Moai Domain HTML Report
modu-ai/moai-adk
Markdown-to-single-file-HTML report renderer. An agent skill from modu-ai/moai-adk.
A skill your agent uses when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100…
Install Explainer Formats
$ npx skills add koolamusic/claudefiles --skill explainer-formats -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install koolamusic/claudefiles explainer-formats --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/explainer-formats .claude/skills/explainer-formats && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "explainer-formats" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formats into .claude/skills/explainer-formats/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer-formats", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formatsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add koolamusic/claudefiles --skill explainer-formats -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install koolamusic/claudefiles explainer-formats --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/explainer-formats .agents/skills/explainer-formats && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "explainer-formats" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formats into .agents/skills/explainer-formats/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer-formats", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add koolamusic/claudefiles --skill explainer-formats -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install koolamusic/claudefiles explainer-formats --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/explainer-formats .cursor/skills/explainer-formats && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "explainer-formats" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formats into .cursor/skills/explainer-formats/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer-formats", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/koolamusic/claudefiles.git --path skills/explainer-formats--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add koolamusic/claudefiles --skill explainer-formats -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install koolamusic/claudefiles explainer-formats --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/explainer-formats .gemini/skills/explainer-formats && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "explainer-formats" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formats into .gemini/skills/explainer-formats/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer-formats", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install koolamusic/claudefiles explainer-formatsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add koolamusic/claudefiles --skill explainer-formats -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/explainer-formats .github/skills/explainer-formats && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "explainer-formats" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formats into .github/skills/explainer-formats/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer-formats", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add koolamusic/claudefiles --skill explainer-formats -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install koolamusic/claudefiles explainer-formats --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/koolamusic/claudefiles.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/explainer-formats .opencode/skills/explainer-formats && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "explainer-formats" agent skill from https://github.com/koolamusic/claudefiles/tree/main/skills/explainer-formats into .opencode/skills/explainer-formats/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer-formats", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
explainer-formats- GitHub stars
- 130
- Token cost
- ~1.7k tokens
- SKILL.md length
- 971 words
- Files
- 14 (incl. scripts, references)
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100…
- Works in 5 steps: Read references/ste-rules.md. It has the… → Apply the level from the dial table. In… → Vocabulary authority: if… → …
- Asked to explain a topic
- SKILL.md covers Invocation, Escalation rule, Guardrails that apply at every… and The ste rung, plus 2 more sections
- Runs Python and Shell scripts from its folder; calls python3, bash and uv
What it does
Explainer Formats is an agent skill from koolamusic/claudefiles. Use when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100 with its controlled vocabulary and short procedural sentences), a diagram, a standalone HTML page, or a narrated video explainer. Triggers on "explain", "explainer", "simplified technical english", "STE", "plain language", "rewrite this so a technician can follow it", "diagram", "html page", "video explainer", or the /explain command. Picks…
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `references/diagram.md`, `references/html.md` and `references/ste-dictionary.md`).
It sits in Writing & Content, covering HTML artifacts and Plain language and style rules. The repository describes itself as: A minimal catalog of my favourite skills for working with claude. The licence is MIT.
When your agent uses it
- Asked to explain a topic
- Document in a specific output format — plain language
- Simplified Technical English (STE
- In the style of ASD-STE100 with its controlled vocabulary and short procedural sentences)
Example prompts
- “explain”
- “explainer”
- “simplified technical english”
- “/explainer-formats”
Requirements
- Python 3
- A Bash shell
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read references/ste-rules.md. It has the nine rule sections, the numeric limits, the verb forms table, the safety instruction format, and…
- Apply the level from the dial table. In one line each: light (default) reads like a careful technical writer, not a specification; 80…
- Vocabulary authority: if references/ste-dictionary-full.md exists, use it as the authority. Otherwise use references/ste-dictionary.md…
- Run the guardrails above as a checklist against the source before answering. Count the facts in the source; count them in the output.
- For strict output, optionally lint with the bundled checker
What it can do on your machine
Read from SKILL.md and the folder at commit 297c432. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 7 files in scripts/ (Python and Shell), which the agent can run.
Shell commands in SKILL.md call:
python3bashuv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Explainer Formats loads about 1.7k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 971 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from koolamusic/claudefiles at commit 297c432, republished under its MIT licence (© koolamusic). 971 words, ~1,746 tokens.
Download SKILL.mdSave it as
.claude/skills/explainer-formats/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.- name
- explainer-formats
- description
- Use when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100 with its controlled vocabulary and short procedural sentences), a diagram, a standalone HTML page, or a narrated video explainer. Triggers on "explain", "explainer", "simplified technical english", "STE", "plain language", "rewrite this so a technician can follow it", "diagram", "html page", "video explainer", or the /explain command. Picks the lowest format that answers the question and offers the next one.
