Coding & Dev Tools

zhaji2333 Skill

当payload被拦截、请求被WAF/过滤/403拒绝、连续多次payload失败、需要绕过黑名单/白名单/正则/语义分析防御时调用。负责编码/变形/逻辑/协议层绕过、换入口、组合利用与时间维度攻击的完整升级路径。

zhaji2333 Skill

当目标为 Windows PE 程序（EXE/DLL/SYS/驱动）、.NET 程序、Windows 服务、内核组件，或需要静态/动态逆向分析挖掘缓冲区溢出、远程命令执行、权限提升、信息泄露、拒绝服务等二进制漏洞时调用。负责反汇编/反编译分析、内存破坏漏洞挖掘、协议逆向、反调试对抗、漏洞利用链构造、shellcode 编写与 PoC 验证。

itspecialist111 Skill

design/canvas — skill payload

itspecialist111 Skill

dev/skill-creator — skill payload

itspecialist111 Skill

dev/webapp-testing — skill payload

itspecialist111 Skill

design/theme-factory — skill payload

itspecialist111 Skill

dev/changelog-generator — skill payload

itspecialist111 Skill

productivity/file-organizer — skill payload

itspecialist111 Skill

productivity/tailored-resume — skill payload

kryptobaseddev Skill

Replace me. One sentence on what this skill does and when to use it.

adesolaodubiyi Skill

One-question-at-a-time design grilling. Ask a single targeted question, wait for the answer, push back like a senior engineer if the answer introduces risk or ambiguity, then continue. Use inside design sessions to stress-test decisions before locking them.

adesolaodubiyi Skill

Structured implementation loop for any non-trivial feature, tool, or change. Use when you have a spec, ticket, or clear requirement and need disciplined execution: confirm context, search best practices with cited sources, lock architecture before coding, TDD vertical slices, review loop, ship. Use instead of coding directly whenever the feature touches more than one layer or requires any design decision.

adesolaodubiyi Skill

Activate when designing, building, or reviewing any user-facing feature, interaction, screen, or flow. Forces product thinking before and during implementation.

adesolaodubiyi Skill

Iterate on AI PR review feedback until all comments are addressed or the cycle limit is hit. Use when the user says "loop on review", "address review comments", "keep going until reviewer is happy", "iterate on PR feedback", or any request to repeatedly fix AI reviewer comments. Works with any AI reviewer (GitHub Copilot, Cursor, Sidekick, etc.) — not tied to a specific tool.

adesolaodubiyi Skill

Write or rewrite a README for any project. Activate when user says: write a readme, create a readme, update the readme, document this project, write docs for this, readme for this.

adesolaodubiyi Skill

Activate when designing features, components, data flows, APIs, or system architecture at any scale. Also activate when refactoring large sections of code where the structure itself is in question, or when a proposed approach needs rigorous evaluation before implementation. Trigger phrases: "design this", "help me think through", "how should I architect", "what's the best approach for", "design review", "is this a good design", "let's design", "system design"

adesolaodubiyi Skill

Code cleanliness, maintainability, and best practices review before any merge. Activate when user says: review this code, cleanliness check, code quality review, check my code, review before merge, is this clean, maintainability review.

adesolaodubiyi Skill

Activate when generating or refactoring Python code that involves function signatures, models, interfaces, or typing decisions.

adesolaodubiyi Bundle

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

igrlebed Skill

Update the local Lazyweb skill pack from GitHub and reinstall Lazyweb skills into supported local coding clients and agentic IDEs. Use when the user asks to update Lazyweb, refresh stale Lazyweb slash commands, sync local skills, reinstall the skill pack, or make Codex/Claude/Cursor/OpenCode/Kiro/Factory/ Slate/Hermes pick up the latest Lazyweb skills.

igrlebed Skill

Critique and rewrite a paywall primary CTA (and adjacent microcopy) by reading the target screen, diagnosing CTA-level conversion friction, and producing ranked CTA candidates backed by Lazyweb's paywall CTA corpus, real before/after A/B observations, and divergent mechanism examples. Use when the user wants to evaluate, rewrite, or stress-test a paywall CTA — not a full paywall redesign.

