Not in the top 1,000 by GitHub stars
eugeniughelbur/doceo
Claude Code skill that teaches you anything in one screen: visual lessons with memory and a feedback loop
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c99d933127b → 4c99d933127b
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c99d933127b
No earlier version was observed for comparison.
17GitHub stars
1star in 7 days
1skill in this repository
3commits in 30 days
Heat
2.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- doceo
/
How it works
doceo
When your agent uses it
Turn anything the user wants to learn into a short, visual, plain-language teachable artifact (one HTML lesson page + a markdown lesson note), calibrated to what they already know and improving with every use. Use when the user runs /doceo, says "teach me X", "I don't understand X", "explain this simply", "make this teachable", or is clearly drowning in a too-technical explanation.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
2,304 tokensWhen the skill is activated
Reference documents
4,121 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 0. Bootstrap (every run, cheap)
- 1. Resolve the input
- 2. Calibrate before writing
- 3. The lesson — structure is fixed, length is capped
- 4. Produce the two artifacts
- 5. Update the memory (every lesson, no exceptions)
- 6. The improvement loop (this is what makes doceo get better)
- 7. Report
Files
LICENSEasset1,072 bytesREADME.mddoc12,928 bytesSKILL.mdcore9,515 bytesSKILL.mdcore9,515 bytesdocs/screenshots/.gitkeepasset0 bytesdocs/screenshots/example-01-llm-a.pngasset134,490 bytesdocs/screenshots/example-01-llm-b.pngasset147,711 bytesdocs/screenshots/example-02-oauth.pngasset157,219 bytesdocs/screenshots/example-03-webhooks.pngasset129,904 bytesdocs/screenshots/example-04-repo.pngasset153,877 bytesdocs/screenshots/example-05-folder.pngasset146,512 bytesdocs/screenshots/example-06-config.pngasset167,321 bytesdocs/screenshots/example-07-task.pngasset142,566 bytesdocs/screenshots/example-08-theory.pngasset148,157 bytesdocs/screenshots/example-09-error.pngasset162,592 bytesdocs/screenshots/example-10-bare.pngasset148,381 bytesdocs/screenshots/lesson-page.pngasset480,445 bytesllms.txtdoc1,608 bytesreferences/claritas.mddoc2,373 bytes
Read SKILL.md
# Doceo — "I teach" (Latin)
Doceo turns anything into a lesson, never a book. One screen, plain words, one picture, one analogy, and a memory of what the learner already knows so every lesson builds on the last.
Core promise: **the learner should never have to reread.** If a lesson needs rereading, it failed.
## 0. Bootstrap (every run, cheap)
1. Read the machine config at `~/.doceo/config.json`:
```json
{ "memory_root": "/absolute/path/to/lessons/folder", "learner": "Name" }
```
2. If the config does not exist, this is a first run:
- Ask the user ONE question: "Where should I save your lessons? (folder path — an Obsidian vault folder works great)". Offer `~/doceo-lessons` as the default.Skills included
- doceo
Repository facts
- License
- MIT
- Created
- Jul 3, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 2
- Open issues
- 1
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 18 network referencesin 2 files: README.md:8 llms.txt:5
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 18 signals by file
README.md
- Network accessline 8
/doceo what is an LLM? /doceo how does OAuth actually work /doceo https://github.com/some/repo - Network accessline 9
/doceo how does OAuth actually work /doceo https://github.com/some/repo /doceo src/services/billing/ - Network accessline 10
/doceo https://github.com/some/repo - Network accessline 73
git clone https://github.com/eugeniughelbur/doceo ~/.claude/skills/doceo - Network accessline 120
/doceo https://github.com/fastify/fastify - Network accessline 187
<p align="center"> Built by <a href="https://github.com/eugeniughelbur"><strong>Eugeniu Ghelbur</strong></a> · AI Automation Engineer shipping agents in production<br /> - Network accessline 188
Built by <a href="https://github.com/eugeniughelbur"><strong>Eugeniu Ghelbur</strong></a> · AI Automation Engineer shipping agents in production<br /> - Network accessline 202
<a href="https://x.com/eugeniu_ghelbur"><img src="https://img.shields.io/badge/Follow_on_X-000?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X" /></a> - Network accessline 203
<a href="https://www.linkedin.com/in/eugeniu-ghelbur/"><img src="https://img.shields.io/badge/Connect_on_LinkedIn-0A66C2?style=for-the-badge&logo=data:image/svg%2Bxml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9Ij - Network accessline 204
<a href="https://theaioperator.io"><img src="https://img.shields.io/badge/Subscribe_on_Substack-FF6719?style=for-the-badge&logo=substack&logoColor=white" alt="Subscribe on Substack" /></a> - Network accessline 205
<a href="https://github.com/eugeniughelbur"><img src="https://img.shields.io/badge/Follow_on_GitHub-181717?style=for-the-badge&logo=github&logoColor=white" alt="Follow on GitHub" /></a> - Network accessline 207
<em>More from the same stack: <a href="https://github.com/eugeniughelbur/obsidian-second-brain"><strong>obsidian-second-brain</strong></a>, the living second-brain vault doceo plugs into.</em> - Network accessline 260
MIT. Built by [Eugeniu Ghelbur](https://theaioperator.io), an AI automation engineer shipping agents in production. More AI-builder tools and write-ups at [theaioperator.io](https://theaioperator.io).
llms.txt
- Network accessline 5
Key facts: - Type: Claude Code skill (works in Claude Code CLI, desktop app, and IDE extensions) - Install: git clone https://github.com/eugeniughelbur/doceo ~/.claude/skills/doceo - Network accessline 6
- Type: Claude Code skill (works in Claude Code CLI, desktop app, and IDE extensions) - Install: git clone https://github.com/eugeniughelbur/doceo ~/.claude/skills/doceo - Command: /doceo <topic | file | folder | URL>, or bare /doceo to tea - Network accessline 7
- Install: git clone https://github.com/eugeniughelbur/doceo ~/.claude/skills/doceo - Network accessline 11
- Theming: optional _style.md lets lessons render in the learner's own design system - License: MIT - Author: Eugeniu Ghelbur, https://theaioperator.io - Network accessline 13
- Author: Eugeniu Ghelbur, https://theaioperator.io
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 18 facts
- Network access in code of documentationREADME.md:8Low confidence
- Network access in code of documentationREADME.md:9Low confidence
- Network access in code of documentationREADME.md:10Low confidence
- Network access in code of documentationREADME.md:73Low confidence
- Network access in code of documentationREADME.md:120Low confidence
- Network access in prose of documentationREADME.md:187Low confidence
- Network access in prose of documentationREADME.md:188Low confidence
- Network access in prose of documentationREADME.md:202Low confidence
- Network access in prose of documentationREADME.md:203Low confidence
- Network access in prose of documentationREADME.md:204Low confidence
- Network access in prose of documentationREADME.md:205Low confidence
- Network access in prose of documentationREADME.md:207Low confidence
- Network access in prose of documentationREADME.md:260Low confidence
- Network access in prose of documentationllms.txt:5Low confidence
- Network access in prose of documentationllms.txt:6Low confidence
- Network access in prose of documentationllms.txt:7Low confidence
- Network access in prose of documentationllms.txt:11Low confidence
- Network access in prose of documentationllms.txt:13Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
