gstack-openclaw-office-hours

An agent skill by garrytan, from garrytan/gstack. Tags: brainstorming, product-strategy, strategy.

What it does

Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add garrytan/gstack --skill gstack-openclaw-office-hours

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/garrytan/gstack
cp -r gstack/openclaw/skills/gstack-openclaw-office-hours ~/.claude/skills/gstack-openclaw-office-hours

Safety box score

Grade B, low risk: 12 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a purely advisory office-hours skill: it reads the current workspace, git history, and codebase to produce a design doc, and it explicitly forbids implementation or code writing. The main exposure is read access to repository contents/history plus a very prescriptive conversation flow; it does not appear to touch the network, secrets, or system privileges.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	Phase 1 asks it to 'Read the workspace', 'Check git log', and 'Search the codebase'; that is tool-driven inspection, but the skill does not request running code or shipped scripts.
Network access	0 (none)	No downloads, API calls, or remote data transmission are specified anywhere in the skill.
Filesystem reach	1 (low)	It reads project docs, the codebase, and git history, so it can inspect repository files and history, but it does not instruct writes, deletes, or access outside the project.
Secrets & credentials	0 (none)	The skill never asks for tokens, keys, passwords, browser sessions, or `.env` contents.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, shell/OS mutation, or other privilege change.
Instruction hijack surface	1 (low)	It strongly scripts the assistant's persona and dialogue flow ('You are a YC office hours partner', 'Ask the user which approach to proceed with. Do NOT proceed without their approval.'), but it does not tell the agent to ignore higher-level instructions or hidden content.
Irreversible actions	0 (none)	The skill explicitly says 'Do NOT invoke any implementation' and limits output to a design document; it does not send messages, deploy, publish, pay, book, or delete.
Transparency	0 (none)	The skill is plain markdown with no binaries, embedded installers, minified code, or runtime-decoded payloads.

Before installing

Confirm you’re okay with the agent reading the repo and recent git history.
If the repository contains anything sensitive, use a scrubbed or scratch clone first.
Verify there are no wrapper scripts or hidden tool hooks in the repo that would turn this read-only workflow into code execution.
Check that the approval gate and one-question-at-a-time flow match how you want the session to run.

Rated 2026-10-16 by an automated review of 1 file from the skill's repository.

Source

Repository: garrytan/gstack (all skills from this repository)
Path: openclaw/skills/gstack-openclaw-office-hours/SKILL.md
Branch: main
Updated: 2026-10-05

ansoff-matrix — Generate an Ansoff Matrix analysis mapping growth strategies across market penetration, market development, product development, and diversification.
brainstorm-experiments-existing — Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods.
brainstorm-experiments-new — Design lean startup experiments (pretotypes) for a new product.
brainstorm-ideas-existing — Brainstorm product ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints.
brainstorm-ideas-new — Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives.
feature-forge — Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria.