manifest format, and component definitions for commands, agents, skills, hooks, and MCP servers
Use when creating specialized subagents for opencode or the task tool - covers description writing for auto-delegation, tool selection, prompt structure, and testing agents
Use when creating, releasing, or maintaining an opencode Plugin Marketplace - covers marketplace.json schema, version management, release checklists, changelog conventions, and validation to prevent sync drift between plugin.json and marketplace.json
Use when completing development phases or branches to identify and update AGENTS.md files that may have become stale - analyzes what changed, determines affected contracts and documentation, and coordinates updates