eli5
Skill1 starsChanged 14 days agoMITView on GitHub
Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and every schema change.
66 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- Suge8/friedbuntheir own version, first seen Nov 8, 2026
- thoughtbot/rails-consultanttheir own version, first seen Nov 8, 2026
- GeiserX/sstacktheir own version, first seen Nov 8, 2026
- dzhng/jevgrepword for word, first seen Nov 7, 2026
- GeiserX/agent-skillstheir own version, first seen Nov 6, 2026
- GeiserX/claude-skillstheir own version, first seen Nov 6, 2026
Used with
Projects with it also use implement-spec-with-codex, audit-decisions and 1 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.
dzhngSkillimplement-spec-with-codex
Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.
Also in 4 projects that use this
wolverin0Skillaudit-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
GeiserXSkilldocs-loop
Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.
Also in 3 projects that use this
Other versions66 projects use a version of this.
Word for word · 4
- dzhng/jevgrep★ 3.2k100% same
- dzhng/skills★ 1.5k100% same
- dzhng/yap★ 112100% same
- dzhng/duet-agent★ 55100% same
Edited · 1
- kv0906/cc-skills★ 4286% same
Wrote their own version · 61
- advaitpaliwal/feynman★ 10ksame name
- companion-inc/feynman★ 10ksame name
- getcompanion-ai/feynman★ 10ksame name
- cloudflare/cloudflare-docs★ 5.4ksame name
- anthropics/claude-plugins-community★ 4.8ksame name
- coldteadotai/pr-lens★ 2.4ksame name
- DreambigOu/ELI5★ 1.4ksame name
- ahmadrosid/nakama★ 786same name
- huang-sh/PiX★ 235same name
- mblode/agent-skills★ 189same name
51 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 repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11ySkill
- agents-mdSkill
- antislop-codeSkill
- antislop-copywritingSkill
- antislop-humanSkill
- antislop-layoutmobileSkill
- antislopSkill
- antislop-uiSkill
- askSkill
- audit-agentsSkill
- audit-choicesSkill
- audit-performanceSkill
- audit-testsSkill
- auto-researchSkill
- close-specSkill
- code-reviewSkill
- compare-screenshotsSkill
- debugSkill
- design-mdSkill
- design-with-imagesSkill
- document-codebaseSkill
- eval-skillsSkill
- explore-unknownsSkill
- handoff-specSkill
- implementSkill
- learnSkill
- marketing-pagesSkill
- memorySkill
- okf-contextSkill
- preview-shotsSkill
- quick-planSkill
- ratchet-filesSkill
- refactor-cleanSkill
- rememberSkill
- repoagent-doc-generationSkill
- retroSkill
- reviewSkill
- rtkSkill
- screenshot-critiqueSkill
- specifySkill
- spec-planSkill
- spec-tasksSkill
- statusSkill
- system-designSkill
- verifySkill
- write-docsSkill
- write-skillsSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 46 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Use small concrete examples without replacing precise claims with analogies.
- Distinctive: line 40
Read the complete referenced artifact and inspect current owners when the spec alone cannot establish behavior.
- Distinctive: line 55
Use these headings in order:
- Distinctive: line 69
Call out destructive resets, migration requirements, compatibility behavior, eventual consistency, and intentional data loss directly.
- Distinctive: line 71
Do not omit a schema change because it is operational rather than user-visible.
“Common” is measured: kept by at least 6 in 10 of the 46 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
ELI5
Turn the referenced spec or change into an accurate mental model for a technical reader who does not live in the code. Plain language, full precision: simplify the telling, never the claims.
The Register
Other skills point here when their output must be readable by someone who didn't live the work. The reader is technical — pseudocode and precise claims land fine — but they have read none of the code and none of the session's messages: no diff, no transcript, no labels the work invented along the way. Writing ELI5 means:
- Walk one concrete scenario end to end — the triggering event, what happens today, what the change (or the unbuilt alternative) would do — instead of describing properties in the abstract.
- Define every term of art at first use; never lean on labels the spec, code, or session invented.
- Use small concrete examples without replacing precise claims with analogies.
- Reach for pseudocode when explaining control flow, ordering, or timing. Prose describing when-something-fires reads as plausible and hides the gap; five lines of pseudocode make the gate visible and let the reader see the case you missed. Write it at the level of the decision, not the implementation — the conditions and their order, not real function signatures. The tell that you needed it: your prose contains "only when", "before", "unless", or "as soon as" and the reader still cannot say what happens on the second call.
- The test: the text stands alone, without the diff, the spec, or the transcript. If the reader must ask "explain this part", it failed.
Workflow
- Read the complete referenced artifact and inspect current owners when the spec alone cannot establish behavior. When no artifact is named, explain the session's current change (working tree or branch diff). Separate what exists today from what is only proposed.
- Explain the problem through its user or operational consequence, including why the current design produces it.
- Explain the solution as one simple before/after data flow. Introduce each component by responsibility, not by filename or internal symbol.
- Inventory schema and durable-contract changes exhaustively: added, changed, removed, reset, and deliberately unchanged. Include cursor or wire-format cutovers when they affect stored data or readers. Say explicitly when there are no schema changes.
Output
Use these headings in order:
ProblemSolutionSchema changes
End with one short sentence stating what users should notice after the change.
Rules
- Lead with behavior and boundaries; mention implementation names only when they clarify ownership or a contract.
- Distinguish canonical records from derived indexes, caches, summaries, and presentation grouping.
- Call out destructive resets, migration requirements, compatibility behavior, eventual consistency, and intentional data loss directly.
- Do not omit a schema change because it is operational rather than user-visible.
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.

