gstack-openclaw-ceo-review
An agent skill by garrytan, from garrytan/gstack. Tags: planning, product-strategy, review, strategy.
What it does
Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add garrytan/gstack --skill gstack-openclaw-ceo-reviewOr 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-ceo-review ~/.claude/skills/gstack-openclaw-ceo-reviewSafety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-21. 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 review-only prompt skill: it analyzes plans and asks for approval before proceeding, but it contains no executable code, downloads, or machine-touching scripts. The main risk is operational overhead and process rigidity, not direct machine or data exposure.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, code evaluation, or bundled scripts are present; `SKILL.md` is plain prose only. |
| Network access | 0 (none) | There are no fetches, API calls, or remote-host interactions defined in the skill file. |
| Filesystem reach | 0 (none) | The skill does not read, write, or delete files on disk; it only describes a review workflow. |
| Secrets & credentials | 0 (none) | It does not request credentials, tokens, `.env` files, keychains, or browser sessions. |
| Privilege & persistence | 0 (none) | No sudo, service registration, shell/profile editing, or other privilege-changing actions are specified. |
| Instruction hijack surface | 0 (none) | The file contains strong workflow instructions such as `Do NOT proceed without approval`, but nothing that tries to override higher-priority instructions or fetch hidden/remote guidance. |
| Irreversible actions | 0 (none) | It explicitly requires user approval before proceeding and does not authorize actions like posting, deploying, paying, or deleting. |
| Transparency | 0 (none) | There are no binaries, minified blobs, base64 payloads, or unpinned downloads; the entire skill is readable text. |
Before installing
- Confirm you want a review-only skill with no code changes or command execution.
- Check the repo path for any companion scripts or installers; this skill file itself has none.
- Expect a very interactive workflow: it asks for scope choice and then one issue at a time.
Rated 2026-10-21 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-ceo-review/SKILL.md
- Branch
- main
- Updated
- 2026-10-05
Related skills
- plan-ceo-review — CEO/founder-mode plan review. (gstack)
- launch — When the user wants to plan a product launch, feature announcement, or release strategy.
- seo-plan — Strategic SEO planning for new or existing websites. Industry-specific templates, competitive analysis, content strategy, and implementation roadmap.
- claude-md-progressive-disclosurer — Optimize, slim, or restructure CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user explicitly asks to audit, 精简, 瘦身.
- grill-with-docs — A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
- advisor — Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done.