Explainer formats
One command, four output formats (rungs), ordered from cheapest to most expensive:
| Rung | Output | Reference to load | Status |
|---|---|---|---|
ste | Prose rewritten in Simplified Technical English at a chosen strictness | references/ste-rules.md; references/ste-dictionary.md at strict (and for substitutions at 80%) | ready |
diagram | A Mermaid or SVG diagram of the mechanism, with an STE caption | references/diagram.md | ready |
html | A standalone explainer page, published as an artifact or a public page | references/html.md | ready |
video | A narrated Manim video, one scene per beat, published as an artifact player page | references/video.md; scripts/ pipeline run as uv run --project scripts python scripts/<file>.py | ready |
If a rung's reference file does not exist yet, say so in one line and fall back to the highest rung below it that is ready.
Invocation
/explain <topic> [--as ste|diagram|html|video] [--level strict|80|light]/explain is the explain command in ~/.claude/commands/; it loads this skill and passes its arguments through. Defaults: --as ste, --level light. <topic> is anything the reader points at: a question, a pasted paragraph, a file path, a function name, a feature. When the topic is a file or symbol, read it first and explain what is there, not what it is named.
Escalation rule
Pick the lowest rung that answers the question. A question about what something does is answered in prose (ste). A question about how parts connect, flow, or change state, where prose would run past two paragraphs, is where a diagram starts to pay for itself (diagram). A page is worth it when the explanation gains from interaction or side-by-side layout, or when the reader wants to keep it or share it outside this conversation (html). A video is the step above a page: build one only when the reader asked for it, or when a page would still leave the order of events unclear.
Always end the answer with one line that offers the next rung up, for example:
Want this as a diagram?
/explain <topic> --as diagram
From ste offer diagram; from diagram offer html; from html offer video; from video offer an edit to the narration, since there is no rung above it.
Never escalate silently. If the reader asked for --as html and prose would have done, still deliver the page and say so in that closing line.
Guardrails that apply at every level
These are not optional and they do not relax at light. A rewrite that reads well but drops a fact is a failure.
- Keep every fact, number, unit, caveat, condition, and domain term from the source. Hedges in the source ("usually", "unless the cache is cold") are facts; keep them.
- Never invent. If the source does not say why, the rewrite does not say why. If something is unclear, say it is unclear rather than guessing.
- Leave code, commands, flags, file paths, identifiers, error messages, and quoted output exactly as written. Do not rewrite them into prose, change their case, or "simplify" them.
- A domain term that is not an approved word stays in the text as written. Never swap it for a near-synonym. (At
strictonly, also declare it as a technical name on first use; see the rung below.) - One source of truth: when a fact appears twice in the source with different numbers, keep both and flag the conflict. Do not pick one.
Why this is strict: a published test of a prompt that said only "write this in ASD-STE100" lost 47% of the code-specific facts in the source (allaboutcoding.ghinda.com/explain-to-me-in-simple-technical-english). The vocabulary rules pulled the model toward fluent sentences and away from the content. The guardrails above and the light default exist to prevent that.
Show full SKILL.md (385 more words)Show less
The ste rung
Read
references/ste-rules.md. It has the nine rule sections, the numeric limits, the verb forms table, the safety instruction format, and the dial table. The dial table is the single definition of whatstrict,80, andlightallow; do not work from memory of it.Apply the level from the dial table. In one line each:
light(default) reads like a careful technical writer, not a specification;80applies the limits, active voice, and the substitution table while domain nouns stay free and undeclared;strictis everything in the specification, with every domain term declared as a technical name on first use ("the hydraulic reservoir, a technical name for the tank that holds the fluid").Vocabulary authority: if
references/ste-dictionary-full.mdexists, use it as the authority. Otherwise usereferences/ste-dictionary.md, which is partial. Load it atstrict; at80consult its substitution table for every verb and connector you are unsure about; atlightuse the common swaps from memory (ensure, utilize, prior to, in order to) and do not load the file.Run the guardrails above as a checklist against the source before answering. Count the facts in the source; count them in the output.
For
strictoutput, optionally lint with the bundled checker:python3 scripts/ste_check.py output.txt # or: cat output.txt | python3 scripts/ste_check.pyIt wraps the open-source
ste100-checkerthroughuvxand prints JSON findings. Treat its findings as hints; the dictionary inreferences/is the authority when they disagree.
Output format for ste: the rewritten text, then a short line naming the level used and any technical names declared, then the escalation line.
Machine check
bash scripts/doctor.sh prints what the video rung needs on this machine (Python, uv and its 3.12, ffmpeg, manim, kokoro-onnx and its model files, espeak-ng, LaTeX, an ElevenLabs key by name only). It installs nothing; it writes only machine.toml (gitignored) in the skill root. bash scripts/setup.sh is the one script that installs; run doctor first, then setup, before the first video.
Not affiliated
The STE references summarize the public outline of ASD-STE100 Issue 9 (January 2025) and a seminar reference sheet. This skill is unofficial and is not affiliated with or endorsed by ASD. ASD-STE100 is free of charge but copyright ASD; the bundled dictionary is partial and the full word list is not redistributed here.
© koolamusic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 13 other files (scripts, references) in skills/explainer-formats of koolamusic/claudefiles.
