Project Development
技能 已验证 活跃This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
To guide users in effectively starting, structuring, and iterating on LLM projects, ensuring task-model fit, efficient pipeline architecture, and cost-effective development.
功能
- Task-model fit analysis framework
- Canonical pipeline architecture patterns
- File system state management for pipelines
- Structured output design and parsing guidance
- Cost estimation formulas and tracking advice
- Agent-assisted development practices
使用场景
- Starting a new project that may benefit from LLMs
- Designing batch processing pipelines with structured outputs
- Evaluating task suitability for agents versus traditional code
- Estimating costs and timelines for LLM-heavy projects
非目标
- Providing specific code implementations for LLM models
- Acting as a general project management tool outside of LLM development
- Detailed tool design or multi-agent orchestration patterns (refer to other skills)
工作流
- Task Analysis: Define input/output, classify task, set error rate, estimate value.
- Manual Validation: Test one example, evaluate quality, identify failure modes, estimate tokens.
- Architecture Selection: Choose single/multi-agent, identify tools/data, design storage/caching, plan parallelization.
- Cost Estimation: Calculate tokens x price with buffer, estimate development time, identify infrastructure needs.
- Development Plan: Implement stage-by-stage, define testing strategy, set iteration milestones, plan deployment.
实践
- Task-Model Fit Recognition
- Pipeline Architecture Design
- Structured Output Design
- Agent-Assisted Development
安装
请先添加 Marketplace
/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering/plugin install Agent-Skills-for-Context-Engineering@context-engineering-marketplace质量评分
已验证类似扩展
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Write A Skill
100Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Extract
100Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
Chat Format
100Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
Wrap Up Ritual
100End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.