Skills for Real Engineers. Straight from my .agents directory.
oma-explanation
Agent skill fromfirst-fluke/oh-my-agent
Create an offline HTML explanation of a code change (diff, PR,
How to install oma-explanation
npx skills add first-fluke/oh-my-agent# or add only this skill to Claude Code: copy the folder
skills/oma-explanation/
# into
~/.claude/skills/oma-explanation/ (all projects)
.claude/skills/oma-explanation/ (one project)
1# oma-explanation — Interactive HTML Explainer23## Scheduling45### Goal6Generate an educational, self-contained interactive HTML document, saved under7`.agents/results/explain/` and validated against a deterministic checklist. Two modes:89- **Change mode** — explains a code change: deep skippable background for newcomers, core10 intuition with toy data, a comprehension-ordered code walkthrough, and a five-question quiz.11- **Topic mode** — explains a concept, a system, or the answer to a question as a one-page12 visual sheet: lead answer, then panels of diagrams, tables, and short prose.1314In both modes the model writes a Markdown **draft** and `oma explain render` produces the HTML.15Layout, theme, diagram geometry, and the quiz script are the renderer's, not the model's.1617### Intent signature18- User invokes `/explain`, names this skill, or asks for a rich explanation/walkthrough of a19 diff, PR, branch, or commit range (설명서, 해설, コード解説, 代码讲解).20- User asks for a visual / HTML explanation of a topic that is not a diff: how a system works,21 a comparison, an answer worth keeping as a page (`/explain how does the row planner work`).22- Another skill or workflow delegates "explain this as a document" output.23- Activation is slash/explicit/delegated only — this skill is intentionally excluded from24 keyword auto-detection ("explain" is everyday vocabulary; `convert` precedent).2526### When to use27…
Excerpt shown under the repository's MIT license.
More skills in oh-my-agent
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
