7-e1even
Featured
learn-agent
A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It applies first-principles reasoning to diagnose real objectives and constraints, uses a stringent evidence policy for resource selection, and supports multiple AI agents (Codex, Claude Code, Gemini CLI) with a single core file, ensuring robust, privacy-respecting, and verifiable learning path generation.
Who it is for
- Self-directed learners seeking structured, evidence-based roadmaps
- Developers and AI enthusiasts who use agent tools for learning assistance
- Professionals preparing for certifications, career transitions, or skill acquisition
- Learners who want to avoid information overload and focus on actionable milestones
Use cases
- Design a 3-month roadmap to build a Python automation tool with specific weekly time constraints
- Plan a structured exploration sprint (e.g., 2 weeks) to decide if a new field like data analysis is worth pursuing
- Resume and re-optimize an existing learning plan from a saved schema v1 or v2 file, adjusting for actual progress
- Create a targeted exam preparation plan by clarifying official scope, diagnostic tests, and spaced review intervals
Strengths
- First-principles diagnosis: clarifies real outcomes, evidence, and constraints before any planning begins
- Evidence-based resource selection: only includes directly relevant, authoritative sources and rejects irrelevant or outdated material
- Cross-agent compatibility: works across Codex, Claude Code, Gemini CLI, and other agents via a single SKILL.md file
- Rigorous verification: includes pre-output checks, progress recovery, and a standardized contract validation test suite
Considerations
- Not a teaching tool: it plans and adjusts roadmaps but does not provide continuous step-by-step instruction
- Dependence on agent execution: the skill's effectiveness relies on the user's agent correctly installing and interpreting the skill file
- Requires clear goals: it is less suited for vague, open-ended exploration without any defined observable outcome or deadline
README quick start
安装
Description
从原点出发，无限逼近真知。目标驱动、证据导向、可验证、可迭代的学习路线规划 Skill。
Related repositories
Similar projects matched by category, topics, and programming language.
amitshekhariitbhu
Featured
ai-agents-tutorial
A comprehensive step-by-step tutorial series that teaches AI agents from scratch, covering function calling, agent loops, ReAct, reflection, plan-and-execute, multi-agent systems, orchestration, evaluation, and related concepts like RAG, GraphRAG, and LangChain.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.