agentleFS
Sign inStart free
mblodemblode/agent-skills/skills/eli5/SKILL.md

eli5

Skill189 starsChanged 2 months agoMITView on GitHub

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. Use when asked for \"ELI5\", \"plain English\", \"re-pitch that\", \"stop using jargon\", \"explain it in STE100\", \"draw me a diagram of how this works\", \"make an interactive explainer\", or \"make a 3b1b style video on X\".

66 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

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:

    Use this style for the explanation requested.

    line 10
  2. Distinctive:

    Avoid minimizers: simply, obviously, just, easy, of course, as you know.

    line 13
  3. Very specific:

    No em dashes in authored prose.

    line 14
  4. Distinctive:

    Use an analogy only when it clarifies the mechanism.

    line 15
  5. Distinctive:

    Put the explanation or result first.

    line 16
  6. Distinctive:

    When the user names a form, use it.

    line 32

“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

Plain-language house style

  • IS NOT: product copy or documentation (use ghostwriter), or slide decks (use presentation-creator).

Use this style for the explanation requested. Keep it for later replies only when the user asks for an ongoing mode; a single ELI5 request does not change the session permanently.

  • Preserve exact identifiers, paths, commands, errors, numbers, and quoted source text. Explain around them.
  • Avoid minimizers: simply, obviously, just, easy, of course, as you know.
  • No em dashes in authored prose; do not substitute a spaced hyphen. For promotional vocabulary and other machine tells, run ghostwriter/references/tells.md, the collection's one list; literal technical uses and quotations stay.
  • Use an analogy only when it clarifies the mechanism; identify its limit if that affects the answer. If an explanation did not land, change the framing instead of making the same analogy longer.
  • Put the explanation or result first. Include a next action only when the reader needs to act. Do not assign the user work the agent is already authorized to complete.

Return the explanation itself. No activation announcement, fixed sentence count, compulsory recap, or pre-send checklist.

Pick the form

Prose is the default. Move up a rung when the user names the form, or when the content has a shape that prose hides. Each rung costs more to make and to check, so take the lowest one that carries the idea.

FormUse whenCost
Plain proseMost answersNone
Controlled EnglishUser asks for STE100 or "Simplified Technical English", or the answer is a procedure or a dense mechanism a non-native reader must followNone
DiagramParts and the links between them, a sequence over time, states, or a data pathLow
HTML pageThe reader learns by changing an input and seeing the result, or the topic needs several linked viewsMedium
Explainer videoUser asks for a video, or the idea is motion (an algorithm stepping, a curve changing)High: render, narration, review

When the user names a form, use it; do not argue down to prose. When choosing on your own, never go past a diagram without asking, and offer the next rung in one line only when it would clearly help.

"80% STE100", "soft STE100", or similar means the relaxed profile in references/formats.md, not the full specification. Diagram, HTML, and video mechanics (tool choice, narration keys, review steps) are in the same file; load it before making any form other than plain prose.

Boundaries

This changes assistant prose and the explanations it makes. Product copy, technical docs, and README structure belong to ghostwriter, PR bodies to pr-creator, slide decks to presentation-creator, and data charts to an installed dataviz skill where one exists.

Maintenance

evals/evals.json contains behavior and routing scenarios for changes to this skill; do not load it during an explanation.

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.

Check your setup, free