agentleFS
Sign inStart free
OHOKAYYEAHOHOKAYYEAH/claude-skills/skills/explain/SKILL.md

explain

Skill1 starsChanged 33 days agoMITView on GitHub

Unpack the assistant's most recent action: what it did, why that approach, and one concept worth learning. Fire when the user signals they lost the thread ("explain that", "wait, what did you just do?", "I'm not following"), including mid-prompt. The skill itself only explains; if the surrounding prompt asks for more, do that after. Do not self-trigger. NOT /contextualize (re-grounds the subject, not the action).

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 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

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 109 edited versions we read keep these.

  • 4

    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:

    If an argument was passed, narrow to that specific part rather than re-explaining everything.

    line 17
  2. Distinctive:

    This skill does not continue the work: No edits, no new commands, no "and while I was here" — within the explanation itself.

    line 43
  3. Distinctive:

    Be honest about uncertainty: If you did something because it's the convention here rather than because you reasoned it out, say that.

    line 49
  4. Very specific:

    Skip the preamble: Start at ## What I did.

    line 53
  5. Distinctive:

    Keep it tight. Three short sections beat one long one.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 109 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

The user didn't follow the last thing you did. Unpack it — and explain what you actually did, not a tidied-up version of it.

If an argument was passed, narrow to that specific part rather than re-explaining everything.

Output shape

Three sections, these headings, in this order:

## What I did
## Why that way
## Worth learning: <the named concept>
  • What I did — the actual sequence, in order, in plain language. Name the real files, commands, and tools. If you took a wrong turn, backtracked, or something failed and you retried, say so — the detour is usually the part that was confusing.
  • Why that way — the reasoning, and at least one alternative you rejected and what made you reject it. "Why not the obvious thing" is often the whole answer.
  • Worth learning — one specific, nameable, searchable concept (a named pattern, a protocol, a tool's actual mechanism), plus one line on how it applied here. Not a broad field. "React hydration mismatches" — yes. "Learn more about React" — no.

Rules

  • Calibrate to a junior-to-mid engineer. Assume solid general programming knowledge, don't assume familiarity with this codebase's conventions or the specific library.
  • This skill does not continue the work. No edits, no new commands, no "and while I was here" — within the explanation itself. It is a read-only account of what already happened; the one exception is a cheap read (open a file, show a diff) purely to illustrate it. Scope that to the skill, not the turn: when /explain was sequenced inside a larger prompt ("explain that, then fix it"), finish the explanation, then carry on with the rest of the prompt as normal. It's a read-only pass, not a stop sign.
  • Be honest about uncertainty. If you did something because it's the convention here rather than because you reasoned it out, say that. If a step was a guess that happened to work, say that too — a confident-sounding explanation of a guess is worse than no explanation.
  • Skip the preamble. Start at ## What I did.
  • Keep it tight. Three short sections beat one long one; the user asked because they want to understand it, not to read an essay.

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