Understand Explain
Egonex-AI/Understand-Anything
Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.
A skill your agent uses when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase.
MITAuto-check passed
Install Explainer
$ npx skills add Royal-lobster/code-explainer --skill explainer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Royal-lobster/code-explainer explainer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "explainer" agent skill from https://github.com/Royal-lobster/code-explainer/tree/main into .claude/skills/explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer", 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.
$ npx skills add Royal-lobster/code-explainer --skill explainer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Royal-lobster/code-explainer explainer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "explainer" agent skill from https://github.com/Royal-lobster/code-explainer/tree/main into .agents/skills/explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer", 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 Royal-lobster/code-explainer --skill explainer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Royal-lobster/code-explainer explainer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "explainer" agent skill from https://github.com/Royal-lobster/code-explainer/tree/main into .cursor/skills/explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer", 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.
$ npx skills add Royal-lobster/code-explainer --skill explainer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Royal-lobster/code-explainer explainer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "explainer" agent skill from https://github.com/Royal-lobster/code-explainer/tree/main into .gemini/skills/explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer", 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 Royal-lobster/code-explainer explainerInstalls 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 Royal-lobster/code-explainer --skill explainer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "explainer" agent skill from https://github.com/Royal-lobster/code-explainer/tree/main into .github/skills/explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer", 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 Royal-lobster/code-explainer --skill explainer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Royal-lobster/code-explainer explainer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "explainer" agent skill from https://github.com/Royal-lobster/code-explainer/tree/main into .opencode/skills/explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explainer", 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- GitHub stars
- 100
- Token cost
- ~1.6k tokens
- SKILL.md length
- 821 words
- Files
- 43 (incl. scripts)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase.
- Works in 5 steps: Parallel init — Dispatch both in a… → Scout — Read docs/scan.md. Dispatch… → Plan + generate — Two paths depending on… → …
- The user asks to explain
- SKILL.md covers Models, Checklist, Q&A on Active Walkthrough and Common Mistakes
- Runs Shell scripts from its folder; calls curl
What it does
Explainer is an agent skill from Royal-lobster/code-explainer. Use when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase. Triggers on 'explain', 'walk me through', 'how does X work', 'what does this code do'.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 45 other files, including scripts (for example `README.md`, `docs/assess.md` and `docs/plan.md`).
The repository describes itself as: Interactive code walkthrough skill with VS Code highlighting and AI-powered voice narration. The licence is MIT.
When your agent uses it
- The user asks to explain
- Understand a feature
- Code flow in the codebase
- Walk me through
Example prompts
- “explain”
- “walk me through”
- “how does X work”
- “/explainer”
Requirements
- A Bash shell
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Parallel init — Dispatch both in a single response
- Scout — Read docs/scan.md. Dispatch SMALL sub-agent to discover relevant files and map the call chain. No highlights yet — discovery only.
- Plan + generate — Two paths depending on depth
- Execute walkthrough — Read the doc for chosen mode: docs/walkthrough.md, docs/read.md, or docs/podcast.md. Walkthrough and podcast…
- Wrap up — 3-5 key takeaways, how feature fits the broader architecture, offer to dive deeper or explain related features.
What it can do on your machine
Read from SKILL.md and the folder at commit d878fc9. 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 1 file in scripts/ (Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, 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 loads about 1.6k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 821 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 Royal-lobster/code-explainer at commit d878fc9, republished under its MIT licence (© Royal-lobster). 821 words, ~1,561 tokens.
Download SKILL.mdSave it as
.claude/skills/explainer/SKILL.md (or your agent's skills folder). This skill also uses 42 other files; get the full folder from GitHub.- name
- explainer
- description
- Use when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase. Triggers on 'explain', 'walk me through', 'how does X work', 'what does this code do'.
Code Explainer
Interactive code walkthrough. Scans the codebase for a feature, builds a segment plan, then walks through each segment — highlighting code in VS Code and explaining at their chosen depth.
Models
Configure your preferred models here. All docs reference these tiers by name — change them once and the whole skill updates.
| Tier | Default | Role |
|---|---|---|
LARGE | opus | Deep Dive planner — narrative reasoning, transition objects |
MEDIUM | sonnet | Deep Dive segment agents — deep code reading, dense highlights |
SMALL | haiku | Scout, Overview plan+highlights — fast exploration and scanning |
When dispatching sub-agents, look up the model for the tier and use that exact model name.
