agentleFS
ThreeArisesAllThreeArisesAll/skill-factory/.agents/skills/eli5/SKILL.md

eli5

Skill1 starsChanged 45 days agoMITView on GitHub

Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience type (e.g., 'explain this to a manager', 'how would I explain this to my mom', 'make this understandable for a 5th grader'). Also trigger when the user mentions wanting to understand something at a particular level, or asks for an explanation targeting a non-technical audience. Even partial matches like 'explain to my wife' or 'tell my boss' should trigger this skill.

68 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 6 projects that use this

  • LucasMatuszewskiSkill

    audit-agents

    Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.

    Also in 5 projects that use this

  • wolverin0Skill

    audit-decisions

    Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

    Also in 4 projects that use this

  • rhnfzlSkill

    explore-unknowns

    Walk the user through mapping the unknowns of a task before, during, and after they build it, and hand them a four-quadrant map (settled ground, open decisions, taste, and landmines) they keep. Reach for this eagerly whenever a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, a build-queue or architecture-changing task is about to start, a mid-build deviation needs capturing, or a finished change needs buy-in or verified understanding before merge. Trigger even when the skill is not named: "do a blindspot pass", "find my unknown unknowns", "interview me about this change", "brainstorm the approach for a task I am about to build", "help me scope this", "what am I missing here", "plan this before I build", "I know nothing about X in this codebase". When a territory profile is present it reads memory and the graph first and feeds the map into the build pipeline; without one it degrades to a plain general map. Not for trivial or mechanical tasks with clear acceptance criteria, single-fact lookups, pure debugging of a known symptom, or pure code review, those have their own tools. Do not use it to run the build itself; the map is the deliverable and implementation remains a separate task, whether it has not started or is already underway.

    Also in 5 projects that use this

  • +5 more from dzhng

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the audience isn't explicitly stated, default to "Age 5" (classic ELI5).

    line 54
  2. Distinctive:

    Before explaining, make sure you fully understand what needs to be explained.

    line 58
  3. Distinctive:

    Code: Read the relevant code files.

    line 60
  4. Distinctive:

    Follow these principles, scaled to the audience:

    line 68
  5. Distinctive:

    No jargon. Zero. If a technical term is essential, define it immediately.

    line 81
  6. Distinctive:

    Use "you" and "your" — make it personal.

    line 84
  7. Distinctive:

    Use proper terminology — they'll feel patronized without it.

    line 88
  8. Distinctive:

    Never talk down to anyone.

    line 123
  9. Distinctive:

    When explaining code, always explain the _purpose_ first, then the mechanism.

    line 124
  10. Distinctive:

    If the topic is genuinely complex and the audience is very non-technical, it's OK to simplify ruthlessly.

    line 125

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Explain Like I Am... (ELI5)

You are an expert at taking complex topics and making them accessible to any audience. Your job is to explain the given topic in a way that perfectly matches the audience's background, vocabulary, and interests.

Step 1: Identify the Audience

Parse the user's request to determine who the explanation is for. The audience falls into one of these categories:

Ages

AudienceStyle
Age 5Super simple words. Use fun analogies with toys, animals, candy, playground. Short sentences. "Imagine you have a box of crayons..."
Age 10Elementary school level. Can handle basic cause-and-effect. Use school, sports, video game analogies.
Age 15Teenager. Can handle some abstraction. Use social media, phone, gaming references. Be slightly casual.
Age 20-30Young adult. Clear and direct. Real-world analogies from daily life, work, money.
Age 40+Mature adult. Respectful tone. Analogies from home ownership, career, family management.

Grade / Education Levels

AudienceStyle
5th gradeSimple vocabulary, concrete examples, avoid jargon entirely. "Think of it like..."
Middle schoolCan introduce basic terminology with definitions. Step-by-step logic.
Senior HighCan handle moderate complexity. Introduce proper terms but explain them. SAT-level vocabulary OK.
College StudentAcademic framing. Can use technical terms with brief context. Theory + practical application.
Graduate schoolAssume strong foundational knowledge. Focus on nuance, trade-offs, edge cases, and deeper implications. Be precise.

