Traced flow of data from source to sink through the program . Enables taint tracking , config value propagation tracing , and data provenance analysis

Documentation and capabilities reference for Mod

flowchart TD

>

design-shotgun

Use when turning any LLM into a structured research analyst. Comprehensive research prompt template.

Use when creating constitutional identity documents for agents. SOUL.md template with all required sections.

>

后台认知合成器（DMN等效，Headless）。不被用户直接触发，由后台调度脚本每3天执行一次。跨碎片关联分析：找到不同时间捕捉的碎片之间的隐性关联，生成合成报告写入L3，等待daily-briefing展示给用户。触发词（人工触发时）：「执行后台合成」「cognitive-background-synthesizer」。

置信度校准（元认知监控）。追踪L1文档和L2碎片中「AI生成/推断」的内容是否事后得到了验证，定期向用户提问「这段内容当时是AI推断，现在有没有实际证据？」。触发词：「验证历史内容」「校准知识置信度」「哪些内容还没验证」「cognitive-calibrate」。也被 cognitive-consistency-check 内部调用（月度维护）。

创造性发散（DMN+CEN协同等效）。遇到思路瓶颈时触发，从认知体系中随机抽取「表面不相关」的跨领域概念，强制寻找结构相似性，生成非常规解法候选列表。触发词：「没有思路」「换个角度想」「帮我发散一下」「有什么不同的方向」「反常识的方案」「跨领域看这个问题」「想不到解法」。

环境变量健康检查工具，扫描代码引用、检测硬编码密钥、验证格式

Generate LaTeX documentation for mathematical research. Use when creating papers, notes, or documenting formulas, proofs, and verification results.

Manage documentation topology and ownership metadata for codebases. Use when Codex needs to create or maintain docs/docs-config.json, inventory Markdown docs, assign doc status such as active/frozen/archived/generated, register topics, map canonical topic ownership, or validate frozen-doc constraints before editing.

讓 Codex/Claude 用固定流程操作履歷資料庫：

Use this skill when the user asks about basketball — NBA stats, player comparisons, fantasy advice, rules, play design, scouting, or coaching. Triggers: 'balltalk', 'basketball', 'NBA', 'who should I start', 'player comparison', 'fantasy basketball', 'basketball stats', 'is X better than Y', 'explain this play', 'basketball rules'. Pulls real stats via web search, compares players, gives fantasy advice, explains rules, and generates scouting reports. Do NOT use for: other sports, basketball video games, or basketball card collecting.

Use when the Apple setup flow needs to generate or align the final repo-local AGENTS.md after workspace, capability, config, and artifact decisions are settled.

Use when the Apple setup flow needs to apply or align README, SwiftLint, workflows, .gitignore, XcodeGen, and other snippet-backed repository artifacts after setup decisions are final.

从 git commit 历史自动生成人类可读的 CHANGELOG

Create, update, and audit SOUL.md, AGENTS.md, CLAUDE.md, and MEMORY.md from a PRD and the current repository state. Use when bootstrapping project governance, refreshing governance after PRD changes, or checking governance drift against the codebase.

Classify AI system risk under EU AI Act (Reg 2024/1689), generate Article 50 disclosures, and design conformity audit trails.

Implement GDPR (Reg 2016/679) data protection — DPIA templates, Art.30 processing records, data subject rights, legal bases, and cross-border transfers.

Generate SBOM (CycloneDX/SPDX), verify SLSA provenance, audit dependency chains, and detect supply chain attack patterns.

从源代码自动生成 Swagger/OpenAPI 3.0 文档

>-

You are a writing editor that identifies and removes signs of AI-generated text. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

从自然语言构建、解释和测试正则表达式

自动检测项目技术栈，生成 GitHub Actions workflow 及其他 CI/CD 配置

Use this skill when working with Groq. Triggers when user mentions Groq or imports from it.

It seems there is no documentation provided. Please provide the documentation content for me to generate the SKILL.md file. I will follow the exact format and create a complete SKILL.md based on the p

Onboard quickly by reading design docs, plans, READMEs, or the codebase to extract key concepts, surface gaps, and generate comprehension checks with answer keys. Includes an adaptive proficiency probe with learning resources and persistent session memory so the user can resume onboarding where they left off. Use when a user wants help understanding a project, validating their grasp of the architecture, or creating a readiness plan before contributing code.

自动检测技术栈，生成优化的 Dockerfile、docker-compose.yml 和 .dockerignore

Generate brand-consistent images using workspace styles and variables. Leverages existing brand guidelines for visual consistency.

Create a complete marketing campaign with product shots, model photos, multi-platform formats, and promotional videos.

Analyze any image, extract individual elements (characters, UI, icons, text, decorations), and generate isolated versions of each.

Generate professional product photography variations from a source image. Creates a workflow with multiple shots optimized for e-commerce and social media.

Create UGC-style video ads with AI-generated creators showcasing products. Builds a complete workflow with character creation, script writing, and video generation.

Create a short promotional video from a product image or concept. Generates a video using AI video models.

LTX-2.3 is a 22B parameter audio-video foundation model by Lightricks. It generates synchronized video AND audio in a single pass. Running on RTX 5090 (32GB VRAM) via ComfyUI Desktop. Uses DualCLIPLoa

Scaffold a new Express API route with auth, validation, and rate limiting following project conventions

<!-- PM-Workspace | Copyright 2026 CaufieldZ | Apache 2.0 + AI Training Restriction | 禁止 AI 训练/蒸馏 -->

Generate full CRUD operations for Hyper-Porto module.

Fix incorrect SKILL.md files when a skill has wrong instructions or outdated API references

Generate a complete semantic color token set from a brand palette. Produces surface, text, border, accent, feedback, and interactive state tokens.

explain-ve-pe-docs

Gerar e validar schema OpenAPI consumível por GPT Actions.

Use when making architectural or implementation decisions that affect upload privacy, server retention, logging, deployment configuration, and public release safety for the Lattes2BibTeX webtool.

skill-gen

Generate and schedule platform-adapted social media posts with brand-consistent voice. Use when the user needs social media content for Twitter/X or LinkedIn, wants to promote product announcements or blog posts on social platforms, needs a consistent posting cadence, or wants to track and analyze social engagement metrics.

Estimate development cost of a codebase based on lines of code and complexity