Individual skill
learn-core
帮助用户学习新领域、技能或资料,并通过主动练习学到能独立应用。用于学习冲刺、AI家教、费曼倒讲、练习提速、学习作品评审和间隔续学;以可验收目标、核心拆解和真实作答证据推进。普通事实查询、纯资料摘要或代做项目不要强行改成课程。
plugins/everclear077/codex-learning-plugin/skills/learn-core/SKILL.md
Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,531
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-coding Repository topic
- awesome Repository topic
- awesome-list Repository topic
- codex Repository topic
- codex-plugins Repository topic
- openai Repository topic
- codex-skill Repository topic
- codex-skills Repository topic
- marketplace Repository topic
- codex-marketplace Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 6,460 bytesagents/openai.yamlasset · 337 bytesreferences/modes.mddoc · 4,956 bytesreferences/progress.mddoc · 2,879 bytesreferences/spaced-recall.mddoc · 3,886 bytesreferences/teaching.mddoc · 5,422 bytesreferences/方法梳理与溯源.mddoc · 17,331 bytesscripts/export_anki.pyruns · 4,016 bytes
Read excerpt
# 学习
目标是用最少必要投入建立与用户目标相符的、可验证的能力。默认中文,跟随用户语言。20小时是冲刺预算;不保证20小时精通,不把生成材料等同于用户学会。
## 首次启动
1. 从对话提取主题、用途、基础、可用时间、交付物。只问真正影响下一步的缺失信息,最多3项,避免重复问已知内容。只有主题时,先给可调整的一句话目标和30分钟首课假设,马上开始首个诊断问题,不等待一份完整个人档案。
2. 把目标写成「在什么条件下,独立完成什么,按哪些标准验收」。定2–4条客观标准。预算与目标不相称时明确缩小范围或标出不可完成部分,不暗中降低标准。
3. 首轮列5–9个核心概念/子技能,按目标贡献、必要依赖和练习成本排序;每项连接到作品或验收题。列必要前置及3–5项「现在故意不学」。很小的主题允许少于5项;广阔领域分批,不展示几十项待学目录。80/20是取舍启发,不是测得比例。
4. 为眼前第一块准备足够且可信的材料,不先做完全部研究或整套课程。概念卡只需直觉、准确机制/条件、一个例子、常见错因、来源。需要最新/专业事实时查原始论文或官方资料;用户材料优先,但核查冲突、版本和缺失范围。初始核心资源通常2–4项,说明各解决什么问题。必要前置、疑点和来源分开标记。
5. 按预算安排短循环和最小交付物,主动练习目标占大多数时间。学习计时只记用户实际确认的投入,AI检索耗时与猜测不当作已学时数。做20小时冲刺时在前4小时争取首版,18小时前进入收尾,20小时前验收;更短预算同比缩小作品。详细预算、适配与证据标准见[teaching.md](references/teaching.md)。
6. 用简短计划收束后立刻给一个诊断/练习问题并停下。不能在同一响应里自行回答、模拟用户或连续推进几轮。
## 每次会话的家教契约