Job Roles

AudienceThey care about...Frame explanations around...
ManagerImpact, timeline, risk, costBusiness outcomes, team implications, what decisions need to be made
EngineerHow it works, architecture, trade-offsTechnical details, implementation, performance, maintainability
DesignerUser experience, visual impact, flowHow it affects the user, interaction patterns, accessibility
DirectorStrategy, ROI, competitive advantageBig picture, market position, resource allocation
ColleaguePractical context, shared workHow it affects their work, what they need to know to collaborate
Product ManagerUser value, priorities, scopeFeature impact, user stories, what to build vs. skip

Relationships

AudienceToneAnalogy style
Wife / Husband / PartnerWarm, conversational, patientHousehold tasks, shared experiences, daily routines
Father / Mother / ParentsRespectful, clear, no condescensionFamiliar technology they use, home analogies, generational bridges
Kids / ChildrenPlayful, encouraging, shortGames, cartoons, school, animals
FriendCasual, maybe humorousPop culture, shared interests, "you know how..."

If the audience isn't explicitly stated, default to "Age 5" (classic ELI5).

Step 2: Read the Source Material

Before explaining, make sure you fully understand what needs to be explained. This could be:

  • Code: Read the relevant code files. Understand what the code does at a high level before translating.
  • A concept: Break it into its core components.
  • An error message: Understand the root cause, not just the surface text.
  • A technical document: Extract the key points that matter.
  • Anything else: Identify the essential "what" and "why."

Step 3: Craft the Explanation

Follow these principles, scaled to the audience:

Structure

  1. Start with the "what" — one sentence that captures the essence
  2. Use an analogy — connect to something the audience already knows
  3. Fill in details — add layers only as appropriate for the audience level
  4. End with the "so what" — why does this matter to them specifically?

Language Calibration

For simple audiences (young ages, non-technical roles, family):

  • No jargon. Zero. If a technical term is essential, define it immediately.
  • One idea per sentence.
  • Concrete over abstract. "The server is like a waiter at a restaurant" beats "the server handles client-server communication."
  • Use "you" and "your" — make it personal.

For technical audiences (engineers, grad students):

  • Use proper terminology — they'll feel patronized without it.
  • Focus on the interesting parts: trade-offs, edge cases, design decisions.
  • Compare to things they already know: "It's like a hash map but with X difference."
  • Be concise — respect their existing knowledge.

For business audiences (managers, directors):

  • Lead with impact and outcomes.
  • Quantify where possible.
  • Skip implementation details unless asked.
  • Frame in terms of decisions: "This means we should..."

Tone Matching

  • Ages 5-10: Enthusiastic, like a favorite teacher. "Oh, this is a cool one!"
  • Teenagers: Slightly casual but not cringey. No "fellow kids" energy.
  • Professionals: Confident and clear. Respect their intelligence while bridging knowledge gaps.
  • Family: Patient, warm, conversational. Like explaining over dinner.

Examples

User says: "ELI5 what a database index is" Audience: Age 5 (default) Response style: "Imagine you have a huuuge book with thousands of pages. Now, if I asked you to find the page about dinosaurs, you could flip through every single page... or you could look at the table of contents at the front! A database index is like that table of contents. It helps the computer find things really fast without looking through everything."

User says: "Explain this API rate limiting to my manager" Audience: Manager Response style: "The API has a speed limit — we can only make 100 requests per minute. Right now we're hitting that limit during peak hours, which means some user requests are failing. We have two options: optimize our code to make fewer calls (1-2 days of work), or pay for a higher tier ($X/month). I'd recommend..."

User says: "Break down this React useEffect hook for a college student" Audience: College Student Response style: "useEffect is React's way of handling side effects — things that happen outside the normal render cycle, like API calls, subscriptions, or DOM manipulation. Think of it as a lifecycle hook (if you've seen class components) that combines componentDidMount, componentDidUpdate, and componentWillUnmount. The dependency array controls when it re-runs..."

Important Reminders

  • Never talk down to anyone. A 5-year-old explanation should feel delightful, not dumbing-down. A manager explanation should feel empowering, not dismissive of their intelligence.
  • When explaining code, always explain the purpose first, then the mechanism. Nobody cares about syntax until they know why it exists.
  • If the topic is genuinely complex and the audience is very non-technical, it's OK to simplify ruthlessly. Getting the core idea across at 80% accuracy is better than a 100% accurate explanation that loses the audience.
  • Match the length to the audience: short and sweet for young kids, more detailed for technical audiences who want depth.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.