Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

wrap-up

Estrelas1

Forks0

Atualizado23 de julho de 2026 às 16:57

Format and upload session wrap-up to NotebookLM for persistent semantic memory

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

gHashTag

gHashTag/t27

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	wrap-up
description	Format and upload session wrap-up to NotebookLM for persistent semantic memory
version	1.0.0
author	Trinity S3AI Framework

Wrap-Up Skill

Upload session summaries to NotebookLM for cross-session memory persistence.

What It Does

Extracts session context from .trinity/ state files
Formats summary as Markdown with metadata
Uploads to NotebookLM as searchable source

Usage

/wrap-up "Session completed Phi Loop iterations for Ring-071"

Or with full details:

/wrap-up --summary "Implemented NotebookLM backend" \
         --decisions "Used notebooklm-py SDK with cookie auth" \
         --files "contrib/backend/notebooklm/*.py" \
         --steps "Run integration tests"

Implementation

This skill uses the t27 spec-first approach:

Spec: specs/automation/wrapup-auto.t27
Backend: contrib/backend/notebooklm/wrapup_auto.py
Invocation: Python script directly (no shell scripts - L7 compliant)

Direct invocation (for debugging):

.trinity/notebooklm-venv/bin/python3 \
    contrib/backend/notebooklm/wrapup_auto.py \
    --summary "Session summary" \
    --session-id "$(git rev-parse --short HEAD)" \
    --decisions "Key decisions" \
    --files "file1.py,file2.py" \
    --steps "Next steps"

Configuration

Auth: Cookie-based via notebooklm login (stores in ~/.notebooklm/storage_state.json)
Active Notebook: Set via --notebook flag (default: "t27-QUEEN-BRAIN")
Default Notebook: "t27-QUEEN-BRAIN" (creates if not exists)
Storage: ~/.notebooklm/ — browser profile, storage state

Setup Commands:

python -m venv .trinity/notebooklm-venv
.trinity/notebooklm-venv/bin/pip install notebooklm-py
notebooklm login              # Authenticate via browser (one-time)

Output

Returns source ID and notebook ID for verification:

{
  "notebook_id": "...",
  "source_id": "...",
  "uploaded_at": "2026-04-08T..."
}

Mais deste repositório

mesmo repositório

phi-loop

gHashTag/t27

Execute 9-phase spec-first development workflow (Issue → Spec → TDD → Code → Gen → Seal → Verify → Land → Learn)

2026-07-231

tri-pipeline

gHashTag/t27

Execute tri commands (gen, test, verify, seal, verdict) for spec-first development

2026-07-231

tri

gHashTag/t27

This skill should be used when user asks to "tri skill begin", "PHI LOOP", "edit .t27 spec", "seal hash", "tri gen", "tri test", "tri verdict", "tri experience save", "tri notebook query", "tri notebook wrapup", or any task requiring spec-first development in the t27 Trinity S³AI project. Implements the canonical PHI LOOP workflow following constitutional laws with NotebookLM-backed semantic memory.

name	wrap-up
description	Format and upload session wrap-up to NotebookLM for persistent semantic memory
version	1.0.0
author	Trinity S3AI Framework

Wrap-Up Skill

Upload session summaries to NotebookLM for cross-session memory persistence.

What It Does

Extracts session context from .trinity/ state files
Formats summary as Markdown with metadata
Uploads to NotebookLM as searchable source

Usage

/wrap-up "Session completed Phi Loop iterations for Ring-071"

Or with full details:

/wrap-up --summary "Implemented NotebookLM backend" \
         --decisions "Used notebooklm-py SDK with cookie auth" \
         --files "contrib/backend/notebooklm/*.py" \
         --steps "Run integration tests"

Implementation

This skill uses the t27 spec-first approach:

Spec: specs/automation/wrapup-auto.t27
Backend: contrib/backend/notebooklm/wrapup_auto.py
Invocation: Python script directly (no shell scripts - L7 compliant)

Direct invocation (for debugging):

.trinity/notebooklm-venv/bin/python3 \
    contrib/backend/notebooklm/wrapup_auto.py \
    --summary "Session summary" \
    --session-id "$(git rev-parse --short HEAD)" \
    --decisions "Key decisions" \
    --files "file1.py,file2.py" \
    --steps "Next steps"

Configuration

Auth: Cookie-based via notebooklm login (stores in ~/.notebooklm/storage_state.json)
Active Notebook: Set via --notebook flag (default: "t27-QUEEN-BRAIN")
Default Notebook: "t27-QUEEN-BRAIN" (creates if not exists)
Storage: ~/.notebooklm/ — browser profile, storage state

Setup Commands:

python -m venv .trinity/notebooklm-venv
.trinity/notebooklm-venv/bin/pip install notebooklm-py
notebooklm login              # Authenticate via browser (one-time)

Output

Returns source ID and notebook ID for verification:

{
  "notebook_id": "...",
  "source_id": "...",
  "uploaded_at": "2026-04-08T..."
}