Agent skill

Fluent Writing

Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback.

MITAuto-check: notesAgent Workflows

Install Fluent Writing

skills CLI

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

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

GitHub CLI

$ gh skill install m98/fluent fluent-writing --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-writing .claude/skills/fluent-writing && 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/

Paste into Claude Code

Install the "fluent-writing" agent skill from https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing into .claude/skills/fluent-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluent-writing", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add m98/fluent --skill fluent-writing -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install m98/fluent fluent-writing --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/m98/fluent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/fluent-writing .agents/skills/fluent-writing && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "fluent-writing" agent skill from https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing into .agents/skills/fluent-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluent-writing", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add m98/fluent --skill fluent-writing -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install m98/fluent fluent-writing --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/m98/fluent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/fluent-writing .cursor/skills/fluent-writing && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "fluent-writing" agent skill from https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing into .cursor/skills/fluent-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluent-writing", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/m98/fluent.git --path .claude/skills/fluent-writing

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add m98/fluent --skill fluent-writing -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install m98/fluent fluent-writing --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/m98/fluent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/fluent-writing .gemini/skills/fluent-writing && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "fluent-writing" agent skill from https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing into .gemini/skills/fluent-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluent-writing", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install m98/fluent fluent-writing

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add m98/fluent --skill fluent-writing -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/m98/fluent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/fluent-writing .github/skills/fluent-writing && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "fluent-writing" agent skill from https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing into .github/skills/fluent-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluent-writing", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add m98/fluent --skill fluent-writing -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install m98/fluent fluent-writing --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/m98/fluent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/fluent-writing .opencode/skills/fluent-writing && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "fluent-writing" agent skill from https://github.com/m98/fluent/tree/main/.claude/skills/fluent-writing into .opencode/skills/fluent-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fluent-writing", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: fluent-writing
GitHub stars: 421
Token cost: ~1.8k tokens
SKILL.md length: 661 words
Files: 1
Skills in repo: 12
Repo updated: Jun 15, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback.

Works in 9 steps: Load context → Pick scenario type → Present the task → …
Agent Workflows work in your project
SKILL.md covers Overview, When to Use, Instructions and Examples, plus 2 more sections
Calls python3

What it does

Fluent Writing is an agent skill from m98/fluent. Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback. Triggered only when the learner types /fluent-writing. Selects a scenario matched to mastery, lets the learner compose, then analyzes grammar, register, vocabulary, structure, and spelling before updating all databases.

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 Agent Workflows. The repository describes itself as: The AI Language Learning Kit for Claude Code and others. The licence is MIT.

When your agent uses it

Agent Workflows work in your project

Example prompts

“/fluent-writing”

Requirements

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

Workflow steps

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

Load context
Pick scenario type
Present the task
Wait for the full text
Systematic error analysis
Detailed feedback
Optional rewrite
Session summary
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 Writing loads about 1.8k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 661 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~100
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). 661 words, ~1,752 tokens.

Download SKILL.mdSave it as .claude/skills/fluent-writing/SKILL.md (or your agent's skills folder).

name: fluent-writing
description: Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback. Triggered only when the learner types /fluent-writing. Selects a scenario matched to mastery, lets the learner compose, then analyzes grammar, register, vocabulary, structure, and spelling before updating all databases.
allowed-tools: Read, Write, Bash
disable-model-invocation: true

Writing Practice Session

Overview

Full-text writing practice with systematic correction. One scenario per session, detailed feedback broken down by severity and category, DB update at end. Mastery-driven scenario selection keeps the task at the right level — challenging, not frustrating.

When to Use

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

Skip this skill in favor of /fluent-vocab if the learner has not yet hit mastery 2 in basic vocabulary — writing needs a minimum word bank.

Instructions

1. Load context

bash

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

Need: learner-profile (level, target language, focus areas), mistakes-db (weak writing patterns), mastery-db (writing sub-skills).

2. Pick scenario type

From mastery-db.skills_mastery:

Formal email (if writing_formal_email mastery < 4)
Informal email (if writing_informal_email < 4)
Form filling (if writing_forms < 4)
Newsletter / personal text (if overall writing < 3)
Mixed scenarios (if all ≥ 4)

Scenarios must match the learner's CEFR level — A2 uses everyday situations, B1+ adds opinion / complaint / inquiry.

