Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

intelligence-vocabulary — Claude Code skill: setup and usage

Locks customer-facing CopilotKit Intelligence docs to a single approved term per concept. Useful when writing docs, nav items, and alt text in showcase/shell-docs.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add CopilotKit/CopilotKit --skill intelligence-vocabulary -a claude-code
Open on GitHub

What intelligence-vocabulary does

The skill enforces consistent phrasing across CopilotKit Intelligence customer documentation. It checks headings, navigation items, button copy, and image alt text against the word list in references/words.md. Every synonym for an established term gets flagged as a regression and replaced with the designated entry from the Use column. Plan names stay strictly as Developer, Team, Team Self-hosted, and Enterprise.

The tool applies strictly to documentation, not code. If an identifier, API field, route slug, or environment variable matches a term from the Stop list, leave it alone. Renaming code to match this vocabulary will break the project. Exceptions such as customer-managed or hosted zone remain intact.

What it helps with

  • prevent multiple names for the same CopilotKit Intelligence concept
  • catch forbidden terminology using the references/words.md stop list
  • standardize plan names across public documentation
  • verify button labels and alt text in showcase/shell-docs

Example prompts for the agent

  • Review showcase/shell-docs for unapproved Intelligence synonyms using references/words.md
  • Check the button labels and alt text in the new Intelligence page against the vocabulary list
  • Audit the pricing prose to ensure plan names match the approved list

How to install intelligence-vocabulary

1Skills CLI (Vercel)

npx skills add CopilotKit/CopilotKit --skill intelligence-vocabulary -a claude-code

2Manually: put the files in place

~/.claude/skills/intelligence-vocabulary/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/intelligence-vocabulary/

From the same set6

The whole set →

Similar

clean-user-facing-text guillaumemeyer Cleans reader-facing prose by auditing invisible Unicode and smoothing repetitive AI cadences. Keeps code, facts, and author voice intact. Claude Code CX Codex Cursor +1 439installs shipping-artifacts phuryn Generates core documentation to make vibe-coded applications reviewable before release. It maps architecture, permission flows, and test coverage for audits. Claude Code CX Codex Cursor +1 1,700installs inkos Narcooo A harness for text work: novels, scripts, storyboards, interactive film, long translation. The agent writes to files as separate actions and reports an artifact revision you can check. Claude Code CX Codex Cursor +1 627installs pptx-slide-specification kimtth A skill for writing and repairing coordinate-explicit JSON specs of slides, so an editable PPTX deck builds the same way every time. Claude Code CX Codex Cursor 2,600installs dataset-curation Seth Hobson This skill formats and checks datasets for model fine-tuning. Use it to prepare data for SFT or preference training before a run. Claude Code CX Codex Cursor 2,600installs write-pr tldraw Sets PR title and description standards: semantic types, structured templates, and reviewer-focused writing rules. Claude Code CX Codex Cursor +1 419installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs

Questions about intelligence-vocabulary

How to install intelligence-vocabulary in Claude Code?

Run npx skills add CopilotKit/CopilotKit --skill intelligence-vocabulary -a claude-code.

What does intelligence-vocabulary do?

It enforces a standardized vocabulary for CopilotKit Intelligence documentation, replacing forbidden synonyms with approved terms.

Does intelligence-vocabulary rename code variables or API fields?

No. It targets customer-facing prose only, leaving code identifiers, route slugs, component names, and environment variables untouched.

Source text

SKILL.md · MIT
---
name: intelligence-vocabulary
description: >
  Locks customer-facing CopilotKit Intelligence docs to one approved name per
  concept. Use when writing, editing, or reviewing Intelligence docs, nav
  labels, signup labels, or image alt text in showcase/shell-docs. Don't use
  for renaming code identifiers, route slugs, env vars, API fields, or
  component names, or for docs that do not mention Intelligence.
version: 1.0.0
---

# Intelligence Vocabulary

Customer-facing Intelligence docs use one name per concept. A second name for the same thing is a regression.

## When To Use

Load this skill before writing or editing prose a customer reads about CopilotKit Intelligence. That includes pages, snippets, nav titles, button labels, and image alt text under `showcase/shell-docs`.

Also load `skills/intelligence-docs/SKILL.md` when the change adds, renames, or removes an Intelligence page. That skill keeps the landing page in sync. This skill owns the words.

Do not load this skill to rename code. Identifiers, route slugs, env vars, API fields, and component names stay as they are, even when a Stop word appears inside them.

## Procedures

### Procedure 1: Apply the word list

1. Read `references/words.md` before writing or editing customer-facing Intelligence prose.
2. Use the **Use** column for headings, nav titles, button labels, alt text, and body prose.
3. Keep plan names as Developer, Team, Team Self-hosted, and Enterprise.
4. If a fact already has a home in `references/words.md`, link to that page. Do not explain the fact again under a second name.
5. Write Inspector click steps with the labels the shipped controls render: **Rich Threads** and **Automatic Learning**.

### Procedure 2: Check the change

1. Search the added or edited prose for every phrase in the **Stop** column of `references/words.md`.
2. Keep a hit that the exception list in `references/words.md` names.
3. Rewrite every other hit to the **Use** word for that concept.
4. Leave identifiers, slugs, env vars, API fields, and component names unchanged.

## Decision Tree

- Customer-facing Intelligence prose, labels, or alt text: Procedure 1, then Procedure 2
- Page added, renamed, or removed: this skill for the words, and `skills/intelligence-docs/SKILL.md` for the landing page
- The only edit is code, a slug, an env var, or an API field: stop. Do not rename it to match the word list
- The page does not mention Intelligence: stop

## Red Flags

| Signal                                                                  | What it means                  | Do instead                                         |
| ----------------------------------------------------------------------- | ------------------------------ | -------------------------------------------------- |
| Two names for one concept on the same page                              | The word list was skipped      | Procedure 2                                        |
| "managed" or "hosted" as the name of the CopilotKit-operated deployment | The deployment name drifted    | Write cloud-hosted                                 |
| A Stop word removed by renaming a component, slug, or env var           | The skill was applied to code  | Restore the identifier. Change only customer prose |
| Clerk, or a rollout cutoff, added to a customer page                    | Internal implementation leaked | Delete that sentence. Say what the customer does   |

## Error Handling

- **A Stop phrase is inside an identifier:** leave the identifier. Change the surrounding prose only when that prose uses the Stop word as a customer-facing name.
- **A hit is on the exception list:** keep it. Do not "fix" managed Channel, customer-managed, a hosted zone, a ticket id, or a plan name.
- **The approved word and the visible product label disagree:** use the label the shipped control renders for a click step. Record the conflict. Do not invent a third name.
- **No home exists for a new fact:** stop and name the missing page. Do not park the fact under a nearby page with a new synonym.

© CopilotKit · MIT · CopilotKit/CopilotKit

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor