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

Fluent Reading

by m98 in m98/fluent

Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions.

MITAuto-check: notesEducation

Install Fluent Reading

skills CLI
$ npx skills add m98/fluent --skill fluent-reading -a claude-code

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

GitHub CLI
$ gh skill install m98/fluent fluent-reading --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/m98/fluent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fluent-reading .claude/skills/fluent-reading && 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
fluent-reading
GitHub stars
420
Token cost
~1.8k tokens
SKILL.md length
511 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions.

  • Works in 9 steps: Load context → Opening → Pick text type + length → …
  • Tasks that involve Study guides and flashcards
  • SKILL.md covers Overview, When to Use, Instructions and Examples, plus 2 more sections
  • Calls python3

What it does

Fluent Reading is an agent skill from m98/fluent. Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions. Triggered only when the learner types /fluent-reading. Presents the text, waits for the learner to read, then asks questions one at a time with immediate feedback, and optionally adds new vocabulary to the spaced-repetition queue.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Education, covering Study guides and flashcards and Language learning. The repository describes itself as: The AI Language Learning Kit for Claude Code and others. The licence is MIT.

When your agent uses it

  • Tasks that involve Study guides and flashcards
  • Tasks that involve Language learning

Example prompts

  • “/fluent-reading”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Bash

Workflow steps

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

  1. Load context
  2. Opening
  3. Pick text type + length
  4. Present the text
  5. Question sequence (one at a time)
  6. Feedback per question
  7. Vocabulary review
  8. Session summary
  9. Update all databases

What it can do on your machine

Read from SKILL.md and the folder at commit 86fb80f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

    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

Fluent Reading loads about 1.8k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 511 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Bash

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 m98/fluent at commit 86fb80f, republished under its MIT licence (© m98). 511 words, ~1,764 tokens.

Download SKILL.mdSave it as .claude/skills/fluent-reading/SKILL.md (or your agent's skills folder).
name
fluent-reading
description
Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions. Triggered only when the learner types /fluent-reading. Presents the text, waits for the learner to read, then asks questions one at a time with immediate feedback, and optionally adds new vocabulary to the spaced-repetition queue.
allowed-tools
Read, Write, Bash
disable-model-invocation
true

Reading Comprehension Session

Overview

Present one text (100-500 words depending on level), ask 4-6 comprehension questions, extract vocabulary. Builds passive-to-active bridge: learners decode target-language writing, then answer questions that force recall.

When to Use

Trigger this skill only when the learner types /fluent-reading. The skill is gated with disable-model-invocation: true — 15-20 min interactive session with DB writes should never start from an ambiguous prompt.

Skip this skill below A1 mastery 3 — shorter flashcard drills (/fluent-vocab) are more appropriate for very early learners.

Instructions

1. Load context
bash
python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/read-db.py"

Need: learner-profile (level, target language, interests), mastery-db.skills_mastery.reading.

2. Opening
markdown
# 👀 {target_language} Reading Practice

Hallo {name}!

Today we're practicing **reading comprehension**. I'll show you a short {target_language} text, then ask you questions about it.

**Focus:** main ideas, details, vocabulary in context
**Level:** {CEFR}
**Duration:** 15-20 min

**Tips:**
- Read the whole text first
- Don't translate every word — get the gist
- Use context clues for unknown words
- Read the questions before rereading the text

**Ready? Let's read!** 📖
3. Pick text type + length

A2 types (100-200 words): personal email, short news, advertisement, instructions, simple story, blog post, social media post, info leaflet.

B1 (200-350 words): opinion pieces, longer narratives, structured guides.

B2+ (350-500): editorials, technical explanations, interviews.

Match the topic to learner-profile.focus_areas when possible.

4. Present the text
markdown
## 📄 Reading Text {N}

**Topic:** {topic}
**Type:** {text_type}
**Length:** ~{word_count} words

---

{target-language text — clean formatting, no inline translation}

---

Take your time. When you're done, type **"ready"**.
5. Question sequence (one at a time)

Rotate across these types:

Main idea:

markdown
## Vraag 1: Hoofdidee (main idea)

{question in target language}

a) {option 1}
b) {option 2}
c) {option 3}

**Type a, b, or c:**

Details:

markdown
## Vraag 2: Details

{specific question about the text}

**Type your answer:**

Vocabulary in context:

markdown
## Vraag 3: Vocabulaire

In the text it says "{word/phrase}". What does this mean?

a) {meaning 1}
b) {meaning 2}
c) {meaning 3}

Inference:

markdown
## Vraag 4: Begrijpen

{question requiring inference — not directly stated}

**Answer in {target language}:**

True / false:

markdown
## Vraag 5: Waar of niet waar?

