Skills Plugins MCP Prompt Model 博客 我的中心
Development #writing #security #ai

agentic-structure

Collaborative programming framework for production-ready development. Use when starting features, writing code, handling security/errors, adding comments, discussing requirements, or encountering knowledge gaps. Applies to all development tasks for clear, safe, maintainable code.

DeepseekModel Curated skill Quality Good · 48 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=backgwa-agentic-structure-plugins-skills-agentic-structure-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name agentic-structure description Collaborative programming framework for production-ready development. Use when starting features, writing code, handling security/errors, adding comments, discussing requirements, or encountering knowledge gaps. Applies to all development tasks for clear, safe, maintainable code. allowed-tools ["Read","Grep","Glob"] Agentic Structure Agentic Structure is a prompting framework designed to make programming more efficient. The core of this guideline is to collaboratively create projects and code together with users. Rather than planning and proceeding with everything independently, the goal is to achieve better results through mutual feedback based on given ideas and opinions. Additionally, the documentation includes good and bad practices, code style rules, and library usage guidelines, which should be referenced throughout the development process. Guideline Collection These are pull-when-needed references - read only what's relevant to your current task; there is no expectation to consume everything upfront. DEVELOPMENT_PROCESS.md - Principles for clear, safe, production-ready, maintainable development DISCUSSION_GUIDELINES.md - When and how to run discussions to reach aligned decisions SECURITY_GUIDELINES.md - Secure defaults for secrets, hashing, auth, and production exposure CODING_STANDARDS.md - Coding rules for clarity, structure, reuse, and maintainable change COMMENTING_GUIDELINES.md - Minimal, high-signal commenting rules and documentation boundaries ERROR_HANDLING.md - Error handling principles, boundaries, and security-minded failures KNOWLEDGE_SHARING.md - Knowledge request protocol for handling information gaps Guideline Selection Matrix Use this matrix to determine which guideline(s) to consult for your current task: Your Task Consult These Guidelines When to Apply Starting any feature implementation DEVELOPMENT_PROCESS.md Before writing any code - establishes workflow User request is unclear or ambiguous DISCUSSION_GUIDELINES.md Cannot determine single correct interpretation Need information beyond training data KNOWLEDGE_SHARING.md Require API docs, specs, or domain knowledge not in codebase Writing or modifying functions/classes CODING_STANDARDS.md Creating or changing code structure Deciding whether to add a comment COMMENTING_GUIDELINES.md About to write comment or user requests documentation Implementing error handling ERROR_HANDLING.md Adding try-catch, error checking, or failure paths Working with sensitive data or user input SECURITY_GUIDELINES.md Handling auth, secrets, file uploads, or external data Multiple valid implementation approaches exist DISCUSSION_GUIDELINES.md Need to present options with trade-offs Unsure about implementation scope DEVELOPMENT_PROCESS.md Need to determine what qualifies as "small step" Code becoming deeply nested or complex CODING_STANDARDS.md Exceeding nesting limits or complexity thresholds Error needs context or transformation ERROR_HANDLING.md Deciding how to handle caught exceptions Guideline Conflict Resolution When guidelines appear to conflict, apply in this priority order: 1. SECURITY_GUIDELINES.md (Highest Priority) Security always takes precedence If a security guideline conflicts with efficiency or simplicity, choose security Example: SECURITY requires input validation even if CODING_STANDARDS suggests avoiding unnecessary checks 2. DEVELOPMENT_PROCESS.md Process constraints and collaboration requirements Example: Must ask user before non-trivial decisions, even if CODING_STANDARDS suggests a clear approach 3. ERROR_HANDLING.md Correctness and proper failure handling Example: Must handle errors explicitly even if CODING_STANDARDS suggests simpler code 4. CODING_STANDARDS.md Code quality and maintainability rules Example: File organization and naming conventions 5. COMMENTING_GUIDELINES.md (Lowest Priority for Conflicts) Documentation style preferences Example: May add comments for security assumptions even if COMMENTING_GUIDELINES discourages them Conflict Resolution Example If CODING_STANDARDS suggests creating an abstraction but ERROR_HANDLING requires explicit error types for each layer, follow ERROR_HANDLING - create explicit error handling even if it means more code. When No Conflict Exists Most guidelines are complementary. Apply all relevant guidelines together: Use DEVELOPMENT_PROCESS for workflow Use DISCUSSION_GUIDELINES for user communication Use CODING_STANDARDS for code structure Use COMMENTING_GUIDELINES for documentation decisions Use ERROR_HANDLING for failure paths Use SECURITY_GUIDELINES for sensitive operations Use KNOWLEDGE_SHARING when information is missing For complete details on each guideline, read the full document. This Skill provides quick reference - consult the full guidelines when detailed guidance is needed.
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。