What is weekly-review?

A workflow that prepares a weekly project review from email, WhatsApp messages, and meeting transcripts. It creates a project dashboard and a detailed weekly log, but needs external helper scripts and account connections.

Use it to collect project communications, normalise transcripts, identify themes, and write a weekly review into a Google document.

It brings updates from several sources into one review instead of requiring separate manual summaries.

weekly-review — Skill for Claude Code by chrisblattman/claudeblattman

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add chrisblattman/claudeblattman --skill weekly-review

Clone the repo

git clone --depth 1 https://github.com/chrisblattman/claudeblattman

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/weekly-review/github.svg)](https://agentmods.dev/skills/chrisblattman/claudeblattman/weekly-review)

Your own site

<a href="https://agentmods.dev/skills/chrisblattman/claudeblattman/weekly-review"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/weekly-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chrisblattman/claudeblattman/weekly-review"><img src="https://agentmods.dev/badge/skills/chrisblattman/claudeblattman/weekly-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,410 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.04410
Opus 5.5	$0.00010	$0.01764
Sonnet 5.5	$0.00005	$0.00882
Haiku 4.5	$0.00002	$0.00441

Measured today against content hash d7d8b4e6cc83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weekly-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/weekly-review/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly Project Review

v1.9.1 — Stricter YAML config parsing (loud failure on malformed .claude/CLAUDE.md); helper scripts for multi-tab Google Doc writes (replace-dashboard.py, insert-weekly-log.py); RTF/PDF transcript normalization (normalize-transcripts.py); hollow-transcript handling per-meeting; document-comment processing (read, apply corrections, reply, resolve).

Generate a comprehensive weekly summary for the current research project, pulling from multiple sources.

Public reference, not a complete install. This file describes a workflow that uses three external Python helpers: normalize-transcripts.py, replace-dashboard.py, and insert-weekly-log.py. Those helpers are not included in this public repository. Set up and review suitable helpers and account connections before running this workflow.

Overview

This skill collects data from WhatsApp, meeting transcripts, and Gmail, then generates:

Tab 1 content: High-level project dashboard (updated directly in Google Doc)
Tab 2 content: Detailed weekly log with thematic synthesis across all sources

Prerequisites

Before fetching, normalizing, archiving or writing anything, verify the three helper files at the configured WEEKLY_REVIEW_HELPERS path and the intended account/project configuration. If any helper is missing, stop and report the missing dependency. Do not invent a bundled scripts directory, silently skip that work, or substitute a different account. The public file alone does not provide those dependencies.

The skill expects three env vars on each machine (set in ~/.zprofile or equivalent):

export GOOGLE_WORKSPACE_MCP_USER_EMAIL="<your@email>"     # account to authenticate as
export GOOGLE_WORKSPACE_MCP_CREDENTIALS_FILE="<path>"     # optional; defaults to ~/.google_workspace_mcp/credentials/<email>.json
export WEEKLY_REVIEW_HELPERS="<path>"                     # required for a public adaptation; point to reviewed local helpers

If GOOGLE_WORKSPACE_MCP_USER_EMAIL is unset on a machine that has only one credentials file, scripts fall back to the legacy default. Multi-account machines must set the env var explicitly — the helper scripts do NOT silently glob-pick the first credentials file (this prevents silent wrong-account writes).

Read the full file on GitHub · 317 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today First seen · 317 lines · 24 tokens per session scan A d7d8b4e6cc83

Subscribe to this mod's changes

weekly-review is a skill published in the GitHub repository chrisblattman/claudeblattman (476 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 4,410 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Analytics and metrics Project management academic-research ai-tools claude-ai mkdocs

weekly-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
weekly-reviewchrisblattman/claudeblattman	Skill	476	yesterday	MIT	A	24	Claude Code
skill-builderyusufkaraaslan/Skill_Seekers	Skill	15k	1mo ago	MIT	A	38	Claude Code, Codex
strategic-revisionflonat/flonat-research	Skill	149	3d ago	MIT	A	66	Claude Code
skill-creatorflonat/flonat-research	Skill	149	3d ago	MIT	A	41	Claude Code
beamer-deckflonat/flonat-research	Skill	149	3d ago	MIT	A	63	Claude Code
numerical-checkflonat/flonat-research	Skill	149	3d ago	MIT	A	65	Claude Code
skill-preflightflonat/flonat-research	Skill	149	3d ago	MIT	A	34	Claude Code