term-explainer
Skill8 starsChanged 5 months agoMITView on GitHub
Finds the technical terms, acronyms, and domain phrases on the current page and defines each in plain language, with why it matters in this context. Use when the user says "explain the jargon", "define these terms", "what does X mean here", "build a glossary", or asks about acronyms, abbreviations, or unfamiliar terminology on the page.
In this repository46 other files it gives its agents.
- answerSkill
- api-to-exampleSkill
- bilingual-readerSkill
- calendar-prepSkill
- caption-assistantSkill
- chart-explainerSkill
- code-translatorSkill
- competitor-snapshotSkill
- coupon-hunterSkill
- course-fit-checkSkill
- cover-letter-builderSkill
- deal-checkerSkill
- draft-from-notesSkill
- explainSkill
- fact-checkSkill
- fix-grammarSkill
- hook-generatorSkill
- improve-writingSkill
- interview-prepSkill
- job-application-assistantSkill
- job-fit-reviewSkill
- job-offer-compareSkill
- landing-page-critiqueSkill
- linkedin-outreachSkill
- localize-textSkill
- meeting-follow-upSkill
- outline-builderSkill
- paper-readerSkill
- portfolio-project-reviewSkill
- product-review-summarizerSkill
- pronunciation-and-usageSkill
- regex-decoderSkill
- reply-assistantSkill
- repo-onboarderSkill
- rewrite-longerSkill
- rewrite-shorterSkill
- social-post-generatorSkill
- source-finderSkill
- source-listSkill
- study-planSkill
- style-matchSkill
- summarizeSkill
- table-to-csvSkill
- terminology-keeperSkill
- tone-rewriterSkill
- translateSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 19
If a term could mean different things in different fields, say so rather than guessing the one the page intends.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Term Explainer
Scan the page for the technical terms, acronyms, and domain phrases that trip readers up, and define each in plain language with why it matters in this particular context. Never invent a definition, force one meaning onto an ambiguous acronym, or define common words that carry no special domain sense here.
- Extract only the terms that matter for understanding this page: acronyms, specialized phrases, metrics, legal terms, formulas, product names, unfamiliar abbreviations.
- Define each in plain language. Expand acronyms; keep each term's original form and capitalization.
- Tie each definition to how the page uses the term — why it matters here.
- If a term could mean different things in different fields, say so rather than guessing the one the page intends.
- Works in any language: read terms as written, respond in the user's language, and add a transliteration or short gloss for terms in another script.
Report each term with its plain meaning, why it matters here, and any related terms or gotchas. Preserve exact names, numbers, and formatting, and skip words that are merely everyday vocabulary in the page's own language.
Example
Source: a fintech page noting "we report on an EBITDA basis."
EBITDA — Earnings Before Interest, Taxes, Depreciation, and Amortization.
Plain meaning: A measure of profit that strips out interest, taxes, and the accounting charges for aging assets, to approximate the cash earnings from a company's core operations.
Why it matters here: The page is signaling profitability before financing and accounting effects, which usually looks rosier than net income — so it's worth noting what the figure leaves out.
Related terms or gotchas: Not the same as net income or free cash flow; "adjusted EBITDA" can exclude even more and varies by company, so it isn't a standardized figure.
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.

