agentleFS
HerbertGaoHerbertGao/herbertgao-skills/skills/eli5/SKILL.md

eli5

Skill0 starsChanged 4 months agoMITView on GitHub

Creates a beginner-first visual explanation as one self-contained HTML file with large diagrams and few words. Use when the user invokes /eli5 <topic>, asks for a picture explainer, or wants a complex technical concept, code path, Agent, MCP, protocol, or system explained visually for a newcomer. Do not use for exhaustive reference documentation, production UI, or slide decks.

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

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 Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines.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

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the topic from the invoking user message.

    line 20
  2. Distinctive:

    If the invoking message contains no non-empty topic, ask for the topic and stop without creating an HTML file.

    line 21
  3. Distinctive:

    Write one plain-language mental model, then split it into 3–6 one-idea scenes.

    line 26
  4. Distinctive:

    Use an explicit user-specified destination when provided.

    line 31
  5. Very specific:

    Never use the current working directory, repository, or a fixed eli5-* directory as the default.

    line 34
  6. Distinctive:

    Prefer HTML and inline SVG.

    line 39
  7. Very specific:

    Use native interactive controls with full keyboard operation.

    line 42
  8. Distinctive:

    When browser tools are available, open the file and inspect narrow and wide layouts, console errors, clipped labels, broken connectors, …

    line 46
  9. Distinctive:

    If browser tools are unavailable, inspect the generated HTML directly and disclose that visual rendering was not verified.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 51 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

Turn the topic from the invoking user message into a visual explanation for someone with no prior knowledge. Use large pictures and few words without sacrificing factual accuracy.

Procedure

  1. Establish the topic and truth sources.
    • Use the topic from the invoking user message; do not rely on a $ARGUMENTS placeholder.
    • If the invoking message contains no non-empty topic, ask for the topic and stop without creating an HTML file.
    • For repository-specific topics, inspect the smallest relevant code, configuration, tests, and documentation before drawing the system.
    • For claims that may be current or version-dependent, prefer official primary sources. Mark remaining uncertainty instead of inventing detail.
  2. Choose the teaching path.
    • Write one plain-language mental model, then split it into 3–6 one-idea scenes.
    • Give every scene a visual that carries the idea: a flow, comparison, timeline, layered system, annotated object, or concrete analogy.
    • Introduce useful jargon only after showing what it does. Keep labels short enough to scan at a glance.
  3. Allocate the output path before writing.
    • Use an explicit user-specified destination when provided.
    • Otherwise treat unique temporary-directory creation as a fail-closed preflight, not an example. On POSIX, first run tmp_dir=$(mktemp -d "${TMPDIR:-/tmp}/eli5.XXXXXX"), require a non-empty absolute result, and use only $tmp_dir/eli5-<topic-slug>.html.
    • On a non-POSIX host, use the native API that creates and returns a unique absolute temporary directory. If no unique absolute directory can be created, stop and report the failure without writing HTML.
    • Never use the current working directory, repository, or a fixed eli5-* directory as the default.
  4. Write one self-contained HTML file.
    • Inline all CSS, SVG, and data. Do not use CDNs, remote fonts, external images, build steps, or runtime network requests.
    • Include a data-URI favicon such as <link rel="icon" href="data:,"> so local preview does not request /favicon.ico.
    • Prefer HTML and inline SVG. Add JavaScript only when a small interaction materially improves understanding.
    • Include a one-sentence takeaway, the visual scenes, one simple example or analogy, and a short “remember this” ending.
    • Set document lang, a useful title, and a responsive viewport. Use semantic headings, high contrast, at least 16px body text, and visible focus styles.
    • Use native interactive controls with full keyboard operation. Do not rely on color alone. Give informative SVGs role="img" and an accessible name via aria-label, aria-labelledby, or <title>; a visible caption may supplement but not replace that name.
    • Preserve exact commands, paths, protocol names, error strings, and code tokens when they matter. Do not trade factual accuracy for simplicity.
  5. Verify the artifact.
    • When browser tools are available, open the file and inspect narrow and wide layouts, console errors, clipped labels, broken connectors, unreadable contrast, keyboard Tab order, and the accessibility tree.
    • Confirm the artifact works offline and contains no unintended external src, href, srcset, CSS url(...), or @import references. Same-page anchors are allowed.
    • If browser tools are unavailable, inspect the generated HTML directly and disclose that visual rendering was not verified.
  6. Deliver.
    • Give one short sentence describing the explainer, then return the absolute HTML path.
    • Mention material uncertainty or an unavailable browser check. Do not paste the full HTML into the response.

Provenance

Portable adaptation of Anthropic community marketplace eli5, originally authored by Thariq Shihipar. Upstream source: https://github.com/anthropics/claude-plugins-community/blob/794af9e63d07fad17087dcab61f21f44cb48effd/eli5/skills/eli5/SKILL.md.

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.