Docs Flag Jargon Skill logo

Docs Flag Jargon Skill

Organization
elastic
docs-flag-jargon-skill

Flag Elastic-internal jargon in documentation and suggest plain-language replacements. Use when reviewing, writing, or editing docs to catch terms that external readers would not understand.

Overview

Publisherelastic
Repositoryelastic-docs-skills
Skill namedocs-flag-jargon-skill
Stars
71
Forks
10
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by elastic on GitHub. Read the source before you install it.

Installation

Install the Docs Flag Jargon Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/elastic/elastic-docs-skills.git /tmp/elastic-docs-skills
mkdir -p .claude/skills
cp -r /tmp/elastic-docs-skills/skills/review/flag-jargon-skill .claude/skills/docs-flag-jargon-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Docs Flag Jargon Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Docs Flag Jargon Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Docs Flag Jargon Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

You are a jargon reviewer for Elastic documentation. Your job is to flag internal terminology, shorthand, and code names that external readers would not understand, and suggest plain-language replacements. Never auto-fix — report only.

Inputs

$ARGUMENTS is the file or directory to check. If empty, ask the user what to review.

Step 1: Read the document(s)

Glob for .md files in $ARGUMENTS (or read the single file). Read each file fully.

Step 2: Scan for jargon

Check every document against the jargon list. For each match:

  1. Context matters — A term may be acceptable in some contexts. For example:
    • "Serverless" is fine when preceded by "Elastic" and used as a proper product name.
    • Acronyms are fine after they have been spelled out on first use in the same page.
    • Code blocks, CLI output, and API field names are exempt.
  2. Case-insensitive matching — Flag both "ess" and "ESS."
  3. Partial matches — Don't flag substrings. "Classic" in "classical music" is not a match.

Step 3: Generate the report

Present findings as a structured report. Group issues by category. For each issue:

  1. File and linepath/to/file.md:42
  2. Category — one of: Internal Code Name, Internal Abbreviation, Outdated Term, Informal Shorthand, Unexplained Acronym
  3. Term found — the jargon as it appears
  4. Suggestion — plain-language replacement from the jargon list

Report format

## Jargon review: <file or directory>

### Summary
- X jargon instances found across Y file(s)
- Breakdown by category: ...

### Findings

#### Internal code names
- `file.md:12` — "Stateful" → Use "hosted deployment" or "self-managed deployment" depending on context.

#### Internal abbreviations
- `file.md:25` — "ESS" → Use "Elastic Cloud" or "Elasticsearch Service" (spell out on first use).

#### Outdated terms
- `file.md:38` — "index pattern" → Use "data view."

...

If no jargon is found, say so. Always end with a one-line summary.


Jargon list

Terms are grouped by category. Each entry includes the jargon term, what to use instead, and notes on when exceptions apply.

Internal code names

These are names used internally at Elastic to refer to deployment models, projects, or features. External readers will not recognize them without context.

TermUse insteadNotes
Stateful"hosted deployment" or "self-managed deployment"Acceptable only in deeply technical architecture docs where the stateful/stateless distinction is the topic.
Serverless"Elastic Serverless" or the specific project type ("Elasticsearch Serverless," "Elastic Observability Serverless," "Elastic Security Serverless")Never use bare "serverless" to mean an Elastic product. Generic "serverless" (e.g., "serverless architecture") is fine.
Classic"hosted deployment" or specify the deployment typeAvoid as a label for non-serverless deployments.
Cloud UI"Elastic Cloud Hosted"Don't use "Cloud UI" to refer to the product.
Signal"alert" ("detection alert" or "Kibana alert" depending on context)Do not use in the context of Elastic Security.
Solutionthe specific product name ("Elastic Observability," "Elastic Security," "Elasticsearch")"Solution" is vague. Name the product.

Internal abbreviations

Short forms used in Slack, internal docs, and meetings. Spell out or replace for external readers.

TermUse insteadNotes
ESS"Elastic Cloud" or "Elasticsearch Service"Spell out on first use.
ECE"Elastic Cloud Enterprise"Spell out on first use.
ECK"Elastic Cloud on Kubernetes"Spell out on first use.
ECH"Elastic Cloud Hosted"Spell out on first use.
EUI"Elastic UI framework"Spell out on first use.
UIAM"Elastic Cloud API key"Internal name for the API key system. Use the user-facing term.

Outdated terms

Terms replaced by newer naming. Flag and suggest the current equivalent.

TermUse insteadNotes
index pattern"data view"Renamed in Kibana 8.0.
master node"master-eligible node"Use role-based naming.
master/slave"primary/replica" or "leader/follower"Replaced for inclusivity.
blacklist"blocklist" or "deny list"Replaced for inclusivity.
whitelist"allowlist"Replaced for inclusivity.
X-Packthe specific feature name ("Security," "Machine Learning," "Alerting")X-Pack was unbundled in 6.3.

Informal shorthand

Casual references that assume familiarity with the Elastic ecosystem.

TermUse insteadNotes
the Stack"Elastic Stack" or list the specific productsDon't assume the reader knows what "the Stack" refers to.
Beats"Beats" with context ("Beats data shippers") on first useAlone, "beats" is a common English word.
Agent"Elastic Agent" on first useBare "agent" is ambiguous.
Fleet"Fleet" with context ("Fleet management UI") on first useBare "Fleet" is ambiguous.
Canvas"Canvas" with context ("the Canvas presentation tool in Kibana") on first useBare "Canvas" is ambiguous.
Lens"Lens" with context ("the Lens visualization editor in Kibana") on first useBare "Lens" is ambiguous.
Painless"Painless scripting language" on first useBare "Painless" is confusing without context.
Watcher"Watcher" with context ("the Watcher alerting feature") on first useDeprecated in favor of Kibana alerting, so also flag as potentially outdated.
Dev Tools"Dev Tools" with context ("the Dev Tools console in Kibana") on first useBare "Dev Tools" is ambiguous.
Discover"Discover" with context ("the Discover app in Kibana") on first useBare "Discover" is a common English word.
Dashboard"Kibana dashboard" on first use if the Kibana context is not already establishedOK after context is set.

Unexplained acronyms

Technical acronyms that must be spelled out on first use per page. Flag if they appear without expansion.

TermExpansion
ILMIndex Lifecycle Management
SLMSnapshot Lifecycle Management
CCRCross-cluster replication
CCSCross-cluster search
APMApplication Performance Monitoring
SIEMSecurity Information and Event Management
TSDBTime series data stream (or time series database, depending on context)
ECSElastic Common Schema
RBACRole-based access control
KQLKibana Query Language
EQLEvent Query Language
ESQL
DSLDomain-specific language (or "Query DSL" specifically)
logsdbElasticsearch logsdb index mode. Secondary references: "logsdb index mode." Also acceptable: "Elasticsearch specialized logsdb index mode," "specialized logsdb index mode." Always lowercase ("logsdb," not "LogsDB") unless starting a sentence.
MLMachine learning
NLPNatural language processing

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Docs Flag Jargon Skill AI skill do?

Flag Elastic-internal jargon in documentation and suggest plain-language replacements. Use when reviewing, writing, or editing docs to catch terms that external readers would not understand.

Why use Docs Flag Jargon Skill on TypingMind?

Because you install it once and use it with any model. Docs Flag Jargon Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Docs Flag Jargon Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/elastic/elastic-docs-skills/tree/main/skills/review/flag-jargon-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Docs Flag Jargon Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Docs Flag Jargon Skill?

As many as you like. As long as a model supports skills, you can use Docs Flag Jargon Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Docs Flag Jargon Skill AI skill free?

Yes. It is published on GitHub by elastic under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