Remove redundant sections for clarity and improve structure.

diff --git a/doc/index.org b/doc/index.org
index 1850c85..299aab1 100644 (file)
--- a/doc/index.org
+++ b/doc/index.org
@@ -178,7 +178,10 @@ may take minutes to hours.
 :PROPERTIES:
 :ID:       6579abb4-8386-418b-9457-cae6c3345dfb
 :END:
-- See also: [[id:1ba0c510-4c11-4f23-8746-eb9675c3e60c][Setting Up "Skills" (Your Custom Instructions)]]
+- See also:
+  - [[id:1ba0c510-4c11-4f23-8746-eb9675c3e60c][Setting Up "Skills" (Your Custom Instructions)]]
+  - [[id:47fd0e4e-f86e-4c94-9656-ed76c0f9c2c5][Skill File Format]]
+  - [[id:4fae9009-eb2e-4d3f-a43e-68ec8c43a7cd][Example Skill File]]
 
 A /skill/ is a predefined behavioral configuration for the AI,
 implemented as a YAML file in the skills directory. Each skill
@@ -742,6 +745,25 @@ understandable! Let me walk you through why each step exists and how
 it ultimately creates a powerful, private, and cost-effective AI
 assistant that works /for you/.
 
+** Requirements
+*Operating System:*
+
+Älyverkko CLI is developed and tested on Debian 13 "Bookworm". It
+should work on any modern Linux distribution with minimal adjustments
+to the installation process.
+
+*Dependencies:*
+- Java Development Kit (JDK) 17 or higher
+- Apache Maven for building the project
+
+*Hardware Requirements:*
+- Modern multi-core CPU.
+- The more RAM you have, the smarter AI model you can use. For
+  example, at least 64 GB of RAM is needed to run decent AI models
+  with sufficiently large context.
+- Sufficient disk space to store large language models and
+  input/output data.
+
 ** Your Setup Journey - What to Expect
 
 Here's what you'll be doing, explained simply with /why/ each step
@@ -825,25 +847,6 @@ provide well-reasoned responses in academic tone"
 - *Key insight*: File-based interaction isn't primitive - it's
   intentional design for batch processing.
 
-** Requirements
-*Operating System:*
-
-Älyverkko CLI is developed and tested on Debian 12 "Bookworm". It
-should work on any modern Linux distribution with minimal adjustments
-to the installation process.
-
-*Dependencies:*
-- Java Development Kit (JDK) 17 or higher
-- Apache Maven for building the project
-
-*Hardware Requirements:*
-- Modern multi-core CPU.
-- The more RAM you have, the smarter AI model you can use. For
-  example, at least 64 GB of RAM is needed to run decent AI models
-  with sufficiently large context.
-- Sufficient disk space to store large language models and
-  input/output data.
-
 ** Installation
 :PROPERTIES:
 :ID:       0b705a37-9b84-4cd5-878a-fedc9ab09b12
@@ -1002,19 +1005,6 @@ file. Below is an example of how the configuration file might look:
       context_size_tokens: 32768
 #+end_src
 
-*** Parameter Precedence Hierarchy
-
-For *temperature*, *top_p*, *top_k*, *min_p* and *repeat_penalty*
-parameters, values are determined using this priority order (highest
-to lowest):
-
-1. *Skill-specific value* (from skill's YAML file)
-2. *Model-specific value* (from model configuration)
-3. *Global default value* (from main configuration)
-
-This allows fine-grained control where more specific configurations
-override broader ones.
-
 *** Enlisting available models
 Once Älyverkko CLI is installed and properly configured, you can run
 following command at commandline to see what models are available to
@@ -1038,7 +1028,11 @@ It verifies:
 - The presence of the *llama.cpp* executable.
 
 ** Skill concept and configuration
++ See also: [[id:6579abb4-8386-418b-9457-cae6c3345dfb][Skill]] concept explanation.
 *** Skill File Format
+:PROPERTIES:
+:ID:       47fd0e4e-f86e-4c94-9656-ed76c0f9c2c5
+:END:
 
 Skills are defined in YAML files stored in the *skills_directory*.
 
@@ -1057,6 +1051,9 @@ The system prompt must contain *<TASK-FILE>* which gets replaced with
 the actual user prompt during execution.
 
 *** Example Skill File
+:PROPERTIES:
+:ID:       4fae9009-eb2e-4d3f-a43e-68ec8c43a7cd
+:END:
 : writer.yaml
 
 #+begin_src yaml
@@ -1502,10 +1499,6 @@ the top of the current buffer."
 
 * Feature ideas
 
-- Document system requirements (minimum RAM, storage, OS)
-
-- Make glossary of concepts. (Task, Task directory, Skill, Model, etc)
-
 - Recommend some concrete AI models.
 
 - In task directory ignore binary files, use joinfiles command as