Checklist
Complete these steps in order:
Parallel init — Dispatch both in a single response:
- Sidebar check (Bash):
PORT=$(cat ~/.claude-explainer-port 2>/dev/null) && TOKEN=$(cat ~/.claude-explainer-token 2>/dev/null) && curl -sf -H "Authorization: Bearer $TOKEN" "http://localhost:$PORT/api/health"—{"status":"ok"}means sidebar is active. When active, NEVER output walkthrough content as terminal text; all output goes through sidebar HTTP API only. - Ask preferences (AskUserQuestion): Read
docs/assess.mdand ask all three questions listed there (familiarity + depth level + delivery mode) in a single call. Do NOT skip any or invent new ones.
- Sidebar check (Bash):
Scout — Read
docs/scan.md. DispatchSMALLsub-agent to discover relevant files and map the call chain. No highlights yet — discovery only.Plan + generate — Two paths depending on depth:
- Overview — Single
SMALLsub-agent reads scout output, builds plan, generates highlights in one pass. Sendset_planwhen done. - Deep Dive — Read
docs/plan.md. DispatchLARGEplanner to build narrative + transition objects. Then readdocs/segments.mdand dispatch parallelMEDIUMsegment agents (all at once). Create a unique temp dir withmktemp -dand have each agent write its segment there. Wait for ALL agents to complete, then assemble from files withjqand send one fullset_plan. Clean up the temp dir after sending. Do NOT send anything to the sidebar until everything is ready.
- Overview — Single
Execute walkthrough — Read the doc for chosen mode:
docs/walkthrough.md,docs/read.md, ordocs/podcast.md. Walkthrough and podcast referencedocs/tts.md.Wrap up — 3-5 key takeaways, how feature fits the broader architecture, offer to dive deeper or explain related features.
First-time setup? Read docs/setup.md.
Q&A on Active Walkthrough
When the user says they're in an active explainer walkthrough and asks a question (even in a new chat), skip the full checklist above and instead:
- Get context: Run
~/.claude/skills/explainer/scripts/explainer.sh state— the response now includes asegmentfield with the full current segment (file,start,end,title,explanation,highlights). Use this to understand what code the user is currently viewing. - Read the code: Use the segment's
file,start, andendto read the relevant source code. - Answer in context: Ground your answer in the specific code and segment the user is looking at. Reference line numbers from the segment, not abstract concepts.
If state returns status: "idle" (no active walkthrough), check .walkthroughs/ for saved plans and ask the user which one they mean.
Show full SKILL.md (345 more words)Show less
Common Mistakes
| Mistake | Fix |
|---|---|
| Scope too large | Stick to segment boundaries. Overview: max 80 lines, Deep Dive: max 40. Split if bigger |
| Not connecting segments | Include a context line linking to previous segment |
| Forgetting to highlight | Sidebar: automatic. Fallback: write to ~/.claude-highlight.json |
| Reading entire file | Use offset+limit on Read for just the segment |
| Not waiting for user | Pause after each segment for questions |
| ttsText missing or has markdown | Include plain ttsText in every segment — strip backticks, bold, line refs from spoken text |
| Explaining obvious code, missing the "why" | Skip standard patterns (loops, imports, null checks). Always explain intent before mechanism |
| Ignoring complexity tags | [core] = thorough, [wiring] = breeze through, [supporting] = brief |
| Sidebar check not parallelized | Dispatch Bash health check + AskUserQuestion in one response, not sequentially |
| Text output when sidebar active | If health check returned ok, send plan JSON only — no terminal text |
| Sub-highlights too many or too granular | Deep Dive: 6-12 highlights per segment, 1-4 lines each. Highlights are a moving pointer over one continuous voice stream — ttsText across highlights is concatenated and spoken as one TTS call, so write it as flowing narration, not self-contained slides. Overview: 1-8 lines, 3-6 per segment |
| Wrong field names in sidebar JSON | Use start/end/title/ttsText/highlights — NOT startLine/endLine/label/subHighlights. See docs/plan.md for exact schema |
Skipping set_plan before goto | Sidebar needs the full plan loaded first. Always send set_plan via explainer.sh plan before any goto messages |
| Sending plan before agents finish | Wait for ALL parallel segment agents to complete. Each writes to a unique temp dir (created via mktemp -d). Assemble from files with jq, then send one set_plan. Clean up temp dir after. Never send stubs or partial plans |
| Scout generating highlights | Scout only maps files and call chain. Highlights are generated in step 2 (Overview: single agent, Deep Dive: parallel agents) |
