Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Admin Governance

ASecurity

Weekly hygiene ritual for Zynkr's local↔cloud knowledge governance. Lists Google Drive Docs modified in the last N days across the 8 LOB folders (and Drive root), diffs against local `_INDEX.md` entries in `~/Desktop/Claude/zynkr/`, and proposes specific index edits: new entries to add, broken/renamed links to fix, deleted Docs to remove. Triggers on phrases like 'drift check', 'weekly hygiene', 'sync indexes', 'check cloud changes', 'what changed in cloud this week', '/admin-governance', or ...

20 stars
0 votes
0 copies
2 views
Added 9/19/2026
businessgogit

Works with

claude codeclimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add peter-tu-zynkr/zynkr-skill-builder --skill admin-governance --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Admin Governance?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Admin Governance
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/peter-tu-zynkr-admin-governance/badge)](https://www.skillsdirectory.com/skills/peter-tu-zynkr-admin-governance)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: admin-governance
sheetId: "3.05"
description: "Weekly hygiene ritual for Zynkr's local↔cloud knowledge governance. Lists Google Drive Docs modified in the last N days across the 8 LOB folders (and Drive root), diffs against local `_INDEX.md` entries in `~/Desktop/Claude/zynkr/`, and proposes specific index edits: new entries to add, broken/renamed links to fix, deleted Docs to remove. Triggers on phrases like 'drift check', 'weekly hygiene', 'sync indexes', 'check cloud changes', 'what changed in cloud this week', '/admin-governance', or when the user pastes nothing but asks to reconcile local/cloud state. Should fire eagerly when the user references the weekly hygiene ritual from the Zynkr knowledge-governance model."
category: operations
project: admin-governance
platform: claude
status: Done
author: Peter Tu
input: "Optional: number of days to look back (default 7). Optional: LOB scope as either an LOB number ('2.0', '7.1') or 'all' (default 'all'). Optional: Google account override (defaults to peter_tu@zynkr.ai)."
process: "List cloud folder contents with modifiedTime via Google Workspace MCP → filter to the time window → read each affected local `_INDEX.md` → diff cloud entries against indexed URLs → emit a per-LOB report: new Docs to add, broken entries to fix, summary count. Do NOT edit `_INDEX.md` files automatically — surface a ready-to-apply changelist for the user to approve."
output: "Per-LOB report (one section per LOB touched in the window): NEW (cloud Docs not in index) · CHANGED (Docs whose modifiedTime moved within the window) · BROKEN (index entries whose URLs no longer resolve). Each line includes the cloud URL and the proposed `_INDEX.md` edit. End with a single-line summary count."
synergy: []
house-style: bound

---

# Drift Check

The weekly (or on-demand) reconciliation between Zynkr's Google Drive (cloud SOT for human knowledge) and the local `_INDEX.md` files (the navigation map). Without this, indexes rot and the governance model breaks.

This skill **only reports** — it does not edit indexes. The user reviews the proposed changes and applies them (or asks Claude Code to apply them).

---

## 0) Required reading (do this before acting)

| File | Read when |
|---|---|
| `references/lob-folder-map.md` | Always — the canonical mapping of LOB number → Drive folder ID → local path. Source of truth for what to scan and where the indexes live. |

---

## 1) Resolve inputs

Defaults:
- `days_back`: 7
- `scope`: `all` (scan every LOB folder)
- `user_google_email`: `peter_tu@zynkr.ai`

If the user gave any of these, use what they said. If `scope` is a specific LOB (e.g., `2.0`), only scan that one folder.

Compute `cutoff_iso = (now - days_back days)` as RFC 3339 (e.g., `2026-05-20T00:00:00Z`).

---

## 2) For each LOB in scope:

### 2a. List cloud folder contents

Call `mcp__google-workspace__list_drive_items` with:
- `user_google_email`: the resolved email
- `folder_id`: from `references/lob-folder-map.md`
- `page_size`: 100

Some LOBs map to multiple cloud folders (e.g., `7` → `[7.1]`, `[7.2]`, `[7.3]`). List each.

For LOB `5` the cloud counterpart is the `[5.x]` series under the Drive root (`1rqkpNt1NFmRXhXnVAXL_eoXVfON4qD32`) — list the root and filter to children whose name starts with `[5.`.

### 2b. Filter to the time window

Keep items where `modifiedTime >= cutoff_iso`.

### 2c. Read the local index

Read `~/Desktop/Claude/zynkr/<local_path>/_INDEX.md` per `references/lob-folder-map.md`. Extract all URLs that match `https://docs.google.com/document/d/<id>` or `https://drive.google.com/drive/folders/<id>`.

### 2d. Diff

- **NEW**: a cloud item whose ID does not appear anywhere in the local index.
- **CHANGED**: a cloud item whose ID appears in the index but whose `modifiedTime` is inside the window (worth re-reading the cloud Doc to decide if the index entry's one-liner needs updating).
- **BROKEN**: an index entry whose URL no longer resolves (404 from `list_drive_items` or its parent folder). To check, call `mcp__google-workspace__list_drive_items` with the parent folder and look for the ID. If absent → BROKEN.

For the broken check: optional, only do it if `days_back >= 30` (cheap on small windows, expensive on large ones). Otherwise note "BROKEN check skipped (window < 30d)" in the report.

---

## 3) Emit the report

Format exactly:

```
# Drift check — 2026-05-27 (window: 7 days)

## LOB 0 — strategy-planning
NEW (1):
  - "Some new Doc title" — https://docs.google.com/document/d/<id>/edit
    → Add to `0 strategy-planning/_INDEX.md` under "Cloud (canonical)":
      `| **Some new Doc title** | Doc | [open](https://...) |`

CHANGED (0): —
BROKEN (0): —

## LOB 2.0 — sales-consultant-offering
NEW (0): —
CHANGED (1):
  - "Sales and Consultant Operating Plan" — modifiedTime 2026-05-26
    → Re-check that the index one-liner still reflects the Doc's current scope. Open: https://...

BROKEN (0): —

...

---
Summary: 1 new · 1 changed · 0 broken across 2 LOBs. 6 LOBs clean.
```

If the entire scan is clean, the report is one line:

```
Drift check — 2026-05-27 (window: 7 days, scope: all): all clean ✓
```

---

## 4) Self-checks

- Did you scan every LOB in scope? Cross-check against `references/lob-folder-map.md`.
- Did you handle the `[5.x]` multi-folder case?
- Did you handle the `[7.x]` multi-folder case?
- Did you skip the BROKEN check when window < 30d, and say so?

---

## 5) What this skill explicitly does not do

- Does **not** edit `_INDEX.md` files. Reporting only.
- Does **not** push or pull content. Pure metadata diff.
- Does **not** touch local files in `6.0 tech/` — that side is git-tracked, not part of the cloud SOT model.
- Does **not** trigger sync re-pulls for Strategy B snapshots (v2 strategy, methodology, dev plan, dev process). If a CHANGED item is one of those, flag it for re-sync in the report — but the user decides.

## 6) Output style

- Be terse. The user is scanning for action items, not reading prose.
- Use the exact format in §3 — downstream tools (or a future auto-apply step) parse it.
- "Clean ✓" is a complete answer. Don't pad.

## House style

Writing style is **not owned by this file**. The house voice lives in two Google Docs under
`[@] 寫作指南` (`12DBdFz3SK22ie9im_ThFMI7IBRXsTZsV`), read at runtime:

- 《[2.0] Zynkr 通用風格指南 House Voice》 `10bOIQwRm9Pxwgct4hlwCwK_B4Pipai1HqBPZKzyRHSE` —
  the universal core, plus the addendum for this surface
- 《[3.2] 禁用詞清單 Forbidden Words》 `1N5sHLP4qzmmhpCGsi6KElxi1z0MFe4QZ0Q_35T10Uyg`

Read both before producing client- or reader-facing text, and scan the draft against 《[3.2]》
before handing it over. If Drive is unreachable, say so in the output rather than proceeding
unchecked. Never re-implement either list inside this file.

Attribution

peter-tu-zynkrpeter-tu-zynkr
View sourceMore from peter-tu-zynkr →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Solution Architect

Designs system architecture, component specifications, and technical integration strategy. Use when: designing solutions, system architecture, technology stack, or integration approaches.

192 votes

Akorchak:Venture Assessment

Generate a comprehensive VC investment assessment report for a company

72 votes

Stock Analysis

Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management (create, add, remove assets), crypto analysis (Top 20 by market cap), and periodic performance reports (daily/weekly/monthly/quarterly/yearly). 8 analysis dimensions for stocks, 3 for crypto. Use for stock analysis, portfolio tracking, earnings reactions, or crypto monitoring.

6511 votes

Just Fucking Cancel

Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'cancel subscriptions', 'audit subscriptions', 'find recurring charges', 'what am I paying for', 'save money', 'subscription cleanup', 'stop wasting money'. Supports CSV import (Apple Card, Chase, Amex, Citi, Bank of America, Capital One, Mint, Copilot) OR Plaid API for automatic transaction pull. Out...

6511 votes

Telegram Compose

Compose rich, readable Telegram messages using HTML formatting via direct Telegram API. Use when: (1) Sending any Telegram message beyond a simple one-line reply, (2) Creating structured messages with sections, lists, or status updates, (3) Need formatting unavailable via Clawdbot's Markdown conversion (underline, spoilers, expandable blockquotes, user mentions by ID), (4) Sending alerts, reports, summaries, or notifications to Telegram, (5) Want professional, scannable message formatting wit...

6511 votes
View all in business →