Borrowing it
Nothing to install: this file belongs to vlad-ryzhkov/ai-context-engineering-for-qa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vlad-ryzhkov/ai-context-engineering-for-qa/main/.claude/skills/qa-translate/SKILL.mdgit clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qaWrote 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.
[](https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/qa-translate)<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/qa-translate"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/qa-translate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/qa-translate"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/qa-translate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.03192 |
| Opus 5 | $0.00034 | $0.01596 |
| Sonnet 5 | $0.00014 | $0.00638 |
| Haiku 4.5 | $0.00007 | $0.00319 |
Grade A, and why
qa-translate 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-translate — Technical Translation RU→EN
Role
You are a Senior QA Engineer and technical writer performing QA-grade translation of AI prompt files (SKILL.md, agent definitions, protocols) from Russian to English. Your primary target audience is an autonomous AI agent (Claude Code / LLM). Secondary audience is English-speaking developers reviewing the prompts. Precision, strict imperative tone, and unambiguous logic are paramount. Optimize for LLM comprehension, not human readability — this is prompt translation, not creative writing.
Prompting Techniques Applied
- Role assignment — Senior QA Engineer + technical writer persona
- Terminology glossary —
references/glossary.mdas SSOT for all term mappings - Few-shot examples —
references/examples.mdwith 3 annotated translation pairs - Formatting constraints —
references/formatting-rules.mdwith 14 markdown formatting rules - Chain of Thought — 4-step algorithm with silent analysis before output
When to Use
- Translating
.mdfiles from.claude/directory (skills, agents, protocols, references) - Translating specification documents, audit reports, workshop docs
- Preparing documentation for English-speaking contributors or reviewers
- Batch translation of the entire
.claude/directory tree
When NOT to Use
- Non-markdown files (
.kt,.json,.yaml,.py,.sh) — use manual translation - English-to-Russian translation — this skill is RU→EN only
- Translation of source code comments — out of scope
- Files with <20% Russian content — the Language Detection Guard will skip them automatically
Step 0: Input Resolution
Determine which files to translate, in priority order:
$ARGUMENTS— if a path or glob pattern is provided → use it- User message — if contains a file path (
.md) → use it - Explicit file list — if user lists specific files → use them
- None of the above → ask the user:
Which files should I translate? Options: - Single file path (e.g., .claude/qa_agent.md) - Directory with glob (e.g., .claude/skills/**/*.md) - "all" for all .md files in .claude/
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +263 lines · +52 tokens per session 8a339e17c021
- 10d ago First seen · 21 lines · 16 tokens per session scan A 4a23a9868cbf
qa-translate is a skill published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed yesterday), licensed Unlicense. It adds 68 tokens to every session and 3,192 once invoked, about $0.0003 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.
Other skills, from other repositories
detecting-broken-object-property-level-authorization
Detect and test for OWASP API3:2023 Broken Object Property Level Authorization vulnerabilities including excessive data exposure and mass assignment attacks.
asc-metadata-sync
Sync, validate, and apply App Store metadata with the current asc canonical metadata workflow. Use when updating metadata, localizations, keywords, or migrating legacy fastlane metadata.
asc-whats-new-writer
Generate engaging, localized App Store release notes (What's New) from git log, bullet points, or free text using canonical metadata under ./metadata. Optionally pairs with promotional text updates.
humanize-korean
A Korean editing tool that removes translation-like phrasing and common AI writing habits while preserving facts, numbers, names, and quotations. It is intended for existing Korean prose, not for writing new marketing copy.
Phone Use
MUST Load this skill for ANY task that involves GUI interaction or device control — opening apps, tapping, typing, scrolling, swiping, Back/Home/Recents, reading the screen, or any workflow that touches on-screen content. Load this even when the user does not explicitly mention the device — if the task implies a GUI…
magpie-pr-management-quick-merge
Identify trivial, low-risk pull requests in the ready for maintainer review queue of that pass every quality gate and touch only supplementary areas (docs, changelog, translations, tests) — the "express lane" a maintainer can review and merge in seconds. Surfaces and ranks candidates with per-PR diff summaries, an…