New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Write Missing Core Words

by nicejade in nicejade/gpt-wordbook

Batch author missing vocabulary MDX files for the gpt-wordbook project.

MITAuto-check passedDocuments & Office

Install Write Missing Core Words

skills CLI
$ npx skills add nicejade/gpt-wordbook --skill write-missing-core-words -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nicejade/gpt-wordbook write-missing-core-words --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nicejade/gpt-wordbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/write-missing-core-words .claude/skills/write-missing-core-words && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
write-missing-core-words
GitHub stars
167
Token cost
~1.1k tokens
SKILL.md length
467 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Batch author missing vocabulary MDX files for the gpt-wordbook project.

  • Works in 4 steps: Plan a small batch → Author files in the project format → Follow content guardrails → …
  • Codex needs to fill entries listed in scripts/missing-core.json
  • SKILL.md covers Quick Start, Workflow, Helper Scripts and Recovery Pattern
  • Calls node and pnpm

What it does

Write Missing Core Words is an agent skill from nicejade/gpt-wordbook. Batch author missing vocabulary MDX files for the gpt-wordbook project. Use when Codex needs to fill entries listed in scripts/missing-core.json, create or revise src/content/docs/words/.mdx in the house style, plan safe writing batches, or verify that generated word pages match the required structure.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/batch-playbook.md` and `references/entry-template.md`).

It sits in Documents & Office, covering Markdown and Static sites and blogs. It works with Vite, Astro and Tailwind CSS. The repository describes itself as: 智析单词书（GPT-Wordbook）是由 AI 赋能的智能英语词汇学习平台，通过 GPT 模型自动生成深度词汇解析内容，帮助学习者从词义、例句、词根词缀、文化背景到助记技巧全面理解单词，而不是简单记忆。项目以 Astro 静态网站 + GPT 内容生成 为核心架构，兼顾性能、可扩展性，是英语学习者、考试备考者和教育者的利器。… The licence is MIT.

When your agent uses it

  • Codex needs to fill entries listed in scripts/missing-core.json
  • Revise src/content/docs/words/.mdx in the house style
  • Plan safe writing batches
  • Verify that generated word pages match the required structure

Example prompts

  • “/write-missing-core-words”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Plan a small batch
  2. Author files in the project format
  3. Follow content guardrails
  4. Validate immediately after writing

What it can do on your machine

Read from SKILL.md and the folder at commit 0795775. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node
    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Write Missing Core Words loads about 1.1k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nicejade/gpt-wordbook at commit 0795775, republished under its MIT licence (© nicejade). 467 words, ~1,121 tokens.

Download SKILL.mdSave it as .claude/skills/write-missing-core-words/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
write-missing-core-words
description
Batch author missing vocabulary MDX files for the gpt-wordbook project. Use when Codex needs to fill entries listed in scripts/missing-core.json, create or revise src/content/docs/words/*.mdx in the house style, plan safe writing batches, or verify that generated word pages match the required structure.

Write Missing Core Words

Use this skill to add missing core vocabulary pages without re-discovering the workflow every time.

Quick Start

  1. Select the next batch:
bash
node .codex/skills/write-missing-core-words/scripts/next-batch.mjs --limit 15
  1. If you want a reusable manifest for the batch, write one:
bash
node .codex/skills/write-missing-core-words/scripts/next-batch.mjs \
  --limit 15 \
  --manifest /tmp/missing-core-batch.json

  1. Read the style references before writing:

  2. Create one MDX file per selected word under src/content/docs/words/.

  3. Validate the batch:

bash
node .codex/skills/write-missing-core-words/scripts/verify-word-batch.mjs \
  --manifest /tmp/missing-core-batch.json

Workflow

1. Plan a small batch
  • Default to 10-20 words per batch.
  • Go above 20 only when the user explicitly prioritizes throughput over reviewability.
  • Do not edit scripts/missing-core.json; treat it as the source of truth.
  • Do not overwrite unrelated user changes in the workspace.
2. Author files in the project format