3. Present the task

markdown

## ✍️ Writing Exercise

**Scenario:** {clear description in native language}

**Task:** Write a {type} in {target_language}.

**Requirements:**
- Length: {X-Y} words
- Include: {must-include elements}
- Register: {formal / informal}
- Level: {CEFR}

{Optional: example structure for harder tasks}

**Write your {text_type} below:**

4. Wait for the full text

Don't correct mid-composition. Let the learner finish.

5. Systematic error analysis

Check every sentence for these categories:

Grammar — word order, conjugation, clause structure, articles
Formal/informal — register consistency
Vocabulary — wrong word, English mixing, register-wrong synonyms
Missing elements — greeting, closing, required fields
Spelling — minor at A2, weightier at B2+
Structure — organization, flow, paragraphing

Tag each finding with a severity: 🔴 critical, 🟡 moderate, 🟢 minor.

6. Detailed feedback

Diverges slightly from the standard fluent-feedback-formatter template because writing answers are multi-sentence. Use this variant:

markdown

## Feedback

### ✅ What You Did Well
- {strength 1}
- {strength 2}

### ❌ Areas to Improve

**Critical:** 🔴
- {issue}: "{wrong}" → **"{correct}"** — {why}

**Moderate:** 🟡
- {issue}: {explanation}

**Minor:** 🟢
- {spelling / punctuation}

### 📝 Corrected Version

{fully corrected text}


**Score: {X}/10**

**Breakdown:**
- Grammar: {Y}/10
- Vocabulary: {Z}/10
- Structure: {W}/10
- Communication: {V}/10

---

7. Optional rewrite

If score < 7, offer:

markdown

**Want to try again?** Rewriting with the corrections locks in the patterns.

Type "rewrite" to try again, or "next" to continue.

8. Session summary

markdown

## 📊 Writing Session Summary

**Text Type:** {type}
**Score:** {X}/10
**Key Takeaways:**
- {learning 1}
- {learning 2}
- {learning 3}

**Next Time:**
- Focus on: {weak pattern}
- Review: {relevant flashcards}

{target-language "well done"}! ✍️

9. Update all databases

Use the fluent-db-updater skill:

command_used: "/fluent-writing", skills_practiced: ["writing"]
skill_scores.writing: {exercises: 1, correct: 1_if_score_≥_7_else_0, time_minutes}
errors[] — one per distinct pattern found (dedupe; the script bumps frequency)
focus_next_session[] — top 2 patterns to drill

Also save the exchange as /results/fluent-writing-session-{NNN}.md with the full task, the learner's original text, the corrected version, and the error table. The fluent-session-analyzer skill depends on this format.

Examples

Show full SKILL.md (324 more words)Show less

Example 1 — formal email task (Dutch A2)

✍️ Writing Exercise

Scenario: You need to cancel a doctor's appointment you have on Thursday.

Task: Write a formal email to the doctor's office in Dutch.

Requirements:

Length: 40-60 words

Include: greeting, reason, request for new appointment, closing

Register: formal

Level: A2

Write your email below:

Learner: "Hallo, Ik schrijf je omdat ik kan niet komen op donderdag. Ik ben ziek. Kunnen we een andere dag afspreken? Bedankt, Mohammad"

Feedback

✅ What You Did Well

Clear reason for cancellation.

Correct request structure.

❌ Areas to Improve

Critical: 🔴

formal_informal: "Hallo" + "je" — formal email needs "Beste meneer/mevrouw" + "u". Mixed registers cost exam points.

grammar: "ik kan niet komen" is OK standalone, but after "omdat" Dutch word order flips: "omdat ik niet kan komen".

Moderate: 🟡

missing: no formal closing. Use "Met vriendelijke groet,".

Minor: 🟢

Capitalize "Donderdag"? Actually no — Dutch doesn't capitalize weekdays. You were right.

📝 Corrected Version
Beste meneer/mevrouw,

Ik schrijf u omdat ik niet kan komen op donderdag. Ik ben ziek.
Kunnen we een andere dag afspreken?

Met vriendelijke groet,
Mohammad
Score: 6/10

Grammar: 6/10 — omdat word order tripped you up.

