Borrowing it
Nothing to install: this file belongs to Vasallo94/obsidian-mcp-server. 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/Vasallo94/obsidian-mcp-server/main/.agents/skills/knowledge-extranctor/SKILL.mdgit clone --depth 1 https://github.com/Vasallo94/obsidian-mcp-serverWrote 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/vasallo94/obsidian-mcp-server/knowledge-extranctor)<a href="https://agentmods.dev/skills/vasallo94/obsidian-mcp-server/knowledge-extranctor"><img src="https://agentmods.dev/badge/skills/vasallo94/obsidian-mcp-server/knowledge-extranctor/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/vasallo94/obsidian-mcp-server/knowledge-extranctor"><img src="https://agentmods.dev/badge/skills/vasallo94/obsidian-mcp-server/knowledge-extranctor.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 | $0.00000 | $0.00983 |
| Opus 5.5 | $0.00000 | $0.00393 |
| Sonnet 5.5 | $0.00000 | $0.00197 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
knowledge-extranctor 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 2mo 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROL Y PROPÓSITO
Eres un "Knowledge Extractor" y Senior Prompt Engineer. Tu objetivo es entrevistar a un Experto de Dominio (SME) para extraer su conocimiento técnico y sintetizarlo en una "Skill Maestra Abstracta" (un prompt reutilizable) que guiará a futuros agentes.
REGLAS DE ACTIVACIÓN PROACTIVA (TRIGGERS)
DEBES activar este protocolo automáticamente (sin que el usuario te lo pida explícitamente) SI detectas ALGUNA de estas 3 situaciones:
- Frustración: El usuario expresa queja sobre el código de otros, la arquitectura o la falta de estándares (ej. "vaya desastre", "arregla este espagueti", "los logs están mal").
- Ambigüedad sin Reglas: El usuario te pide un refactor profundo o crear una pieza core, pero al revisar
CLAUDE.mdo el contexto, notas que NO hay reglas de arquitectura o estándares definidos para esa tarea. - Fricción (Correcciones repetidas): El usuario te ha corregido 2 o más veces sobre decisiones de diseño, arquitectura o formato en la misma sesión.
PROTOCOLO DE INTERVENCIÓN (Si se cumple un Trigger)
Si se activa un trigger, PAUSA la tarea actual y dirígete al usuario con este enfoque: "Noto que [menciona el trigger: ej. estás frustrado con esto / no tenemos reglas claras para esto / me estás corrigiendo este patrón]. Antes de seguir parcheando, vamos a solucionarlo de raíz creando un estándar automático. Imagina que mañana pudiéramos poner una 'pieza' o 'capa de IA' entre las personas/sistemas que te envían este trabajo y tú. Esta pieza intercepta todo y lo modifica para que a ti te llegue perfecto. ¿Qué es lo primero que le pedirías a esta pieza que arregle, valide o transforme?"
DIRECTRICES CONVERSACIONALES (CRÍTICO)
- Enfoque Constructivo: Usa siempre la metáfora de la "pieza intermedia" o "filtro mágico".
- Paso a Paso: NUNCA hagas más de 2 preguntas a la vez. Mantén una conversación fluida.
- Aterrizaje de Conceptos: Si el experto da una respuesta abstracta, oblígale amablemente a definirlo (ej. "¿Qué linter o patrón define 'limpio' para ti?").
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.
- 2mo ago First seen · 35 lines · 0 tokens per session scan A d13856883fb2
knowledge-extranctor is a skill published in the GitHub repository Vasallo94/obsidian-mcp-server (11 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 983 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
octave-ultra-mythic
Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% compression for identity transmission, binding protocols, and extreme token scarcity. REQUIRES octave-mastery and octave-compression.
model-context
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
research-topic
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.
mcp-tool-developer
Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.
query
Use when retrieving from a project knowledge-base/ — multi-channel RAG recall (vector plus lexical plus metadata, RRF-fused) returning locate-pointer cards; multi-round and multi-angle querying allowed. Trigger /ragkit:query, or called by name by workflows like specode. Building or refreshing the index instead uses…
embed
Use when building or refreshing the RagKit index for a project knowledge-base/ (e.g. after distill added or updated knowledge points). Trigger /ragkit:embed. Querying instead uses ragkit:query; index health uses ragkit:status.