agentleFS
sohaibdevvsohaibdevv/project-template/.agents/skills/explain/SKILL.md

explain

Skill2 starsChanged 3 months agoMITView on GitHub

Give a plain-English tour. Use when someone asks what a file does, what just changed, what a technical word means, or says they are lost.

122 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 9 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

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 108 edited versions we read keep these.

  • 3

    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:

    Read project/PROFILE.md for how much detail they asked for.

    line 14
  2. Very specific:

    Read project/BRIEF.md too, so you can explain in the vocabulary of their business rather than in the vocabulary of software.

    line 20
  3. Very specific:

    Done when: every technical word in your answer is either defined in the same sentence or is a term in docs/glossary.md.

    line 22
  4. Distinctive:

    Done when: all four parts are present.

    line 36
  5. Distinctive:

    Ask what they were trying to do.

    line 54
  6. Distinctive:

    Read the recent changes and list one line per file, in their words, most important first.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 108 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

A tour of one thing, pitched at the person in front of you.

Someone asking this is usually mid-task and lost. Answer the question they asked, at the size they asked it.

1. Find the right altitude

Read project/PROFILE.md for how much detail they asked for.

  • Just do it wants two sentences and an offer of more.
  • Tell me what you did wants a short paragraph.
  • Teach me why wants the reasoning, and will follow a tangent.

Read project/BRIEF.md too, so you can explain in the vocabulary of their business rather than in the vocabulary of software.

Done when: every technical word in your answer is either defined in the same sentence or is a term in docs/glossary.md.

2. Give the tour

Four parts, in this order.

What it is for. In their words, in one sentence. Not "this module handles order persistence" but "this is where an order gets saved so it's still there tomorrow."

What it does. Three to five lines, in sequence. Enough that they could describe it to someone else.

What would break if it vanished. Imagine deleting it. If nothing gets harder, say so plainly, because that is worth knowing. If the same work would reappear in five other places, say where.

What to change to make it behave differently. The one or two things in this file someone would realistically want to alter.

Done when: all four parts are present.

The third part is the one that teaches. It turns "this file exists" into "this file earns its keep", and it is the same test used to decide whether code should exist at all. docs/glossary.md calls it the deletion test.

3. Leave them something to try

Name one thing they could safely change right now: the file, the line, and what would visibly happen.

In app/page.tsx, line 34 says limit(20). Change it to limit(5) and save. The list will show five rows. That is the whole change.

People learn this by turning a knob and watching, not by reading an explanation of the knob.

Done when: the suggestion names a file and a specific value.

When they say they are lost

Different shape. Do not tour a file.

Ask what they were trying to do. Then say, in three lines, where they are and what the next single action is.

Then do that action with them.

Being lost is usually about the next step, not about understanding the system.

When they ask what just changed

Read the recent changes and list one line per file, in their words, most important first.

Then say what is now possible that was not possible before. That is the part they actually asked about.

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.