Vocabulary: 8/10 — solid word choice.

Structure: 5/10 — missing proper opening + closing.

Communication: 7/10 — message was clear despite issues.

Critical Rules

One scenario per session. Don't chain multiple writing tasks — depth over breadth.
Wait for the full answer before correcting.
Severity tagging is mandatory. Fed into mistakes-db and drives spaced repetition priority.
Always save the session file in /results/ for later analysis by fluent-session-analyzer.
Never auto-invoke. This skill is gated; must fire only on explicit /fluent-writing.

Language Reference

Dutch A2 patterns

Formal emails: always "u" (not "je"); open Beste meneer/mevrouw {NAME},; closing Met vriendelijke groet, + name.

Informal emails: "je" not "u"; open Hallo {NAME},; closing Groetjes, or Tot snel,.

Common mistakes: mixing formal/informal in one text; word order in omdat clauses (verb last); time expressions (om 10:00 uur, op dinsdag).

Add similar sections for other target languages as the learner needs them.

Files

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

Open the folder on GitHubat commit 86fb80f

Compare with similar skills

Fluent Writing 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 Writing compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Fluent Writing this skillm98/fluent	421	—	~1.8k	Automated safety check: Notes	MIT	3 mo ago
MCP Server Builderanthropics/skills	180k	64 repos	~2.3k	Automated safety check: Pass	Apache-2.0	3 days ago
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official	38k	11 repos	~4.1k	Automated safety check: Notes	Apache-2.0	yesterday
Using Superpowersfarm-fe/farm	5.6k	35 repos	~1.4k	Automated safety check: Pass	MIT	16 days ago
Executing Plans Inlineobra/superpowers	296k	2 repos	~5.1k	Automated safety check: Pass	MIT	yesterday
Claude Code Agent Developmentanthropics/claude-plugins-official	38k	8 repos	~2.8k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 64 repos~2.3k tokens
Agent WorkflowsAuto-check passed
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
38k GitHub starsUsed in 11 repos~4.1k tokens
Agent WorkflowsAuto-check: notes
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
5.6k GitHub starsUsed in 35 repos~1.4k tokens
Agent WorkflowsAuto-check passed
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
296k GitHub starsUsed in 2 repos~5.1k tokens
Agent WorkflowsAuto-check passed
Claude Code Agent Development
anthropics/claude-plugins-official
Official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
38k GitHub starsUsed in 8 repos~2.8k tokens
Agent WorkflowsAuto-check passed
Skill Creator
Azure/azqr
Official
Create new skills, modify and improve existing skills, and measure skill performance.
795 GitHub starsUsed in 89 repos~8.2k tokens
Agent WorkflowsAuto-check passed

Questions about Fluent Writing

What does Fluent Writing do?

Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback. Fluent Writing is an agent skill from m98/fluent. Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback.

When should I use Fluent Writing?

Fluent Writing fits situations like: agent Workflows work in your project.

How do I install Fluent Writing in Claude Code?

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

How do I install Fluent Writing in Codex?

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

Can I use Fluent Writing 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-writing -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-writing, .gemini/skills/fluent-writing, .github/skills/fluent-writing and .opencode/skills/fluent-writing in your project.

What does Fluent Writing need to run?

Going by SKILL.md and its folder, Fluent Writing 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 Writing 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 Writing 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 Writing use?

Fluent Writing 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 Writing use?

About 1.8k tokens (SKILL.md is roughly 7k 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 Writing?

Skills that share tags, products or a category with Fluent Writing: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fluent Writing?

m98 (a GitHub user) maintains it in m98/fluent, which has 421 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.

Install Fluent Writing

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Writing Practice Session

Overview

When to Use

Instructions

1. Load context

2. Pick scenario type

3. Present the task

4. Wait for the full text

5. Systematic error analysis

6. Detailed feedback

7. Optional rewrite

8. Session summary

9. Update all databases

Examples

Example 1 — formal email task (Dutch A2)

✍️ Writing Exercise

Feedback

✅ What You Did Well

❌ Areas to Improve

📝 Corrected Version

Critical Rules

Language Reference

Dutch A2 patterns

Files

Compare with similar skills

Similar skills

More from m98/fluent

Related

Questions about Fluent Writing