Borrowing it
Nothing to install: this file belongs to IBazylchuk/paparats-mcp. 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/IBazylchuk/paparats-mcp/main/.claude/skills/extract-terminology/SKILL.mdgit clone --depth 1 https://github.com/IBazylchuk/paparats-mcpWrote 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/ibazylchuk/paparats-mcp/extract-terminology)<a href="https://agentmods.dev/skills/ibazylchuk/paparats-mcp/extract-terminology"><img src="https://agentmods.dev/badge/skills/ibazylchuk/paparats-mcp/extract-terminology/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/ibazylchuk/paparats-mcp/extract-terminology"><img src="https://agentmods.dev/badge/skills/ibazylchuk/paparats-mcp/extract-terminology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01828 |
| Opus 5 | $0.00000 | $0.00914 |
| Sonnet 5 | $0.00000 | $0.00366 |
| Haiku 4.5 | $0.00000 | $0.00183 |
Grade A, and why
extract-terminology 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/extract-terminology — seed the company glossary from docs & code
User-invoked. $ARGUMENTS is [group] [project] — the Qdrant group and, optionally,
the project (directory basename) to scope extraction to. If project is omitted, cover
the whole group.
The glossary is a paparats knowledge layer (like arch memory) that stores domain terms — abbreviations, service names, product names, jargon — that dense embeddings retrieve poorly on their own. It's authored by the agent, not the file indexer. This skill does the bulk first pass; day-to-day work then keeps it current by recording new terms as they're encountered.
Prerequisites
- The paparats coding MCP server must be connected and expose
term_record,term_search,term_list,search_docs, andsearch_code. Ifterm_recordis missing, the terminology layer isn't configured on this server — stop and tell the user.
1. Establish what's already there
Call term_list(group, project?) and keep the returned terms in mind. Everything you
record goes through a duplicate/similar gate, but knowing the existing set avoids
wasted calls and helps you spot terms that need updating rather than adding.
2. Gather source material
Work from prose, not from code identifiers:
search_docswith broad, domain-oriented queries: "overview", "architecture", "glossary", "getting started", "concepts", "what is", the product name, each major feature area. Read the returned passages.search_codeonly to confirm or refine a term you already met in prose — e.g. to check what a service actually does before defining it. Not as a source of new terms.- Look especially at:
docs/prose, product and feature descriptions, module/service boundaries, bounded-context names, and any acronym that appears without expansion.
Do NOT mine code for terminology: config keys, feature flags, environment variables,
class and package names. search_code already finds those by name — a glossary entry
adds nothing, and every extra term costs precision (see below).
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.
- 11d ago First seen · 165 lines · 0 tokens per session scan A 172f51259931
extract-terminology is a skill published in the GitHub repository IBazylchuk/paparats-mcp (10 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,828 tokens. 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
lookup
Use when writing code that calls any AI API, giving API code samples, or answering questions about AI model names/versions/pricing. Handles ALL AI model lookups including: OpenAI (gpt-, o1-, o3-, o4-), Anthropic (claude-), Google (gemini-), Zhipu/z.ai (glm-), DeepSeek (deepseek-), Meta (llama-), Mistral (mistral-)…
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.