update skills docs (#31)

* update skills docs

* chore: vbump to align with vibe-llama-core

---------

Co-authored-by: Clelia (Astra) Bertelli <clelia@runllama.ai>

documentation/skills/pdf-processing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: PDF Processing
-description: Extract text from PDFs in order to read and understand their content. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
+description: Invoke this skill BEFORE implementing any text extraction/parsing logic to learn how to use LlamaParse to process any document accurately. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
 ---
 
 # PDF Processing

documentation/skills/structured-data-extraction/REFERENCE.md

@@ -32,7 +32,6 @@ extract_config = ExtractConfig(
     extraction_target=ExtractTarget.PER_DOC,  # PER_DOC, PER_PAGE
     system_prompt="<Insert relevant context for extraction>",  # set system prompt - can leave blank
     # Advanced options
-    chunk_mode=ChunkMode.PAGE,  # PAGE, SECTION
     high_resolution_mode=True,  # Enable for better OCR
     nvalidate_cache=False,  # Set to True to bypass cache
     # Extensions
@@ -43,7 +42,7 @@ extract_config = ExtractConfig(
 
 # Extract data directly from document - no agent needed!
 result = extractor.extract(Resume, config, "resume.pdf")
-print(result.data)
+print(Resume.model_validate(result.data))
 ```
 
 ### Supported File Types
@@ -207,7 +206,7 @@ be sufficient for a wide variety of use-cases.
 Configure how extraction is performed using `ExtractConfig`. The schema is the most important part, but several configuration options can significantly impact the extraction process.
 
 ```python
-from llama_cloud import ExtractConfig, ExtractMode, ChunkMode, ExtractTarget
+from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget
 
 # Basic configuration
 config = ExtractConfig(
@@ -220,7 +219,6 @@ config = ExtractConfig(
 # Advanced configuration
 advanced_config = ExtractConfig(
     extraction_mode=ExtractMode.MULTIMODAL,
-    chunk_mode=ChunkMode.PAGE,  # PAGE, SECTION
     high_resolution_mode=True,  # Better OCR accuracy
     invalidate_cache=False,  # Bypass cached results
     cite_sources=True,  # Enable source citations
@@ -247,7 +245,6 @@ advanced_config = ExtractConfig(
 
 - `system_prompt`: Additional system-level instructions
 - `page_range`: Specific pages to extract (e.g., "1,3,5-7,9")
-- `chunk_mode`: Document splitting strategy (`PAGE` or `SECTION`)
 - `high_resolution_mode`: Better OCR for small text (slower processing)
 
 **Extensions** (return additional metadata):
@@ -290,7 +287,7 @@ agent = extractor.create_agent(
 
 # Use the agent
 result = agent.extract("resume.pdf")
-print(result.data)
+print(Resume.model_validate(result.data))
 ```
 
 ### Agent Batch Processing

documentation/skills/structured-data-extraction/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: Extract structured data from unstructured files (PDF, PPTX, DOCX...)
-description: Extract structured data from PDFs and other unstructured file types in order to get the most relevant information from them. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
+description: Invoke this skill BEFORE implementing any structured data extraction from documents to learn the correct llama_cloud_services API usage. Required reading before writing extraction code. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
 ---
 
 # Structured Data Extraction
@@ -19,6 +19,8 @@ class Resume(BaseModel):
     skills: list[str] = Field(description="Technical skills and technologies")
 ```
 
+**NOTE:** Use basic types when possible. Avoid nested dictionaries. Lists are ok.
+
 - Create a LlamaExtract instance:
 
 ```python
@@ -28,6 +30,8 @@ from llama_cloud_services import LlamaExtract
 extractor = LlamaExtract(
     show_progress=True,
     check_interval=5,
+    # Optional API key, else reads from env
+    # api_key=os.environ.get("LLAMA_CLOUD_API_KEY"),
 )
 ```
 
@@ -43,7 +47,6 @@ extract_config = ExtractConfig(
     extraction_target=ExtractTarget.PER_DOC,  # PER_DOC, PER_PAGE
     system_prompt="<Insert relevant context for extraction>",  # set system prompt - can leave blank
     # Advanced options
-    chunk_mode=ChunkMode.PAGE,  # PAGE, SECTION
     high_resolution_mode=True,  # Enable for better OCR
     nvalidate_cache=False,  # Set to True to bypass cache
     # Extensions
@@ -57,7 +60,9 @@ extract_config = ExtractConfig(
 
 ```python
 result = extractor.extract(Resume, config, "resume.pdf")
-print(result.data)
+
+# result.data has our model as a python dict
+print(Resume.model_validate(result.data))
 ```
 
 For more detailed code implementations, see [REFERENCE.md](REFERENCE.md).

documentation/skills/text-classification/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: Classify files according to specific rules
-description: Perfom classification of files (based on their content) into pre-defined categories (e.g. 'invoice', 'resume', 'email'). Requires the llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
+description: Invoke this skill BEFORE implementing any text/document classification task to learn the correct llama_cloud_services API usage. Required reading before writing classification code." Requires the llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.
 ---
 
 # Texts and Files Classification
@@ -35,6 +35,7 @@ rules = [
 from llama_cloud_services.beta.classifier.client import ClassifyClient
 
 # Initialize client
+# Note: the beta client differs in usage slightly compared to other clients in llama-cloud-services
 classifier = ClassifyClient.from_api_key(api_key)
 
 # Classify a PDF directly (parsing happens implicitly)

pyproject.toml

@@ -13,12 +13,12 @@ dev = [
 
 [project]
 name = "vibe-llama"
-version = "0.4.7"
+version = "0.4.7.post1"
 description = "vibe-llama is a set of tools that are designed to help developers build working and reliable applications with LlamaIndex, LlamaCloud Services and llama-index-workflows."
 readme = "README.md"
 requires-python = ">=3.10"
 dependencies = [
-  "vibe-llama-core>=0.1.0",
+  "vibe-llama-core>=0.1.1.post1",
   "bm25s>=0.2.13",
   "fastmcp>=2.11.3",
   "llama-cloud-services>=0.6.62",