{statement}

**Type your answer:**
6. Feedback per question
markdown
{✅ or ❌}

**Answer:** {correct_answer}

**Explanation:** {why — reference the text}

{If incorrect: **The text says:** "{relevant_quote}"}

**Score: {X}/10**

---
7. Vocabulary review

After the questions:

markdown
## 📚 New Vocabulary from the Text

| {target_language} | {native_language} | Example from text |
|-------|---------|-------------------|
| {word 1} | {meaning} | "{sentence}" |
| {word 2} | {meaning} | "{sentence}" |

**Save these for future review?** (They'll enter spaced repetition.)

Type "yes" to add, "no" to skip.

If yes, stage each word for new_vocabulary[] in the end-of-session DB update.

8. Session summary
markdown
## 📊 Reading Session Complete!

**Text:** {title/topic}
**Length:** {words} words
**Questions:** {N}
**Accuracy:** {percent}%

### Comprehension Breakdown
- Main idea: {✅ or ❌}
- Details: {score}
- Vocabulary: {score}
- Inference: {score}

### New Words Added: {count}
{list}

### For Next Time
- {suggestion based on which question type was weakest}

**{target-language well done}!** 📖✨
9. Update all databases

Use the fluent-db-updater skill:

  • command_used: "/fluent-reading", skills_practiced: ["reading"]
  • skill_scores.reading: {exercises: N, correct: count_right, time_minutes}
  • errors[] — per question-type weakness (category comprehension, vocabulary, inference)
  • new_vocabulary[] — words the learner chose to save
  • focus_next_session[]

Save to /results/fluent-reading-session-{NNN}.md — include the full text + Q&A for later analysis.

Examples

Example 1 — personal email text (Dutch A2)

📄 Reading Text 1

Topic: Making weekend plans Type: Personal email Length: ~75 words

Beste Mohammad,

Bedankt voor je email! Leuk dat je naar Amsterdam komt volgende maand. Ik heb tijd op zaterdag 15 maart. Zullen we om 14:00 uur afspreken bij het Centraal Station? We kunnen naar een café gaan en daarna door de stad wandelen.

Het weer is meestal koud in maart, dus neem een warme jas mee! Ik verheug me erop om je te zien.

Groetjes, Lisa

Take your time. When you're done, type "ready".

Show full SKILL.md (181 more words)Show less
Example 2 — main-idea question on the above

Vraag 1: Hoofdidee

Waar gaat deze email over?

a) Lisa is op vakantie in Iran. b) Lisa en Mohammad maken plannen voor een ontmoeting. c) Lisa vraagt naar het weer.

Learner: "b"

✅ Correct!

Answer: b) Lisa en Mohammad maken plannen voor een ontmoeting.

Explanation: The email's core is the meetup plan — date, time, place, and activity. The weather is a secondary detail.

Score: 10/10

Critical Rules

  • Wait for "ready" before asking the first question. Rushing the reading step defeats the purpose.
  • One question at a time. Multiple at once invites skimming.
  • Ask questions in the target language (at least from A2 up). Reading-comprehension checks should happen in the same language as the text.
  • Quote the text in explanations so the learner can trace the answer back to the source.
  • Vocabulary opt-in. Don't force-add every unknown word — ask the learner which they want to keep.
  • Never auto-invoke. Gated; must fire only on explicit /fluent-reading.

Sample Text Bank (Dutch A2)

Advertisement
CURSUS NEDERLANDS VOOR BEGINNERS

Wil je Nederlands leren? Start deze maand nog!

- Kleine groepen (max 8 personen)
- Ervaren docenten
- 2x per week, 's avonds
- Locatie: Centrum Amsterdam
- Prijs: €150 per maand

Aanmelden kan via email: info@nederlandscursus.nl
Bel voor meer informatie: 020-123-4567

Eerste les gratis!

Keep a small bank per target language — don't reuse the same text in consecutive sessions.

© m98, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/fluent-reading of m98/fluent.

Open the folder on GitHubat commit 86fb80f

Compare with similar skills

Fluent Reading 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.

Fluent Reading compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fluent Reading this skillm98/fluent420—~1.8kAutomated safety check: NotesMIT
Study Companion Enmingchen666/Reviva236—~5.7kAutomated safety check: PassNone
Language Learningsundial-org/awesome-openclaw-skills663—~2.7kAutomated safety check: PassNone
German LearnerFerroxLabs/wayland608—~4.2kAutomated safety check: PassApache-2.0
Language Learning CoachFerroxLabs/wayland608—~4.4kAutomated safety check: PassApache-2.0
Portuguese LearnerFerroxLabs/wayland608—~3.2kAutomated safety check: PassApache-2.0

Similar skills

  • Study Companion En

    mingchen666/Reviva

    General study companion for learning, review, exam prep, exam-point analysis, syllabus/exam-outline interpretation, finals speedrun teaching, concept explanation, problem solving, homework coaching…

    236 GitHub stars~5.7k tokensUpdated 16 days ago
    EducationAuto-check passed

  • Language Learning

    sundial-org/awesome-openclaw-skills

    AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice.

