gchat SKILL.md skillA

gchat from zjshen14/agy-hq is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add zjshen14/agy-hq/gchat@git:20261115.c017ea4

Pins git:20261115.c017ea4 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
zjshen14/agy-hq
Path
templates/skills/gchat/SKILL.md
Versions recorded
1
Latest version
git:20261115.c017ea4, committed Nov 15, 2026
Size
6,220 bytes
Repository stars
32
License
Apache-2.0

Read, search, draft, and send Google Chat messages and manage Spaces/DMs using hq gchat. Use whenever the user mentions Google Chat, GChat, a Chat space or group (e.g. "Project Launch Space", "Engineering Core"), asks to send a message on Google Chat, check unread Chat messages, or list Chat spaces.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Google Chat Integration (`hq gchat`)

Use `hq gchat` for all Google Chat operations across personal (`@gmail.com`) and Google Workspace accounts.

> **Never** use `chrome-devtools` MCP tools directly on `chat.google.com` (blocked by `PreToolUse`). Always use `hq gchat`, which manages an isolated, network-jailed `--headless=new` Chrome profile (`local/private/gchat/chrome-profile`) and enforces cryptographic 1-tap approval.

## 1. Sending a Google Chat Message (Inline 1-Step Workflow)

When the user asks to send a message to a Google Chat space or DM (even from `[HQ] Front Desk`), **do not spawn a subagent** and **do not grep code**. Execute this 2-turn flow directly:

1. **Stage Draft + Proposal in 1 Command (Supports Natural Space Names or IDs):**
   ```sh
   # Simple single-line message without '$'
   hq gchat propose --to="Project Launch Space" --body="Your message text here"

   # Multi-line or messages containing '$' (e.g. currency like $382.34) — ALWAYS use --body-stdin with <<'EOF'
   cat <<'EOF' | hq gchat propose --to="Project Launch Space" --body-stdin
   Total reimbursement is $382.34.
   Please confirm when received.
   EOF
   ```
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_6ourjrqpnvrjecnw/9f8ac452d5e6c8397864a048f949b26f3ab74928c75c505cb7af5a66316f0145.json

Then /plugin install gchat@markdownregistry-6ourjrqpnvrjecnw in Claude Code. It installs git:20261115.c017ea4, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add zjshen14/agy-hq/gchat@sha256:9f8ac452d5e6c839

The line at the top of this page pins the label git:20261115.c017ea4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6ourjrqpnvrjecnw.svg)](https://markdownregistry.com/a/art_6ourjrqpnvrjecnw)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in zjshen14/agy-hq/gchat since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of gchat from somewhere else? Ask it: where did my gchat come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 15, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261115.c017ea4 latest2026-11-15 c017ea4 6,220 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6220 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

zjshen14/agy-hq · 32 stars · license Apache-2.0 · pushed 2026-11-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6ourjrqpnvrjecnw
GET https://markdownregistry.com/api/v1/resolve?ref=zjshen14/agy-hq/gchat
GET https://markdownregistry.com/api/v1/blob/9f8ac452d5e6c8397864a048f949b26f3ab74928c75c505cb7af5a66316f0145

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from zjshen14/agy-hq

AGENTS.md@.agents/plugins/agy-hq/rules AGENTS.md file
zjshen14/agy-hq · .agents/plugins/agy-hq/rules/AGENTS.md
git:20261117.8cc750f · audit A · 32 stars
inbox-triage SKILL.md skill
zjshen14/agy-hq · .agents/plugins/agy-hq/skills/inbox-triage/SKILL.md · Quarantined triage of inbound channel events or files dropped into local/inbox/. Classifies items by urgency, stages…
git:20261117.e14ac3c · audit A · 32 stars
morning-brief SKILL.md skill
zjshen14/agy-hq · .agents/plugins/agy-hq/skills/morning-brief/SKILL.md · Generate the daily Morning Brief across configured connectors, inbox rollups, pending approvals, active engineering…
git:20261116.4f4d0f7 · audit A · 32 stars
sleep-consolidate SKILL.md skill
zjshen14/agy-hq · .agents/plugins/agy-hq/skills/sleep-consolidate/SKILL.md · Nightly sleep-time memory consolidation ("dreaming") workflow. Audits Vault memory health, verifies turn journal claims…
git:20261116.4f4d0f7 · audit A · 32 stars
AGENTS.md AGENTS.md file
zjshen14/agy-hq · AGENTS.md
git:20261115.fff04a9 · audit A · 32 stars
filing-diff SKILL.md skill
zjshen14/agy-hq · templates/skills/filing-diff/SKILL.md · Section-by-section semantic diff of consecutive SEC filings (10-K vs prior 10-K, 10-Q vs prior 10-Q) highlighting new…
git:20261115.c017ea4 · audit A · 32 stars
ledger-ingest SKILL.md skill
zjshen14/agy-hq · templates/skills/ledger-ingest/SKILL.md · Plain-text accounting (Beancount / hledger) ingestion and reconciliation workflow. Parses bank CSV/OFX statements from…
git:20261115.c017ea4 · audit A · 32 stars
swe-pulse SKILL.md skill
zjshen14/agy-hq · templates/skills/swe-pulse/SKILL.md · Single-entry-point software engineering orchestrator. Manages isolated git worktrees in local/worktrees/<repo>-<task>/…
git:20261115.c017ea4 · audit A · 32 stars
tax-prep SKILL.md skill
zjshen14/agy-hq · templates/skills/tax-prep/SKILL.md · Tax document extraction, checklist tracking, and deterministic workpaper preparation inside local/private/taxes/. Use…
git:20261115.c017ea4 · audit A · 32 stars
thesis-check SKILL.md skill
zjshen14/agy-hq · templates/skills/thesis-check/SKILL.md · Investment thesis tracker and falsification monitor. Evaluates new earnings releases, 10-K/10-Q/8-K filings, or market…
git:20261116.4f4d0f7 · audit A · 32 stars

Every file in zjshen14/agy-hq

Browse by kind, by grade A, or by owner.