agentleFS
nicodiansknicodiansk/draw-it-out/skills/explain/SKILL.md

explain

Skill1 starsChanged 3 days agoMITView on GitHub

Explains code or a process as a drawing that builds itself, in plain words for people who don't read code. Use when someone asks "what happens when I click X", "how does this part of my app work", "walk me through this flow", or asks to explain, draw or visualise a process, pipeline, agent loop or business flow.

129 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use debug-fix, root-cause 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.
  • zebbernSkill

    debug-fix

    Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)

    Also in 3 projects that use this

  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 5 projects that use this

  • ralphkraussSkill

    resolve-conflicts

    Resolve git merge conflicts or re-apply changes from a stale branch onto current main. Use when user says "resolve conflicts", "merge conflicts", "rebase branch", "branch is behind", "re-apply changes", "port branch", or a branch is too far behind main to merge cleanly.

    Also in 4 projects that use this

  • neurofooSkill

    socratic

    Socratic questioning to examine beliefs, uncover assumptions, and develop deeper understanding. Use to challenge thinking, evaluate proposals, or teach without lecturing.

    Also in 4 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 6 projects that use this

  • mitsuhikoSkill

    summarize

    Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize

    Also in 8 projects that use this

  • Other versions129 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 129

    1. Z3Prover/z3★ 13ksame name
    2. crbnos/carbon★ 2.8ksame name
    3. poshan0126/dotclaude★ 871same name
    4. VinkyDev/vibestart★ 295same name
    5. hsantanna88/clo-author★ 262same name
    6. hugosantanna/clo-author★ 262same name
    7. entireio/skills★ 240same name
    8. sammcj/agentic-coding★ 169same name
    9. SerhiiKorniienko/bullshit-detector★ 151same name
    10. kv0906/pm-kit★ 138same name

    119 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 117 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not sure which? Ask one question: "Should I follow it through your code, or draw the process?" Read only the mode's file, then schema.md …

    line 18
  2. Distinctive:

    Read only the mode's file, then schema.md for the JSON you write.

    line 19
  3. Very specific:

    Write in the asker's language, whatever it is: text, label, title and lang.

    line 23
  4. Very specific:

    Never describe what you didn't see.

    line 27
  5. Distinctive:

    Read-only: never edit the project, submit a form, sign in or pay.

    line 29
  6. Distinctive:

    Write the JSON (and any screenshots) to a folder outside the project, such as your scratchpad or a temp folder, then run:

    line 33

“Common” is measured: kept by at least 6 in 10 of the 117 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

Draw it out

You explain one thing as a sheet: a drawing that builds itself piece by piece. The reader built software with AI and can't read the code, so every word on the sheet is plain.

Pick the mode

  • walk: the question is what their own code does when they do something ("what happens when I click Pay?", "where does my signup form go?"). Read walk.md.
  • sheet: the question is how a process works (a pipeline, an agent loop, a business flow, a document they shared). Code is optional. Read sheet.md.

Not sure which? Ask one question: "Should I follow it through your code, or draw the process?" Read only the mode's file, then schema.md for the JSON you write.

Rules for every sheet

  • Write in the asker's language, whatever it is: text, label, title and lang. For a language other than English or Italian, also fill ui (schema.md).
  • Plain words, short sentences. Explain each technical term the first time it appears ("the server: the computer that runs your app's code").
  • Never describe what you didn't see. A gap goes in unsure, said plainly.
  • Code reaches the sheet only through render.py: you write {"file", "lines"}, never the code.
  • Read-only: never edit the project, submit a form, sign in or pay.

Render

Write the JSON (and any screenshots) to a folder outside the project, such as your scratchpad or a temp folder, then run:

python3 <this skill's folder>/engine/render.py <folder>/walk.json --root <project folder> --out <folder>/walk.html

--root is the folder that code paths start from; screenshot paths start from the JSON's folder. Exit 1 prints one line per problem: field → problem → how to fix. Fix the JSON and rerun, at most three times. Still refused: stop and tell the user, in plain words, what is missing.

Show it

  • An Artifact tool is available: publish the HTML file as an artifact.
  • Claude Code without one: give the path and open it (open on macOS, xdg-open on Linux, start on Windows).
  • claude.ai without one: share the HTML file.

Then two or three lines: what the sheet shows, the one piece to look at, and any gap from unsure.

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.