    663 GitHub stars~2.7k tokensUpdated 7 mo ago
    EducationAuto-check passed

  • German Learner

    FerroxLabs/wayland

    Structured German learning path covering the case system, word order rules, compound word formation, verb conjugation including separable verbs and modal verbs, pronunciation patterns, and…

    608 GitHub stars~4.2k tokensUpdated yesterday
    EducationAuto-check passed

  • Language Learning Coach

    FerroxLabs/wayland

    Expert language learning methodology advisor covering acquisition theory comparison, immersion technique design, spaced repetition optimization, plateau diagnosis and breakthrough strategies…

    608 GitHub stars~4.4k tokensUpdated yesterday
    EducationAuto-check passed

  • Portuguese Learner

    FerroxLabs/wayland

    Portuguese language learning expertise covering Brazilian vs European Portuguese differences, pronunciation and phonology, essential grammar patterns, cultural context and etiquette, study…

    608 GitHub stars~3.2k tokensUpdated yesterday
    EducationAuto-check passed

  • Spanish Learner

    FerroxLabs/wayland

    Structured Spanish learning path from A1 to B2, covering grammar fundamentals, vocabulary acquisition through frequency lists, pronunciation coaching, verb conjugation mastery, cultural immersion…

    608 GitHub stars~3.8k tokensUpdated yesterday
    EducationAuto-check passed

More from m98/fluent

All 12 skills in this repo

  • Fluent Progress

    m98/fluent

    Show the learner's language learning progress, statistics, mastery levels, streak, and achievements.

    420 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check: notes

  • Fluent Session Analyzer

    m98/fluent

    Parse Fluent /results/.md session files to extract error patterns, strengths, accuracy trends, and focus areas for the next session.

    420 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Fluent Sm2 Calculator

    m98/fluent

    SM-2 spaced-repetition algorithm reference for the Fluent language learning system.

    420 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

  • Fluent DB Updater

    m98/fluent

    Atomically update all 6 Fluent learner databases (learner-profile, progress, mistakes, mastery, spaced-repetition, session-log) at session end by calling .claude/hooks/update-db.py with a single…

    420 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed

  • Fluent Feedback Formatter

    m98/fluent

    Canonical feedback template for every learner answer in the Fluent system — celebrate correct parts, correct mistakes with category and brief explanation, show the full correct version, score out of…

    420 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

  • Fluent Learn

    m98/fluent

    Main adaptive language-learning session that mixes skills (writing, speaking, vocabulary, reading) and exercise types based on the learner's current level, weak patterns, and due reviews.

    420 GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check: notes

Categories

Questions about Fluent Reading

What does Fluent Reading do?

Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions. Fluent Reading is an agent skill from m98/fluent. Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions.

When should I use Fluent Reading?

Fluent Reading fits situations like: tasks that involve Study guides and flashcards; tasks that involve Language learning.

How do I install Fluent Reading in Claude Code?

Run `npx skills add m98/fluent --skill fluent-reading -a claude-code`. Or copy the skill folder (.claude/skills/fluent-reading in m98/fluent) into .claude/skills/fluent-reading in your project. Claude Code loads it when a task matches its description.

How do I install Fluent Reading in Codex?

Run `npx skills add m98/fluent --skill fluent-reading -a codex`. Or copy the skill folder (.claude/skills/fluent-reading in m98/fluent) into .agents/skills/fluent-reading in your project. Codex loads it when a task matches its description.

Can I use Fluent Reading 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 m98/fluent --skill fluent-reading -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fluent-reading, .gemini/skills/fluent-reading, .github/skills/fluent-reading and .opencode/skills/fluent-reading in your project.

What does Fluent Reading need to run?

Going by SKILL.md and its folder, Fluent Reading needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Bash.

Does Fluent Reading 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 Fluent Reading safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Fluent Reading use?

Fluent Reading 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 Fluent Reading use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fluent Reading?

Skills that share tags, products or a category with Fluent Reading: Study Companion En (mingchen666/Reviva, 236 stars), Language Learning (sundial-org/awesome-openclaw-skills, 663 stars), German Learner (FerroxLabs/wayland, 608 stars) and Language Learning Coach (FerroxLabs/wayland, 608 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fluent Reading?

m98 (a GitHub user) maintains it in m98/fluent, which has 420 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on June 15, 2026.

Source: m98/fluent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.