| Running planner + parallel agents for Overview | Overview uses one fast SMALL agent for plan + highlights. Planner and segment agents are Deep Dive only |
| Using tier names as literal model names | LARGE, MEDIUM, SMALL are placeholders — always resolve to the actual model name from the Models table in SKILL.md before dispatching |
© Royal-lobster, 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 42 other files (scripts) in the repository root of Royal-lobster/code-explainer.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- docs/assess.md
- docs/cover.png
- docs/plan.md
- docs/plans/2026-03-06-sharing-walkthroughs-design.md
- docs/plans/2026-03-06-sharing-walkthroughs-plan.md
- docs/podcast.md
- docs/read.md
- docs/scan.md
- docs/segments.md
- docs/setup.md
- docs/tts.md
- docs/uninstall.md
- docs/walkthrough.md
- scripts/explainer.sh
- … and 25 more
Open the folder on GitHubat commit d878fc9
Compare with similar skills
Explainer 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 this skillRoyal-lobster/code-explainer | 100 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Understand ExplainEgonex-AI/Understand-Anything | 86k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Understand Diff AnalysisEgonex-AI/Understand-Anything | 86k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Explain Usageasgeirtj/system_prompts_leaks | 69k | — | ~345 | Automated safety check: Pass | CC0-1.0 | |
| Video Understandcalesthio/OpenMontage | 65k | — | ~841 | Automated safety check: Pass | AGPL-3.0 | |
| Logic Explainsickn33/agentic-awesome-skills | 47k | 1 repos | ~894 | Automated safety check: Pass | MIT |
Similar skills
Understand Diff Analysis
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
Explain Usage
asgeirtj/system_prompts_leaks
Explain where this session's tokens went, with one simple chart in plain language.
Video Understand
calesthio/OpenMontage
Understand video content locally using ffmpeg frame extraction and Whisper transcription.
Logic Explain
sickn33/agentic-awesome-skills
Explain what a specific piece of code actually does for a given input by producing a step-by-step execution trace (interprocedural, with name resolution and type transitions).
Faceless Explainer Video
heygen-com/hyperframes
Turns an article, notes or a topic brief into an explainer video whose visuals are invented per scene, built frame by frame in HyperFrames with no footage.
Questions about Explainer
What does Explainer do?
A skill your agent uses when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase. Explainer is an agent skill from Royal-lobster/code-explainer. Use when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase.
When should I use Explainer?
Explainer fits situations like: the user asks to explain; understand a feature; code flow in the codebase; walk me through.
How do I install Explainer in Claude Code?
Run `npx skills add Royal-lobster/code-explainer --skill explainer -a claude-code`. Or copy the skill folder (the Royal-lobster/code-explainer repository) into .claude/skills/explainer in your project. Claude Code loads it when a task matches its description.
How do I install Explainer in Codex?
Run `npx skills add Royal-lobster/code-explainer --skill explainer -a codex`. Or copy the skill folder (the Royal-lobster/code-explainer repository) into .agents/skills/explainer in your project. Codex loads it when a task matches its description.
Can I use Explainer 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 Royal-lobster/code-explainer --skill explainer -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, .gemini/skills/explainer, .github/skills/explainer and .opencode/skills/explainer in your project.
What does Explainer need to run?
Going by SKILL.md and its folder, Explainer needs a shell for the scripts in its folder and the command-line tools its instructions call (curl). Our summary lists: A Bash shell.
Does Explainer access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Explainer 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 use?
Explainer is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Explainer use?
About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Explainer?
Skills that share tags, products or a category with Explainer: Understand Explain (Egonex-AI/Understand-Anything, 86k stars), Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars), Explain Usage (asgeirtj/system_prompts_leaks, 69k stars) and Video Understand (calesthio/OpenMontage, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Explainer?
Royal-lobster (a GitHub user) maintains it in Royal-lobster/code-explainer, which has 100 GitHub stars. The repository was last updated on August 21, 2026.
Source: Royal-lobster/code-explainer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.