Skill Claude Code
Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety"…
Skill Claude Code
Code quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell linter), computes a weighted composite 0-10 score, and tracks trends over time. Use when: "health check", "code quality", "how healthy is the codebase", "run all checks", "quality score". (gstack).
Skill Claude Code
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…
Skill Claude Code
Turn any markdown file into a publication-quality PDF. Proper 1in margins, intelligent page breaks, page numbers, cover pages, running headers, curly quotes and em dashes, clickable TOC, diagonal DRAFT watermark. Not a draft artifact — a finished artifact. Use when asked to "make a PDF", "export to PDF", "turn this…
Skill Claude Code
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…
Skill Claude Code
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
Skill Claude Code
Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to "review the design plan" or "design critique". Proactively…
Skill Claude Code
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
Skill Claude Code
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively…
Skill Claude Code
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a…
Skill Claude Code
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land…
Skill Codex
A tool for generating Guizang-style social media image sets and WeChat cover images from articles, scripts, screenshots, product notes, subtitles, or photos. WeChat is a Chinese messaging and publishing platform, while Xiaohongshu is a Chinese social shopping platform.
Skill Claude CodeCodex
A design-stage review for AI-agent products based on the GX two-bus architecture. It checks how agents, skills, business systems, and shared business data should be separated before implementation.
Skill Claude CodeCodex
An implementation audit for AI-agent products using the GX two-bus architecture. It checks whether the agent, skills, business systems, APIs, end-to-end traces, and monitoring are connected as intended, and looks for local test leftovers.
Skill Codex
A design guide for interfaces used by smart-mining, geology, mining-dashboard, and AI-copilot products. It applies an approved teal-and-green mining visual style and interaction pattern.
Skill Codex
Use when evaluating an Agent product or proposed Agent product for harness maturity, including MVP readiness, mid-stage improvement direction, full-form harness completeness, OpenHarness-style benchmark comparison, AI PM self-checks, PRD/design review, and recommendations for making an Agent product more usable…
Skill Claude CodeCodex
A tool for creating images for WeChat public-account articles, including cover images, illustrations, and infographics. It can use AI image generation or HTML rendering when text needs to be exact.
Skill Codex
A general-purpose guide for writing and revising natural Chinese content, from forum posts and explainers to news analysis, tutorials, stories, and speeches. It emphasises clear context, a human voice, and fact checking for real-world material.
Skill Claude Code
An editing guide for removing common signs of AI-generated writing and making text sound more natural. It checks for patterns such as exaggerated claims, vague attribution, repetitive structures, and promotional language.
Skill Claude CodeCodex
A helper that turns article or section content into plans and prompts for consistent 16:9 infographics. It decides how many images are needed, what each should explain, and how to keep the text brief and readable.
Skill Claude CodeCodex
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
Skill Claude CodeCodex
A writing guide for producing long Chinese articles for WeChat public accounts. It covers how to understand source material, choose a topic, and decide which writing tasks AI should handle.
Skill Claude CodeCodex
When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' 'product update,' 'how do I launch this,' 'launch checklist,' 'GTM plan,' or…
Skill Claude CodeCodex
A guide for turning a short idea into a detailed task brief that an AI agent can carry out independently. It can split work between agents and includes checks for scope, evidence, acceptance, and resuming interrupted work.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: