explain
Skill2 starsChanged 3 months agoMITView on GitHub
Invoked by the owner only, never on your own initiative - do not use this skill unless they ask for it by name. Explain something in plain English, from the legal workflow outward. Use for a term, a decision, or a whole piece of work that was not made clear enough the first time.
130 other projects use a version of this.
Adopted by
Most recently taken up by
- tekumara/skillstheir own version, first seen Nov 16, 2026
- abdallahkht/arabic-motion-kittheir own version, first seen Nov 16, 2026
- nicodiansk/draw-it-outtheir own version, first seen Nov 16, 2026
- samsam007b/claude-code-standards-kittheir own version, first seen Nov 16, 2026
- librosdeia/builder-method-claude-plugintheir own version, first seen Nov 15, 2026
- dafto1/skillstheir own version, first seen Nov 15, 2026
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.
zebbernSkilldebug-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
Ingramradical235Skillroot-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
ralphkraussSkillresolve-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
neurofooSkillsocratic
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
AntaresYuanSkilliterate
Meta-skill for skill self-improvement. After another skill finishes a run, /iterate analyzes the run's logs (friction events, retries, sub-agent rejections, pacing mismatches, bugs), produces a structured retrospective report, accumulates per-class friction counts, and — when a class crosses the configured threshold — opens a PR to that skill's open-source repo with a proposed SKILL.md diff. NEVER auto-merges; the human always reviews. Target skills opt in by declaring an `iteration:` block in their frontmatter. Invoke when the user says "iterate this skill", "iterate /devloop", "run a retro on the last skill run", "/iterate <skill-name>", or when a target skill auto-hands-off at end of its run.
Also in 3 projects that use this
anombyte93Skilldiscover
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
Other versions130 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 130
- Z3Prover/z3★ 13ksame name
- crbnos/carbon★ 2.8ksame name
- poshan0126/dotclaude★ 871same name
- VinkyDev/vibestart★ 295same name
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- entireio/skills★ 240same name
- sammcj/agentic-coding★ 172same name
- SerhiiKorniienko/bullshit-detector★ 151same name
- kv0906/pm-kit★ 138same name
120 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.
In this repository21 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .claude/rules/agents.mdAGENTS.md
- evals/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-reviewSkill
- code-reviewSkill
- evaluation-reviewSkill
- interview-reviewSkill
- learning-reviewSkill
- security-reviewSkill
- start-projectSkill
- architecture-reviewSkill
- code-reviewSkill
- evaluation-reviewSkill
- explainSkill
- interview-reviewSkill
- learning-reviewSkill
- security-reviewSkill
- start-projectSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 118 edited versions we read keep these.
6
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
- Distinctive: line 23
If the request is a bare "explain that" after a message that did not land, treat it as whichever of the three the message was mostly about.
- Distinctive: line 30
Follow the teaching order in AGENTS.md How to work with the owner, and start further back than feels necessary:
- Very specific: line 74
Check the term that failed against docs/GLOSSARY.md.
- Distinctive: line 78
Not there?: Add it once the owner can use the term correctly, following the rules at the top of the glossary.
- Distinctive: line 82
If the confusion was about a *legal* word being used loosely rather than an engineering one — a proposed deadline described as a deadline, …
- Very specific: line 96
An explanation that finally landed is evidence: If the owner then uses the concept correctly, catches a problem with it, or explains it …
- Distinctive: line 102
Every other teaching decision in this repository is made by the agent, which judges when a concept needs explaining and how far back to …
- Distinctive: line 108
Treat a use of this skill as a signal about the previous explanation, not about the owner.
“Common” is measured: kept by at least 6 in 10 of the 118 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.
Files
<!-- Generated from ../../../.claude/skills/explain/SKILL.md - do not edit this copy.
Edit the source and run `uv run python scripts/sync_agent_files.py`. -->Explain
The owner has asked for something to be explained, or re-explained. Work out which of three ranges is being asked about, since they need different answers:
- A word. A term arrived before the idea behind it. Build the idea first, then attach the word to it.
- A decision. Something was chosen and the reasoning did not come across, or was never stated. Explain the pressure that forced a choice, the options, and why this one.
- What we just did. A stretch of work needs summarising into something the owner could describe to somebody else. Explain what changed, why, and what it now makes possible.
If the request is a bare "explain that" after a message that did not land, treat it as whichever of the three the message was mostly about. Do not repeat the same explanation more slowly, and do not apologise at length — go back further than you did the first time and build up from something the owner already has.
How to explain
Follow the teaching order in AGENTS.md How to work with the owner, and start further back than feels necessary:
- The practical problem. What is actually happening in the workflow or the code? Use the owner's own domain — a matter, a letter, a bundle, a deadline — not an abstract software example.
- What we are changing, and why. What concrete difficulty does it remove?
- The technical name, last. Introduce it only once the idea underneath is already clear, and only if the owner will meet the word again.
Two habits make the second attempt land where the first did not:
- Use one concrete example rather than a general description. "The code that reads the letter also decides where the result is saved, so changing where results go could break the reading" beats any definition of separation of concerns.
- Say what the thing is for before saying what it is. A schema is a definition of the exact shape of information the rest of the program expects; that is worth knowing before the word "schema" appears.
- Say which part was the software and which was the model. In this repository that distinction is usually the explanation. "The rules found the date; nothing here decided whether it was a real obligation" is a different system from one where a model made that call, and the owner cannot judge how far to trust an output without knowing which they are looking at.
Then check: ask which part is still unclear, rather than asking whether it now makes sense. The second question is easy to answer politely and tells you nothing.
Explain what is actually true
An explanation is not a performance of confidence. Where the honest answer involves something the project has not established, say so in the explanation rather than around it:
- "We do not know how often it gets that right — we have never measured it" is the
correct explanation of an unevaluated behaviour, and it points at the next piece of work
rather than papering over it. Route that to
evaluation-review. - "That was a guess, and it has not been tested" is a legitimate answer about a design choice made early.
A fluent explanation of something nobody has evidence for is worse than an awkward one, because it produces confidence the work has not earned — which is the failure this whole repository is built to avoid.
Keep the glossary honest
Check the term that failed against docs/GLOSSARY.md.
- Already there, and the entry did not help? The entry is the problem. Rewrite it using the explanation that just worked.
- Not there? Add it once the owner can use the term correctly, following the rules at the top of the glossary. A term the owner has just understood is exactly the term worth recording; a term they have merely been shown is not.
If the confusion was about a legal word being used loosely rather than an engineering one — a proposed deadline described as a deadline, "matter" and "case" used interchangeably — that is more serious than a vocabulary gap, because the software will inherit the ambiguity. Settle which meaning is intended, then fix it in the glossary and anywhere the code or documents used it the other way.
Where a good explanation should end up
Two of these are worth keeping rather than leaving in a transcript.
- A decision explained well is most of an interview answer. Where the range was a
decision, close with the short version the owner could say to someone else: the problem,
the options, the choice, and what would make them revisit it.
interview-reviewbuilds on that; this skill produces the raw material. - An explanation that finally landed is evidence. If the owner then uses the concept
correctly, catches a problem with it, or explains it back, that is exactly what
docs/learning-log/exists to record. Being shown something is not.
Why this exists
Every other teaching decision in this repository is made by the agent, which judges when a
concept needs explaining and how far back to start. It will sometimes get that wrong, and
the cost of the owner saying so should be as close to zero as possible. Typing /explain
is meant to be easier than composing a sentence that admits an explanation missed — the
friction it removes is social, not technical.
Treat a use of this skill as a signal about the previous explanation, not about the owner. Two uses in quick succession mean the pitch is starting too far in; go back to the workflow and rebuild from there.
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
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.

