Translate English tech docs to compressed Ukrainian. Use when user asks to translate docs, README, or technical text, or calls /cavemenko-translate.
Scanned 5/28/2026
Install via CLI
openskills install ruslanlap/cavemenko---
name: cavemenko-translate
description: >
Translate English tech docs to compressed Ukrainian.
Use when user asks to translate docs, README, or technical text,
or calls /cavemenko-translate.
---
Translate English tech text → compressed Ukrainian. Don't translate then compress — do both at once.
## Rules
1. Translate meaning, not words
2. Keep English terms where shorter: auth, deploy, config, cache, middleware, callback, handler, endpoint, payload, runtime
3. Use all cavemenko compression techniques during translation
4. Result should be SHORTER than original English
5. Don't translate code, CLI commands, file paths, URLs
6. Don't translate well-known abbreviations: API, UI, UX, CI/CD, JWT, ORM, SDK, CLI
## Keep in English
- Tech terms shorter in English (see abbreviation table in main SKILL.md)
- Brand names: React, Docker, Kubernetes, PostgreSQL
- Code identifiers: function names, variable names, class names
- CLI commands and flags
- File extensions and paths
## Translate to Ukrainian
- Explanatory text
- Instructions (use imperative: "зроби", "додай", "запусти")
- Descriptions of behavior
- Error explanations
## Example
Input:
```
## Authentication
The application uses JWT-based authentication. When a user logs in,
the server generates a token that includes the user's ID and role.
This token must be included in the Authorization header of all
subsequent API requests.
To configure authentication, set the following environment variables:
- `AUTH_SECRET` — the secret key used to sign tokens
- `AUTH_EXPIRY` — token expiration time in seconds (default: 3600)
```
Output:
```
## Auth
JWT-based auth. При login server генерує token з user ID + role.
Token додавати в `Authorization` header всіх API requests.
Config env vars:
- `AUTH_SECRET` — secret key для signing tokens
- `AUTH_EXPIRY` — token expiry в seconds (default: 3600)
```
## Process
1. Read full English text
2. Identify terms to keep in English
3. Translate + compress simultaneously
4. Verify result is shorter than original
5. Output translated text
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...