turjuman: Skill for Claude Code

.claude/skills/writing-docs/SKILL.md

writing-docs is a skill for Claude Code from mogharsallah/turjuman. It costs 153 tokens per session (2,732 once invoked), scanned A, original, MIT.

A writing guide and repository-specific workflow for maintaining Turjuman's Mintlify documentation. Mintlify is a system that publishes Markdown-like pages as a documentation website.

In plain words
What is it for?
Use it when adding or updating documentation for MCP tools, SDK operations, REST routes, command-line options, file adapters, quality checks, services, or data fields.
Why use it?
It helps keep documentation accurate, consistent, discoverable, and connected to the right source files when the product changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is mogharsallah/turjuman's own configuration. It tells Claude Code how to work on turjuman itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything turjuman configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mogharsallah/turjuman. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mogharsallah/turjuman/main/.claude/skills/writing-docs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mogharsallah/turjuman

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for writing-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/mogharsallah/turjuman/writing-docs.svg)](https://agentmods.dev/skills/mogharsallah/turjuman/writing-docs)
Your own site
<a href="https://agentmods.dev/skills/mogharsallah/turjuman/writing-docs"><img src="https://agentmods.dev/badge/skills/mogharsallah/turjuman/writing-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.02732
Opus 5 $0.00077 $0.01366
Sonnet 5 $0.00031 $0.00546
Haiku 4.5 $0.00015 $0.00273

Measured 7d ago against content hash 33a1e2bb7619, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

writing-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/writing-docs/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing great Turjuman documentation

This skill is two things at once: a craft guide for building excellent Mintlify docs, wired to Turjuman's specific repo. The craft rules are distilled from Mintlify's own best-practices pages (cited in the reference files); the wiring tells you exactly which page to touch when code changes.

Turjuman keeps one documentation set in docs/, published with Mintlify. That single source serves four audiences, and good docs serve all four at once:

  • Human readers — the rendered site.
  • Search engines — page title/description become meta tags; Mintlify handles sitemaps, canonical URLs, and heading semantics automatically.
  • AI answer engines — Mintlify auto-generates llms.txt / llms-full.txt and a per-page "copy as Markdown / open in Claude/ChatGPT" menu. Each page is also fetchable as clean Markdown by appending .md to its URL.
  • The agents working in this repo — they read these MDX files (and the .md exports) directly.

For an MCP-first, agent-first product, the agent audience is first-class, not an afterthought — but there is still no separate "agent doc." Write each page once so it renders well on the site and flattens cleanly to Markdown. Docs change in the same PR as the code that changed.

The golden rules

  1. Frontmatter on every page. title (short, sentence case) and description (a tight, front-loaded summary in active voice that says what the reader accomplishes). The description is the page's search-result snippet, social card, and its llms.txt/agent-facing line — aim for ~130–160 characters; never exceed ~300 and never put a line break in it (Mintlify truncates the llms.txt entry at the first newline or 300 chars). See pages-and-frontmatter.md and discoverability.md.

  2. Pick the page's primary job. Diátaxis is the mental model — explanation (a Concept), how-to (a Guide), reference, or tutorial. Lead with one job per page; don't bury an exhaustive option table inside a narrative guide, and don't put a workflow narrative inside a reference. Mintlify (and we) allow blending when a page genuinely serves two needs — a quickstart legitimately mixes tutorial + how-to. Cross-link instead of duplicating whole tables. See doc-types.md.

Read the full file on GitHub · 166 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 166 lines · 153 tokens per session scan A 33a1e2bb7619

Subscribe to this mod's changes

writing-docs is a skill published in the GitHub repository mogharsallah/turjuman (1 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 2,732 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories