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

Hq Cowork Sync

ASecurity

Run bidirectional HQ Sync from Cowork.

85 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgoshellnode

Works with

claude codemcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add indigoai-us/hq-core --skill hq-cowork-sync --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hq Cowork Sync?

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

Security grade badge for Hq Cowork Sync
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/indigoai-us-hq-cowork-sync/badge)](https://www.skillsdirectory.com/skills/indigoai-us-hq-cowork-sync)

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

Download Zip
Files
SKILL.md
---
name: hq-cowork-sync
description: Run bidirectional HQ Sync from Cowork.
allowed-tools: mcp__hq__hq_sync, mcp__hq__hq_whoami
---

# /hq-cowork-sync — Sync HQ from a sandboxed agent

Runs the same sync engine the HQ Desktop App uses, but from
inside a sandboxed Claude Code plugin host (Cowork, in particular). Walks
every cloud-backed company in your local HQ, syncs in both directions
against the vault, and writes conflict mirror files when divergence is
detected.

**Args:** `$ARGUMENTS` — optional flags. Accepted shapes (parse free-text):

- `--company <slug>` → scope to one company
- `--personal` → sync only the caller's personal vault
- `--on-conflict overwrite|keep|abort` → conflict strategy (default `keep`)
- `--message "<msg>"` → optional journal message attached to push leg

Without args, syncs every membership + personal vault with `--on-conflict keep`.

## When to use this instead of `/hq-sync`

- **You're in Cowork or another sandboxed plugin host.** The sandbox can't see
  `~/.hq/cognito-tokens.json` and `hq` isn't on PATH inside it, so the regular
  `/hq-sync` skill (which spawns `npx ... hq-sync-runner`) cannot run.
- **You want native MCP tool-call ergonomics** — observable in the host's tool
  log, not just shell output.

In a regular Claude Code session running on the host directly, prefer the
unprefixed `/hq-sync` skill — same engine, fewer hops.

## What you do

### Step 1 — Confirm the host MCP is wired

Before the first sync of a session, call `mcp__hq__hq_whoami`. If it returns
your identity + session expiry, the host MCP is live and authenticated. If
it errors with "not signed in" or "tokens expired", tell the user to run
`hq login` on the host machine (the sandboxed agent cannot do this itself
— `hq login` opens a browser on the host).

### Step 2 — Call the sync tool

Parse `$ARGUMENTS` into the `hq_sync` tool's input schema:

| Arg pattern | Tool input |
|---|---|
| `--company <slug>` | `{ "company": "<slug>" }` |
| `--personal` | `{ "personal": true }` |
| (neither) | `{}` — server defaults to `--all` |
| `--on-conflict <strategy>` | `{ "onConflict": "<strategy>" }` |
| `--message "<msg>"` | `{ "message": "<msg>" }` |

Call `mcp__hq__hq_sync` with the assembled input. Sync output can be chunky
(per-company push + pull legs) — surface a terse summary, not the full log,
unless the user asked for verbose detail.

### Step 3 — Report

Quiet by default. Surface:
- Companies synced (count + names)
- Conflicts written (count + the path to `<hqRoot>/.hq-conflicts/index.json`
  if any — the user can run `/resolve-conflicts` next)
- Errors from any individual company leg (don't swallow them)

If conflicts were written, mention `/resolve-conflicts` as the next step.

## Why this skill exists

The unprefixed `/hq-sync` skill resolves HQ root via four config tiers and
then `exec`s the cloud-runner binary directly with the host's Cognito
session. None of that works from Cowork's sandbox, where `~/.hq` is not
mounted and the host's Node binary isn't reachable. The
`hq-pack-cowork` MCP server fixes that by running on the host (with full
auth + binaries) and exposing `hq_sync` as a tool call the sandboxed agent
*can* make. This skill is the thin in-session adapter for that tool.

Attribution

indigoai-usindigoai-us
View sourceMore from indigoai-us →
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

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →