Receber por email
← Voltar para o catálogo

review-session

Use when the user wants to review a Claude Code session for quality — analyzes the current session (or a specified transcript path) for prompting effectiveness, agent performance, and environment gaps, producing actionable recommendations

235estrelas
Atualizado há 4 meses

Ver no GitHub ↗

Como adicionar

/plugin marketplace add ed3dai/ed3d-plugins

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/review-session/svg)](https://www.skillteca.com.br/skills/review-session)

Skills relacionadas

Ver todas de Pesquisa e Web →

Alerta por categoria

Receba novas skills de Pesquisa e Web toda segunda

1 email curto, só com as skills novas de Pesquisa e Web. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

Review Session

Review a single Claude Code session transcript for quality and produce actionable findings.

Do not use nested subagents. This workflow may dispatch the conversation-reviewer agent, but that agent must analyze the transcript directly and must not dispatch additional subagents.

Prerequisites

  • The ed3d-extending-claude plugin must be installed.
  • The ed3d-session-reflection plugin must be installed (provides the conversation-reviewer agent and reduce-transcript.py script).
  • The current session's transcript path must be available (injected by the SessionStart hook). If it is not available, ask the user for the transcript path.

Invocation

The user may invoke this as:

  • /review-session — review the current session
  • /review-session /path/to/transcript.jsonl — review a specific transcript

If no argument is provided, use the current session's transcript path (from the SessionStart hook context injection).

Steps

1. Determine the transcript path

If an argument was provided, use it as the transcript path. Otherwise, use the current session's transcript path from the SessionStart hook injection.

If you cannot determine the transcript path, tell the user:

I don't know the current session's transcript path.
Either provide a path: /review-session /path/to/session.jsonl
Or ensure the ed3d-session-reflection SessionStart hook is active.

2. Reduce the transcript

Run the reduction script to produce a token-efficient version:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/reduce-transcript.py" "<transcript_path>" "/tmp/session-review/reduced.txt"

Tell the user you're reducing the transcript for analysis.

3. Dispatch the reviewer

Create a temporary output path for findings:

/tmp/session-review/findings.md

Dispatch the conversation-reviewer agent with:

<invoke name="Agent"> <parameter name="subagent_type">ed3d-session-reflection:conversation-reviewer</parameter> <parameter name="description">Review session transcript</parameter> <parameter name="model">opus</parameter> <parameter name="prompt"> Review the reduced Claude Code 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. Do not dispatch or invoke any subagents. </parameter> </invoke>

4. Present findings

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.

Compartilhar X LinkedIn