AI & ML

kelvinchenof Bundle

Writing, exploit — shape raw material into an article, paragraph by paragraph.

kelvinchenof Bundle

A relentless interview that asks every frontier question at once, round by round.

kelvinchenof Bundle

Hand the current conversation off to a fresh background agent that picks up the work immediately.

kelvinchenof Bundle

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

kelvinchenof Bundle

Writing, explore — mine raw fragments, no structure yet.

kelvinchenof Bundle

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

kelvinchenof Bundle

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

kelvinchenof Bundle

Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

kelvinchenof Bundle

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

kelvinchenof Bundle

Use when a user explicitly requires whole-task implementation before any tests, builds, linters, type checks, or manual runtime checks; when testing every module is unwanted; or when one unified validation pass is required.

skyllwt Skill

交互式 API key 配置引导 — 检测当前 .env 状态，逐步引导配置 Semantic Scholar、DeepXiv 和 Review LLM

skyllwt Skill

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

skyllwt Skill

多源 novelty 验证：WebSearch + Semantic Scholar + wiki + Review LLM cross-verify，输出 novelty 评分与建议。可选 --write，把分数写回 idea 页面。

skyllwt Skill

实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 linked idea 的 status / failure_reason 与 graph edges

skyllwt Skill

解析审稿意见 → 原子化 concerns (Rvx-Cy) → 映射到 wiki ideas/methods → 检查 evidence → Review LLM stress-test → 生成 rebuttal

skyllwt Skill

从 idea graph 编译论文大纲：编译 evidence map → 叙事结构 → 章节计划 + figure plan + citation plan，Review LLM review 必选

yigityildiz0 Bundle

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools.

hassaan146 Bundle

Prevents post-deployment failures by fixing their root cause during the build, not after launch. Use whenever scaffolding, building, or reviewing an app, API, or backend that will be deployed and handed to a client or put into real use. Covers the 8 categories of post-deployment breakage and maps each to the build-time decision that causes it: infrastructure/hosting hygiene, database/schema drift (indexes, pagination, migrations), dependency rot, AI/LLM output and cost decay, scale and concurrency bugs (race conditions, N+1 queries, missing transactions), third-party integration breakage, usage/cost limits, and handoff documentation. Trigger this any time the user is building something meant to go to production or to a client, asks how to make an app 'not break after deployment', 'keep working', be 'maintainable', or mentions post-deployment issues, app maintenance, production failures, or client handoff.

jeremylongshore Bundle

Validate a Claude Code plugin directory against the official Anthropic spec and Intent Solutions enterprise standard. Runs structural validation (plugin.json fields, file references, permissions) and content validation (SKILL.md grading, command/agent frontmatter). Use when building a new plugin, preparing for marketplace submission, or auditing existing plugins. Trigger with "validate this plugin", "check plugin structure", "grade my plugin", "/validate-plugin".

jeremylongshore Bundle

Uses Xquik from Hermes Agent for X research, monitoring, and approval-gated actions. Use when the user requests X data or an approved X action. Trigger with "search X", "monitor X", "post tweet", or "X trends".

carlkibler Bundle

Run a multi-agent pre-mortem that returns ranked risks and mitigations.

carlkibler Bundle

Create a personal AI profile, working guide, and compact assistant prompt.

carlkibler Bundle

Run repeatable multi-LLM hardening sweeps: review, fix, document, repeat.

carlkibler Bundle

Run a bounded independent code review with the opposite-company model first, complete git scope context, and a same-company fallback.

carlkibler Bundle

Analyze Claude/Codex logs for behavior patterns, repeated friction, and Toolsmith gaps.

carlkibler Bundle

Run multi-model brainstorming for product strategy and experience design.

cbusillo Bundle

Use when the user explicitly asks about local LLMs, LM Studio, local model inventory, local model chat, local model benchmarking, model role curation, or configuring private/local model endpoints. Provides public-safe mechanics and model index guidance for locally hosted or trusted-network OpenAI-compatible models without deciding when other domain skills should use a local model.

cbusillo Bundle

Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Supersedes docs-lookup for OpenAI-specific questions. Do not use for generic app/software tasks that merely mention Codex.

cbusillo Bundle

Use when a change should be reviewed by a model from another provider, or when the user asks for a second opinion, an independent or outside review, dissent, or a Gemini, GPT, or Claude review of work. Covers shared agent instructions, approval and safety rules, destructive helpers, and contracts other repositories depend on. Runs OpenAI, Anthropic, and Google models read-only against a repository and says how to weigh what they return without adding edge cases nobody can produce. Do not use for ordinary code review of tested code, a human reviewer's comments, or type-checker and scanner output.

yigityildiz0 Skill

Reference for nimble agent commands. Load for Step 0 agent lookup. Contains: full agent table (50+ sites across e-commerce, food, real estate, jobs, social.

yigityildiz0 Bundle

Convert Claude Code agent-kit setups into Codex-compatible skills, project instructions, guardrail scripts, command workflows, subagent guidance.

05-deepak-patidar Skill

Building production features powered by LLMs — model selection, prompt design as engineering, structured output, RAG, evals, cost/latency budgets, and guardrails. Use when adding AI features to a product (chat, extraction, summarization, classification, search), designing prompts that ship to production, building RAG pipelines, or when the user says "LLM feature", "integrate AI", "prompt engineering", "RAG", "embeddings", or "evals".

05-deepak-patidar Skill

Designing and building AI agents — tool design, agent loops, context management, permissions/guardrails, memory, multi-agent orchestration, MCP, and agent evaluation. Use when building an agent that takes actions (calls tools/APIs, writes files, automates workflows), designing tool schemas, debugging agent misbehavior, or when the user says "AI agent", "agentic", "tool calling", "function calling", "MCP server", "autonomous", or "multi-agent".

05-deepak-patidar Skill

Schema design, data modeling, migrations, and query correctness for relational databases (and when to use non-relational). Use when creating or altering tables, designing schemas, writing migrations, modeling money/inventory/ledgers, adding indexes, or when the user says "schema", "data model", "migration", "database design", or "normalize".

05-deepak-patidar Skill

Getting reliably high-quality software out of ANY AI model (Claude, GPT, Gemini, local models) — task packaging, context, verification, and drift control. Use when delegating coding work to an AI model, writing prompts/specs for AI-driven development, reviewing AI-generated code, setting up CLAUDE.md/AGENTS.md-style project instructions, or when the user says "have the AI build", "prompt for", "why did the model do this wrong", or "AI code review".

05-deepak-patidar Skill

Security-first development and review. Use when building or reviewing auth, sessions, payments, file uploads, user input handling, multi-tenant data access, secrets, APIs exposed to the internet, or when the user says "security", "vulnerability", "harden", "pentest", or before any production launch. Applies to defensive work on systems the user owns.