For each selected word:

  • Create src/content/docs/words/<word>.mdx.
  • Keep the filename lowercase.
  • Capitalize the first letter in frontmatter title.
  • Keep this frontmatter shape:
yaml
---
title: Word
description: ...
sidebar:
  hidden: true
tableOfContents: false
---
  • Always import Pronunciation from ../../../components/Pronunciation.svelte.
  • Import WordRelations only when at least one synonym or antonym is present.
  • Keep section order exactly as shown in references/entry-template.md.
  • Write explanations in Chinese.
  • Keep example sentences in English and translations in Chinese.
  • Prefer natural, high-frequency meanings and collocations over rare senses.
  • Prefer conservative etymology. If a root story is uncertain, stay factual and avoid speculative pseudo-analysis.
3. Follow content guardrails
  • Avoid placeholders such as Example sentence, 需要进一步研究, common collocation, or A short story using ....
  • Avoid empty WordRelations arrays. Omit the component instead.
  • Prefer 2-5 synonyms and 1-4 antonyms, using simple lemma forms when possible.
  • Keep the page helpful for learners: concrete usage, concise explanations, practical collocations, memorable examples.
  • Prefer relation words that are likely to have entries in this repo, but do not block on perfect coverage.
Show full SKILL.md (200 more words)Show less
4. Validate immediately after writing
  • Run verify-word-batch.mjs on the exact batch you created.
  • Fix structure issues before moving to the next batch.
  • If you changed many files or touched shared components, run pnpm build.

Helper Scripts

scripts/next-batch.mjs

Use this script to compute the next writable batch from scripts/missing-core.json.

Supported flags:

  • --limit <n>: number of words to select, default 20
  • --offset <n>: skip this many remaining words before selecting
  • --from <word>: start from a specific remaining word
  • --manifest <path>: write the selection to a JSON manifest
  • --json: print machine-readable JSON
scripts/verify-word-batch.mjs

Use this script to validate newly created files.

Supported flags:

  • --words word1,word2: validate an explicit word list
  • --manifest <path>: validate the selectedWords from a manifest

The validator checks:

  • file existence
  • required frontmatter fields
  • required headings in order
  • Pronunciation import and component usage
  • WordRelations import/component consistency
  • at least three numbered examples
  • common placeholder text that should be replaced

Recovery Pattern

  • If validation fails, fix the files first instead of continuing with the next batch.
  • If a word already exists by the time you start writing, skip it and continue.
  • If a word is hard to analyze confidently, write a simpler but accurate learner-friendly entry instead of forcing a speculative deep dive.

© nicejade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .codex/skills/write-missing-core-words of nicejade/gpt-wordbook.

  • SKILL.md
  • agents/openai.yaml
  • references/batch-playbook.md
  • references/entry-template.md

Open the folder on GitHubat commit 0795775

Compare with similar skills

Write Missing Core Words next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Write Missing Core Words compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Write Missing Core Words this skillnicejade/gpt-wordbook167—~1.1kAutomated safety check: PassMIT
Using Docs Kitlobehub/lobe-ui2.2k—~2.8kAutomated safety check: PassMIT
Portable Text Serializationsanity-io/agent-toolkit1871 repos~1.1kAutomated safety check: PassMIT
Publish Skillglebis/claude-skills388—~4.1kAutomated safety check: PassMIT
Codebase Wikiryuever/react-tapable-editor365—~1.8kAutomated safety check: PassNone
Launch With AWSaws/agent-toolkit-for-aws2.8k—~3.2kAutomated safety check: PassApache-2.0

Similar skills

  • Using Docs Kit

    lobehub/lobe-ui

    Set up and author a documentation site with @lobehub/docs-kit (the lobedocs CLI, React Router + Vite static docs used by ui.lobehub.com).

