guard
Full safety mode: destructive command warnings + directory-scoped edits. (gstack)gstack/guardAIpkg · registry
Packages / all
Every package in the registry — skills, subagents, rules, setups, and boxes. Search by key, namespace, or tag.
total59·page01/03
matching
gstack→59 results58downloads0likesv0.1.02 months
hackernews-frontpage
Scrape the Hacker News front page (titles, points, comment counts).gstack/hackernews-frontpagefreeze
Restrict file edits to a specific directory for the session. (gstack)gstack/freezebrowse
Fast headless browser for QA testing and site dogfooding. (gstack)gstack/browseGstack
Garry Tan's gstack — a large library of Claude Code skills for shipping: QA, design review, planning, investigation, iOS workflows, deploys, and headless-browser dogfooding. Bundles the individually-published gstack/* skills as one box.gstack/Gstackgstack-openclaw-ceo-review
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.gstack/gstack-openclaw-ceo-reviewgstack-openclaw-retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware with per-person contributions, praise, and growth areas. Use when asked for weekly retro, what shipped this week, or engineering retrospective.gstack/gstack-openclaw-retrogstack-openclaw-office-hours
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.gstack/gstack-openclaw-office-hoursgstack-openclaw-investigate
Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.gstack/gstack-openclaw-investigateautoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)gstack/autoplanbenchmark-models
Cross-model benchmark for gstack skills. (gstack)gstack/benchmark-modelsbenchmark
Performance regression detection using the browse daemon. (gstack)gstack/benchmarkcanary
Post-deploy canary monitoring. (gstack)gstack/canarycareful
Safety guardrails for destructive commands. (gstack)gstack/carefulcodex
OpenAI Codex CLI wrapper — three modes. (gstack)gstack/codexcontext-restore
Restore working context saved earlier by /context-save. (gstack)gstack/context-restorecontext-save
Save working context. (gstack)gstack/context-savecso
Chief Security Officer mode. (gstack)gstack/csodesign-consultation
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)gstack/design-consultationdesign-html
Design finalization: generates production-quality Pretext-native HTML/CSS. (gstack)gstack/design-htmldesign-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)gstack/design-reviewdesign-shotgun
Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate. (gstack)gstack/design-shotgundevex-review
Live developer experience audit. (gstack)gstack/devex-reviewdocument-generate
Generate missing documentation from scratch for a feature, module, or entire project. (gstack)gstack/document-generatedocument-release
Post-ship documentation update. (gstack)gstack/document-releaseAIpkg/registry · online · “Have you tried turning the AI off and on?” indexed