agentleFS
70asunflower70asunflower/70asunflower-skills/captain-resource/SKILL.md

captain-resource

Skill1 starsChanged 13 days agoMITView on GitHub

Add a new resource (link/article/external material) to one of the three learning repositories: ai-learning-journey, embodied-ai-learning, or ic-chip-design-learning. Trigger whenever the user provides a URL or asks to save a resource to their learning repos, or mentions adding content to these directories. Do this for any resource the user wants to catalog — tutorials, docs, videos, tools, papers — regardless of domain. When in doubt about which repo, ask the user.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add a URL or resource to the correct learning repository following the 3-place update pattern.

    line 8
  2. Distinctive:

    If unsure, ask the user. If a link fits multiple repos (e.g., CUDA touches both AI and IC design), add it to all applicable repos.

    line 20
  3. Very specific:

    Create a .md file in the chosen subfolder.

    line 59
  4. Distinctive:

    Add a row to the table in the subfolder's README.md:

    line 91
  5. Very specific:

    Add an entry to 0-Resources/0-Index.md.

    line 112
  6. Very specific:

    All three repos are git repositories under P:\my_project\.

    line 116
  7. Distinctive:

    If push fails due to remote changes, git pull --rebase and push again.

    line 125
  8. Distinctive:

    Frontmatter tags: should be short English keywords (the same tags appear in both README table and .md file)

    line 133

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Captain Resource

Add a URL or resource to the correct learning repository following the 3-place update pattern.

Step 1: Choose the right repository

Three repos exist under P:\my_project\(P: 为可移动/网络盘——未挂载时先挂载,盘符以实际为准). Pick the best match:

RepoFocus
ai-learning-journey/LLMs, agents, prompts, AI frameworks, official docs
embodied-ai-learning/Robotics, VLA, sim-to-real, Isaac Sim, MuJoCo, ROS2
ic-chip-design-learning/GPU/CUDA, RTL, EDA tools, IC design, hardware architecture

If unsure, ask the user. If a link fits multiple repos (e.g., CUDA touches both AI and IC design), add it to all applicable repos.

Step 2: Choose the right subfolder

Each repo has 0-Resources/ with different categories. Check the subfolder structure below and pick the best match. The naming convention is the same across all repos — each subfolder has a README.md with a table of existing resources.

ai-learning-journey

SubfolderContent
1-Official-Docs/Official docs, best practices
2-Papers/Research papers
3-Tutorials/Tutorials, blogs, courses
4-Tools-Frameworks/Tools & frameworks
5-Datasets/Datasets

embodied-ai-learning

SubfolderContent
1-Papers/Important papers
2-Frameworks-Tools/Frameworks & tools
3-Datasets/Datasets
4-Tutorials-Courses/Tutorials, blogs, courses
5-Projects-OpenSource/Open-source projects

ic-chip-design-learning

SubfolderContent
1-Books/IC design textbooks
2-Papers/Research papers
3-EDA-Tools/EDA tools
4-OpenSource-Projects/Open-source projects
5-Courses-Tutorials/Courses & tutorials
6-Industry-Standards/AMBA, UCIe, JEDEC, etc.

Step 3: Create the resource file

Create a .md file in the chosen subfolder. Naming: lowercase, hyphen-separated (e.g., cuda-programming-guide.md).

Start with frontmatter:

---
source: <original URL>
date: YYYY-MM-DD
tags: [tag1, tag2, tag3]
---

# Title

## 核心要点(摘要)

Brief summary in Chinese.

## 详细内容

Key points, topics, what this resource covers.

## 个人备注

Why you're saving it, how it connects to your learning goals.

_Last updated: YYYY-MM-DD_

Adjust headings based on content type (e.g., "主要内容" for docs, "核心贡献" for papers). Keep content bilingual or Chinese as the user prefers.

Step 4: Update the subfolder README.md

Add a row to the table in the subfolder's README.md:

| [Resource Name](filename.md) — one-line description | `#tag1 #tag2 #tag3` | YYYY-MM-DD |

Step 5: Update the main README.md wiki navigation

Find the matching <details> section in the root README.md and add the link. All repos use <details open> for most sections. Example:

<details open>
<summary>4-Tutorials-Courses</summary>

- [Resource Name](0-Resources/4-Tutorials-Courses/filename.md) — one-line description

</details>

Step 6: Update 0-Resources/0-Index.md

Add an entry to 0-Resources/0-Index.md. The format varies slightly by repo — follow the existing pattern (usually a table row or link under the relevant section).

Step 7: Commit and push

All three repos are git repositories under P:\my_project\. Before running any git command, always cd into the correct repo first — don't run git from P:\my_project itself.

cd <repo-name>  # ai-learning-journey, embodied-ai-learning, or ic-chip-design-learning
git add <changed files>
git commit -m "Add <resource name> to <category>"
git push

If push fails due to remote changes, git pull --rebase and push again.

Key rules

  • File names: lowercase, hyphen-separated
  • Every new file gets linked in: subfolder README → main README wiki nav → 0-Index.md
  • Last updated footer on every resource file
  • Chinese descriptions preferred, bilingual OK
  • Frontmatter tags should be short English keywords (the same tags appear in both README table and .md file)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.