    2.2k GitHub stars~2.8k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Portable Text Serialization

    sanity-io/agent-toolkit

    Official

    Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text.

    187 GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed

  • Publish Skill

    glebis/claude-skills

    This skill should be used when publishing a new or updated skill to the claude-skills-site Astro website.

    388 GitHub stars~4.1k tokensUpdated 11 days ago
    Documents & OfficeAuto-check passed

  • Codebase Wiki

    ryuever/react-tapable-editor

    将对话中的源码阅读与分析整理为规范化 Markdown，归档到项目 codebase-wiki/（architecture/discussion/issue/reference/roadmap）、维护 INDEX 与 references 图；支持 VitePress、Mintlify、Starlight、Fumadocs 等文档站点。适用于「保存到 wiki / 归档到…

    365 GitHub stars~1.8k tokensUpdated 4 mo ago
    Knowledge ManagementAuto-check passed

  • Launch With AWS

    aws/agent-toolkit-for-aws

    Official

    Migrates vibe-coded web applications to AWS. An agent skill from aws/agent-toolkit-for-aws.

    2.8k GitHub stars~3.2k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Cloudbase Sites Runtime

    TencentCloudBase/CloudBase-AI-Toolkit

    A skill your agent uses when the user wants to develop, run, preview, save, deploy, or roll back a CloudBase Web app in this conversation as a Lovable/Codex-Sites-like vibe- coding session — i.e.

    1.1k GitHub stars~5k tokensUpdated yesterday
    MobileAuto-check: notes

Works with

Categories

Questions about Write Missing Core Words

What does Write Missing Core Words do?

Batch author missing vocabulary MDX files for the gpt-wordbook project. Write Missing Core Words is an agent skill from nicejade/gpt-wordbook. Batch author missing vocabulary MDX files for the gpt-wordbook project.

When should I use Write Missing Core Words?

Write Missing Core Words fits situations like: Codex needs to fill entries listed in scripts/missing-core.json; revise src/content/docs/words/.mdx in the house style; plan safe writing batches; verify that generated word pages match the required structure.

How do I install Write Missing Core Words in Claude Code?

Run `npx skills add nicejade/gpt-wordbook --skill write-missing-core-words -a claude-code`. Or copy the skill folder (.codex/skills/write-missing-core-words in nicejade/gpt-wordbook) into .claude/skills/write-missing-core-words in your project. Claude Code loads it when a task matches its description.

How do I install Write Missing Core Words in Codex?

Run `npx skills add nicejade/gpt-wordbook --skill write-missing-core-words -a codex`. Or copy the skill folder (.codex/skills/write-missing-core-words in nicejade/gpt-wordbook) into .agents/skills/write-missing-core-words in your project. Codex loads it when a task matches its description.

Can I use Write Missing Core Words in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nicejade/gpt-wordbook --skill write-missing-core-words -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-missing-core-words, .gemini/skills/write-missing-core-words, .github/skills/write-missing-core-words and .opencode/skills/write-missing-core-words in your project.

What does Write Missing Core Words need to run?

Going by SKILL.md and its folder, Write Missing Core Words needs the command-line tools its instructions call (node and pnpm).

Does Write Missing Core Words access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Write Missing Core Words safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Write Missing Core Words use?

Write Missing Core Words is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Write Missing Core Words use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 878 tokens, read only when the agent opens those files.

What are the alternatives to Write Missing Core Words?

Skills that share tags, products or a category with Write Missing Core Words: Using Docs Kit (lobehub/lobe-ui, 2.2k stars), Portable Text Serialization (sanity-io/agent-toolkit, 187 stars), Publish Skill (glebis/claude-skills, 388 stars) and Codebase Wiki (ryuever/react-tapable-editor, 365 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Missing Core Words?

nicejade (a GitHub user) maintains it in nicejade/gpt-wordbook, which has 167 GitHub stars. The repository was last updated on September 1, 2026.

Source: nicejade/gpt-wordbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.