Learn how a project, work area, or technical system works through spoken interactive lessons, source-based explanations, and quizzes. Quizzes can revisit earlier gaps and check what has changed, helping you explain or apply the material yourself.
Keeps the principal current on the fundamentals of what is going on in the principal's projects, work and technical infrastructure: spoken interactive lessons on the conversation topic, deep explanations of an area's fundamentals read fresh from live sources, and quizzes that remember what the principal missed. USE WHEN teach me, /tm, /teach-me, tutorial, teach me this, walk me through this interactively, learn mode, quiz me, help me actually understand what we just did, explain fundamentals, /ef, what are the fundamentals of, how does this project actually work, catch me up on, refresh me on, quiz fundamentals, /qf, quiz me on the fundamentals, test what I know about, am I still current on. NOT FOR elaborating my last answer (the elaborate shortcut), the LifeOS core pitch (lc), story explanations of content (StoryExplanation), designed visual maps (Visualize), discovery interviews on a half-formed idea (/discuss).
Run score Not tested
See how to installExplain helps you learn topics from a conversation through spoken, interactive lessons. It breaks an explanation into concepts, asks questions along the way, and ends with a short quiz and review. You can also ask about a project, work area, or technical system even if it was not discussed in the current conversation. For those explanations, the skill reads current sources and describes key parts of how the system works, related flows, and recent changes. Quizzes ask application questions and focus on topics you previously missed or changes since your last check.
Use it to revisit a technology you encountered while working, understand the broader shape of a project you support, or check whether you can explain and apply a topic in your own words. It can help you go beyond reading an explanation by testing what you understand.
First-time setup for spoken lessons requires a voice server and a Fish key. Explanations and quizzes about projects or work areas consult sources current at the time of use.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 28, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Keeps the principal up on the fundamentals of what is going on across the principal's projects, work and technical infrastructure, deeply and thoroughly. The principal lives inside many systems at once and cannot hold all of them in mind, so this skill teaches the topic in front of them, explains the parts of any area that it cannot lose, and quizzes the principal so gaps show up before they cost anything. It absorbed the Teach skill on 2026-10-16, when the principal asked for these intents and for any existing teaching skill to be merged in rather than duplicated.
| Intent | Trigger | File |
|---|---|---|
| Teach | "teach me", "/tm", "/teach-me", "tutorial", "quiz me" on what we just covered | Intents/Teach.md |
| ExplainFundamentals | "/ef", "explain the fundamentals of", "catch me up on", "how does X actually work" | Intents/ExplainFundamentals.md |
| QuizFundamentals | "/qf", "quiz me on the fundamentals of", "test what I know about", "am I still current on" | Intents/QuizFundamentals.md |
| File | Read when |
|---|---|
Setup.md | first-time setup: the voice server and Fish key the spoken narration needs, and a read-only check |
Teach works on the conversation topic as a spoken dialogue. ExplainFundamentals and QuizFundamentals work on a standing area (a project, a work stream, a system) whether or not we touched it this session, and share one set of fundamentals per area so the quiz tests what the explanation taught.
e shortcut is not this skill. It explains my last answer more, and more simply; /ef explains an area's fundamentals.Example 1: Teach the thing we just built
User: "teach me" (after a session debugging DNS records)
→ Teach intent
→ Spoken intro, a concept map of 3-5 ideas, one beat and one question per turn
→ Ends with a 2-3 question quiz and a recap diagram
Example 2: Explain an area's fundamentals
User: "/ef billing service"
→ ExplainFundamentals intent
→ Reads its projects-table row, the project ISA and its code layout this session
→ The fundamentals by the "without X it can no longer ___" test, each with what it connects to, one flow diagram, what changed lately
Example 3: Quiz on fundamentals
User: "/qf home network"
→ QuizFundamentals intent
→ Reads the live sources and the learning record, asks 5 application questions one per turn, weighted to past misses
→ Each answer gets a verdict against the source and is appended to the STATVS learning stream
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find and fetch vendor cybersecurity reports, then compare their findings on topics such as ransomware, breaches, cloud security, and AI. Analyses identify the reports consulted and cite each figure by vendor, year, and report, including where sources disagree.
Compare a component's own design needs with the goals of the larger system through three structured passes. The result identifies conflicts, recommends an appropriate scope, and assesses whether the proposed design fits the whole.
Find quotes that fit a text’s themes, with attribution and a short reason for each suggestion. Add sourced quotes, research thinkers, and organize a quote collection by theme and usage history to avoid repetition.
Create blog illustrations, technical diagrams, comparisons, comics, and icons through workflows tailored to each format. The skill guides composition, color, and model selection, then stages generated images for review before they are used in a project.
Assess the visual quality of images, films, slides, and site captures against a brief and craft criteria. Two vision judges score the work and rank defects, guiding bounded revision; delivery is gated on a passing critique, with human calibration labels recorded separately.
Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.