agentleFS
ahmadrosidahmadrosid/nakama/.agents/skills/eli5/SKILL.md

eli5

Skill826 starsChanged 12 days agoMITView on GitHub

Explain any topic like the reader knows nothing: big pictures, few words, concrete metaphors, optional self-contained HTML artifact opened in the browser. Use when the user says ELI5, /eli5, "explain like I'm five", "like I know nothing", wants a visual explainer, or asks for big pictures and few words.

68 other projects use a version of this.

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

  • 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 Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines.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

  • 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

  • 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

  • +7 more from dzhng

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Assume zero knowledge: No repo paths, issue numbers, or acronyms unless the slide teaches them.

    line 24
  2. Very specific:

    Open it: Write under /tmp/ (or a path the user names), then open the file.

    line 25
  3. Distinctive:

    Avoid purple gradients, glow, emoji sticker clutter, and dense dashboards

    line 43
  4. Distinctive:

    If a term must appear, define it in the same sentence: “Skills = recipe cards for the AI.”

    line 54
  5. Distinctive:

    Use “as mentioned above” — restating is fine.

    line 59
  6. Distinctive:

    Commit or publish the HTML unless the user asks

    line 61

“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

ELI5

Teach one idea so a smart stranger with zero domain context gets it in one glance.

Default output

Prefer a single self-contained HTML file opened in the browser (open <path> on macOS). Chat-only ELI5 is fine when the user asks for text, or the topic is one sentence.

HTML rules

  1. One file. Inline CSS + inline SVG. No external fonts, scripts, images, or network requests.
  2. Big pictures, few words. Each slide = one metaphor picture (large SVG) + a short heading + ≤2 short sentences. No jargon unless the metaphor defines it.
  3. ≤5 slides. Cap at five. Rank must-know first; cut the rest.
  4. Assume zero knowledge. No repo paths, issue numbers, or acronyms unless the slide teaches them.
  5. Open it. Write under /tmp/ (or a path the user names), then open the file. Tell them the path in one line.
  6. No quizzes, forms, or buttons. Display-only.

Slide recipe

1. What is the thing?     (concrete metaphor)
2. What already exists?   (if comparing to something shipped)
3. What is new / missing? (the ask)
4. One contrast picture   (before vs after / now vs later)

Drop steps that do not apply. Never pad.

Visual style

  • High contrast, thick strokes, large labels on the SVG itself
  • System font stack only
  • Avoid purple gradients, glow, emoji sticker clutter, and dense dashboards
  • One job per slide — no card grids of stats

Chat fallback (when HTML is skipped)

Lead with the metaphor in one line. Then at most three short bullets. No preamble. No recap.

Voice

  • Short words. Concrete nouns. Active verbs.
  • Metaphors from daily life (recipe cards, boxes, janitors, editors) over product jargon.
  • If a term must appear, define it in the same sentence: “Skills = recipe cards for the AI.”

Do not

  • Dump architecture, file trees, or acceptance criteria
  • Use “as mentioned above” — restating is fine; memory is not assumed
  • Soften into marketing copy or a status update
  • Commit or publish the HTML unless the user asks

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.