跳到正文
cccskills
免费在 GitHub 公开

create-learning-path

Use when asked to create a multi-session learning plan. Returns a milestoned plan, practice, and review rubric. Don't use for tasks that require source or remote-system changes.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md2.8 KB
  • agents/openai.yaml129 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Create learning path

Contract

FieldBound contract
TriggerCreate a multi-session learning plan.
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effectConversation artifact only.
DoneMilestoned plan, practice, and review rubric returned.

Inputs

Required inputs from the learner:

  • Learning goal: the skill or topic to master.
  • Current level: what the learner already knows or can do.

Optional inputs; request any that are absent:

  • Session count or total time budget.
  • Session length and cadence.
  • Constraints (materials, deadlines, prior gaps).

Procedure

  1. Collect the required inputs and any optional inputs the learner supplies. Ask for missing required inputs before proceeding; do not invent them. Done when: required inputs are collected or missing ones are requested.
  2. Decompose the goal into ordered milestones, each a demonstrable capability, sequenced so no milestone depends on a later one. Done when: milestones are ordered with no forward dependencies and each is a demonstrable capability.
  3. Map milestones onto the available sessions, respecting the session count, length, and cadence. If no budget is given, propose a default and label it as proposed. Done when: every milestone is mapped to a session within the stated or proposed budget.
  4. For each milestone, define one practice exercise that produces observable evidence the milestone was reached. Done when: each milestone has one practice exercise with observable evidence.
  5. Define a review rubric for each milestone with criteria that distinguish not-yet, partial, and met, so the learner can self-assess. Done when: each milestone has a rubric with not-yet, partial, and met criteria.
  6. Return the plan, practice, and rubric as a single conversation artifact. Done when: the plan, practice exercises, and rubrics are returned as one artifact.

Failure and recovery

  • Missing required input: stop and request it; do not fabricate a goal or level.
  • Goal too broad for the stated budget: report the mismatch, propose a narrowed scope, and let the learner confirm before continuing. Do not silently widen the budget.
  • No recovery action mutates files, credentials, or remote state. A partial result is returned only as an explicit incomplete plan with the missing milestone or rubric named.

Output

Return a conversation artifact with ordered milestones mapped to sessions, one practice exercise per milestone, and a review rubric with not-yet, partial, and met criteria for each milestone.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

af-xdp

免费

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

agents-md

免费

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy, or irreversible changes.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

查看 OutlineDriven 的全部技能

报告此技能的问题