- SKILL.md
- .gitignore
- references/diagram.md
- references/html.md
- references/ste-dictionary.md
- references/ste-rules.md
- references/video.md
- scripts/doctor.sh
- scripts/pyproject.toml
- scripts/render.py
- scripts/setup.sh
- scripts/ste_check.py
- scripts/tts.py
- scripts/uv.lock
Open the folder on GitHubat commit 297c432
Compare with similar skills
Explainer Formats next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Explainer Formats this skillkoolamusic/claudefiles | 130 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Moai Domain HTML Reportmodu-ai/moai-adk | 1.2k | — | ~6.4k | Automated safety check: Notes | Apache-2.0 | |
| Eli5mblode/agent-skills | 142 | — | ~861 | Automated safety check: Pass | MIT | |
| No AI Slophuytieu/COG-second-brain | 1.3k | — | ~5.9k | Automated safety check: Pass | MIT | |
| Candao Review Expert Analysis Prodinfometa/workbuddyskills | 342 | — | ~1.8k | Automated safety check: Pass | None | |
| UX Writingcontent-designer/ux-writing-skill | 222 | — | ~3.8k | Automated safety check: Pass | MIT |
Similar skills
Eli5
mblode/agent-skills
Picks the form that explains best and applies the house explanation style: plain prose, controlled English modelled on ASD-STE100, a diagram, an interactive HTML page, or a narrated explainer video.
No AI Slop
huytieu/COG-second-brain
Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting.
Candao Review Expert Analysis Prod
infometa/workbuddyskills
Generate evidence-based Chinese delivery-review reports from the installed Candao AGE connector.
UX Writing
content-designer/ux-writing-skill
Applies UX writing practice to interface copy such as buttons, errors, forms and onboarding, using four quality standards and accessibility guidance.
Nbj Write Clearly
daniel-p-green/nbj-write-clearly
Drafts, revises, and audits reader-first technical and product documentation.
More from koolamusic/claudefiles
All 13 skills in this repoBreadboarding
koolamusic/claudefiles
Transform a workflow description into affordance tables showing UI and Code affordances with their wiring.
Orchestrator
koolamusic/claudefiles
Turn the current session into a chief-of-staff thread that runs a war room of three role slots — surveyor, executor, auditor — and routes per-branch work to durable, reusable child agents.
Retro
koolamusic/claudefiles
A skill your agent uses when a user completes a phase, sprint, milestone, or meaningful unit of work and needs a retrospective.
Skill Creator
koolamusic/claudefiles
Guide for creating effective skills. An agent skill from koolamusic/claudefiles.
Debug
koolamusic/claudefiles
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework with built-in backward tracing for deep-stack failures…
Grill
koolamusic/claudefiles
Adversarial questioning and collaborative shaping in one skill.
Related
Categories
Questions about Explainer Formats
What does Explainer Formats do?
A skill your agent uses when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100…. Explainer Formats is an agent skill from koolamusic/claudefiles. Use when asked to explain a topic, codebase, process, or document in a specific output format — plain language or Simplified Technical English (STE, in the style of ASD-STE100 with its controlled vocabulary and short procedural sentences), a diagram, a standalone HTML page, or a narrated video explainer.
When should I use Explainer Formats?
Explainer Formats fits situations like: asked to explain a topic; document in a specific output format — plain language; simplified Technical English (STE; in the style of ASD-STE100 with its controlled vocabulary and short procedural sentences).
How do I install Explainer Formats in Claude Code?
Run `npx skills add koolamusic/claudefiles --skill explainer-formats -a claude-code`. Or copy the skill folder (skills/explainer-formats in koolamusic/claudefiles) into .claude/skills/explainer-formats in your project. Claude Code loads it when a task matches its description.
How do I install Explainer Formats in Codex?
Run `npx skills add koolamusic/claudefiles --skill explainer-formats -a codex`. Or copy the skill folder (skills/explainer-formats in koolamusic/claudefiles) into .agents/skills/explainer-formats in your project. Codex loads it when a task matches its description.
Can I use Explainer Formats in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add koolamusic/claudefiles --skill explainer-formats -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/explainer-formats, .gemini/skills/explainer-formats, .github/skills/explainer-formats and .opencode/skills/explainer-formats in your project.
What does Explainer Formats need to run?
Going by SKILL.md and its folder, Explainer Formats needs Python and a shell for the scripts in its folder and the command-line tools its instructions call (python3, bash and uv). Our summary lists: Python 3; A Bash shell.
Does Explainer Formats access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Explainer Formats safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Explainer Formats use?
Explainer Formats is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Explainer Formats use?
About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.
What are the alternatives to Explainer Formats?
Skills that share tags, products or a category with Explainer Formats: Moai Domain HTML Report (modu-ai/moai-adk, 1.2k stars), Eli5 (mblode/agent-skills, 142 stars), No AI Slop (huytieu/COG-second-brain, 1.3k stars) and Candao Review Expert Analysis Prod (infometa/workbuddyskills, 342 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Explainer Formats?
koolamusic (a GitHub user) maintains it in koolamusic/claudefiles, which has 130 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 5, 2026.
Source: koolamusic/claudefiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.