igrlebed Skill

Capture a screenshot of the user's current design, find similar screens in Lazyweb, and generate concrete improvement ideas backed by real references. Use when the user has an existing design and wants feedback or improvement suggestions. Trigger on: "improve this design", "how can I make this better", "critique my design", "design feedback", "what should I change", "make this look better", "compare my design to", "design review".

igrlebed Skill

Optimize a mobile or web paywall by reading the target screen, diagnosing conversion friction, and producing 2-4 falsifiable redesign hypotheses backed by Lazyweb paywall references, experiment evidence, conventions, and divergent design moves. Use when the user wants to redesign, improve, critique, or optimize a paywall screen for paid conversion.

igrlebed Bundle

Builds and maintains product UX design specifications from a codebase (no implementation code in the doc). Use when the user asks for UX spec, design specification, CJM, user stories, screen map, gap analysis vs code, or to sync docs/UX_SPECIFICATION.md after feature changes — including narrated updates like "сделали X, обнови спеку".

igrlebed Skill

Cross-pollination design brainstorm. Deliberately searches outside the obvious category to find novel patterns that could be applied in unexpected ways. The "zig when everyone zags" skill — finds inspiration from domains nobody in your space is looking at. Trigger on: "brainstorm design ideas", "creative alternatives for", "design exploration", "what if we tried", "unconventional approach to", "fresh ideas for", "think outside the box", "surprise me".

iris-ymy Bundle

Create visualizations and interactive tools directly in conversation. Use when asked to show how something works, make simulators or labs, maps, plots, charts or graphs, comparisons, UI mockups, scenarios, adjustable inputs, and exploration beyond regular text.

iris-ymy Bundle

Host websites with Sites. Always use after `sites-building`, and use for website publishing, deployment, hosting management, or projects containing `.openai/hosting.json`.

iris-ymy Bundle

Use Sites to build websites, including landing pages, portfolios, dashboards, portals, trackers, hubs, and internal tools. Always use Sites when the project contains `.openai/hosting.json`.

iris-ymy Bundle

Diagnose and safely repair repeated Codex reconnecting, sampling-stream disconnects, WebSocket connection failures, or missing proxy inheritance on macOS or Windows. Use when Codex Desktop, ChatGPT Desktop's Codex surface, the IDE extension, or Codex CLI repeatedly reconnects or cannot reach chatgpt.com. Diagnose before changing settings and never guess a proxy port.

iris-ymy Bundle

Validate, package, and publish one or more Codex Skills or a Skill plugin through an explicitly selected GitHub repository and Draft PR. Use when the user asks to publish, share, open-source, back up, distribute, synchronize, or update Codex Skills on GitHub. Choose source collection versus installable Plugin delivery, keep confirmation efficient, and verify remote state.

mrwogu Skill

Systematically debug issues using graph-powered code navigation

mrwogu Skill

PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files. Use when working with PromptScript syntax, creating or editing .prs files, adding blocks like @identity, @standards, @restrictions, @shortcuts, @skills, or @agents, configuring promptscript.yaml, resolving compilation errors, understanding inheritance (@inherit) and composition (@use, @extend), or migrating AI instructions to PromptScript. Also use when asked about compilation targets (GitHub Copilot, Claude Code, Cursor, Antigravity, Factory AI, and 30+ other AI coding agents).

mrwogu Skill

Perform a structured code review using change detection and impact

mrwogu Skill

Plan and execute safe refactoring using dependency analysis

mrwogu Skill

Navigate and understand codebase structure using the knowledge graph

parvez3019 Bundle

Write the persistence layer so it is correct under concurrency and fast under load. Covers repository implementations that return domain types, ORM discipline and the N+1 problem, explicit transaction boundaries and isolation levels, optimistic and pessimistic locking, connection pool sizing, keyset pagination, indexing and query plans, batching, caching with a defined invalidation story, and zero-downtime schema migrations. Use when writing a repository, a query, a migration, or a caching layer, when diagnosing a slow or deadlocking query, or when the user says 'repository', 'ORM', 'query', 'N+1', 'transaction', 'migration', 'index', 'connection pool', or 'lock'. This skill governs how data is stored and fetched — the shape of domain types belongs to domain-modelling, read models and consistency to cqrs-and-consistency.