gilles/claude-code-best-practice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[weather orchestration workflow] updated

Browse Source
This commit is contained in:
Shayan Rais
2026-02-28 20:29:11 +05:00
parent 110b639b65
commit 54064d9e23
9 changed files with 33 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/agents/weather.md
+4 -4
View File
@@ -1,6 +1,6 @@
--- ---
name: weather name: weather
description: Use this agent PROACTIVELY when you need to fetch and transform weather data for Karachi, Pakistan. This agent fetches real-time temperature from wttr.in API and applies transformation rules from weather-orchestration/input.md, writing results to weather-orchestration/output.md. description: Use this agent PROACTIVELY when you need to fetch and transform weather data for Karachi, Pakistan. This agent fetches real-time temperature from wttr.in API and applies transformation rules from orchestration-workflow/input.md, writing results to orchestration-workflow/output.md.
tools: WebFetch, Read, Write tools: WebFetch, Read, Write
model: sonnet model: sonnet
color: green color: green
@@ -34,9 +34,9 @@ Follow the weather-fetcher skill instructions to:
### Step 2: Transform Temperature (weather-transformer skill) ### Step 2: Transform Temperature (weather-transformer skill)
Follow the weather-transformer skill instructions to: Follow the weather-transformer skill instructions to:
- Read transformation rules from `weather-orchestration/input.md` - Read transformation rules from `orchestration-workflow/input.md`
- Apply the transformation to the fetched temperature - Apply the transformation to the fetched temperature
- Write formatted results to `weather-orchestration/output.md` - Write formatted results to `orchestration-workflow/output.md`
## Final Report ## Final Report
@@ -46,7 +46,7 @@ After completing all steps, provide a summary:
- Transformation rule applied - Transformation rule applied
- Final transformed result - Final transformed result
- Comparison with previous reading (if available in memory) - Comparison with previous reading (if available in memory)
- Confirmation that output was written to `weather-orchestration/output.md` - Confirmation that output was written to `orchestration-workflow/output.md`
## Critical Requirements ## Critical Requirements
.claude/commands/weather-orchestrator.md
+3 -3
View File
@@ -21,7 +21,7 @@ Use the Task tool to invoke the weather agent.
Use the Task tool to invoke the weather agent: Use the Task tool to invoke the weather agent:
- subagent_type: weather - subagent_type: weather
- description: Fetch and transform Karachi weather - description: Fetch and transform Karachi weather
- prompt: Fetch the current temperature for Karachi, Pakistan in [unit requested by user]. Then apply the transformation rules from weather-orchestration/input.md and write the results to weather-orchestration/output.md. The agent has preloaded skills (weather-fetcher and weather-transformer) that provide the detailed instructions. - prompt: Fetch the current temperature for Karachi, Pakistan in [unit requested by user]. Then apply the transformation rules from orchestration-workflow/input.md and write the results to orchestration-workflow/output.md. The agent has preloaded skills (weather-fetcher and weather-transformer) that provide the detailed instructions.
- model: haiku - model: haiku
Wait for the agent to complete its workflow. Wait for the agent to complete its workflow.
@@ -37,5 +37,5 @@ Wait for the agent to complete its workflow.
Provide a clear summary to the user showing: Provide a clear summary to the user showing:
- Temperature unit requested - Temperature unit requested
- Original temperature fetched - Original temperature fetched
- Transformation rule applied (from weather-orchestration/input.md) - Transformation rule applied (from orchestration-workflow/input.md)
- Final transformed result (written to weather-orchestration/output.md) - Final transformed result (written to orchestration-workflow/output.md)
.claude/skills/weather-transformer/SKILL.md
+7 -7
View File
@@ -1,6 +1,6 @@
--- ---
name: weather-transformer name: weather-transformer
description: Instructions for applying mathematical transformations to temperature data based on rules in weather-orchestration/input.md description: Instructions for applying mathematical transformations to temperature data based on rules in orchestration-workflow/input.md
--- ---
# Weather Transformer Skill # Weather Transformer Skill
@@ -13,13 +13,13 @@ Apply mathematical transformations to a temperature value and write results to o
## Instructions ## Instructions
1. **Read Transformation Rules**: Use the Read tool to read `weather-orchestration/input.md` which contains the transformation instructions. 1. **Read Transformation Rules**: Use the Read tool to read `orchestration-workflow/input.md` which contains the transformation instructions.
2. **Apply Transformation**: Apply the transformation rule to the temperature value. 2. **Apply Transformation**: Apply the transformation rule to the temperature value.
- Example: If instruction says "add +10", add 10 to the temperature - Example: If instruction says "add +10", add 10 to the temperature
- Example: If instruction says "multiply by 2", multiply temperature by 2 - Example: If instruction says "multiply by 2", multiply temperature by 2
3. **Write Output**: Use the Write tool to save the transformed result to `weather-orchestration/output.md` with proper formatting. 3. **Write Output**: Use the Write tool to save the transformed result to `orchestration-workflow/output.md` with proper formatting.
## Expected Input ## Expected Input
@@ -30,7 +30,7 @@ Temperature: [X]°C
## Expected Output ## Expected Output
Write to `weather-orchestration/output.md` with format: Write to `orchestration-workflow/output.md` with format:
```markdown ```markdown
# Weather Transformation Result # Weather Transformation Result
@@ -38,7 +38,7 @@ Write to `weather-orchestration/output.md` with format:
[X]°C [X]°C
## Transformation Applied ## Transformation Applied
[description from weather-orchestration/input.md] [description from orchestration-workflow/input.md]
## Final Result ## Final Result
[Y]°C [Y]°C
@@ -49,6 +49,6 @@ Write to `weather-orchestration/output.md` with format:
## Notes ## Notes
- Read the exact transformation from weather-orchestration/input.md - don't assume - Read the exact transformation from orchestration-workflow/input.md - don't assume
- Show your work: include original value, transformation, and result - Show your work: include original value, transformation, and result
- Ensure weather-orchestration/output.md is properly formatted and readable - Ensure orchestration-workflow/output.md is properly formatted and readable
CLAUDE.md
+3 -3
View File
@@ -13,9 +13,9 @@ A demonstration of the **Command → Agent → Skills** architecture pattern:
- `/weather-orchestrator` command (`.claude/commands/weather-orchestrator.md`): Entry point that invokes the weather agent - `/weather-orchestrator` command (`.claude/commands/weather-orchestrator.md`): Entry point that invokes the weather agent
- `weather` agent (`.claude/agents/weather.md`): Executes workflow using preloaded skills - `weather` agent (`.claude/agents/weather.md`): Executes workflow using preloaded skills
- `weather-fetcher` skill (`.claude/skills/weather-fetcher/SKILL.md`): Instructions for fetching temperature from wttr.in API - `weather-fetcher` skill (`.claude/skills/weather-fetcher/SKILL.md`): Instructions for fetching temperature from wttr.in API
- `weather-transformer` skill (`.claude/skills/weather-transformer/SKILL.md`): Instructions for applying transformation rules from `weather-orchestration/input.md`, writes results to `weather-orchestration/output.md` - `weather-transformer` skill (`.claude/skills/weather-transformer/SKILL.md`): Instructions for applying transformation rules from `orchestration-workflow/input.md`, writes results to `orchestration-workflow/output.md`
The agent has skills preloaded via the `skills` field, providing domain knowledge for sequential execution. See `weather-orchestration/weather-orchestration-architecture.md` for the complete flow diagram. The agent has skills preloaded via the `skills` field, providing domain knowledge for sequential execution. See `orchestration-workflow/orchestration-workflow.md` for the complete flow diagram.
### Skill Definition Structure ### Skill Definition Structure
Skills in `.claude/skills/<name>/SKILL.md` use YAML frontmatter: Skills in `.claude/skills/<name>/SKILL.md` use YAML frontmatter:
@@ -106,7 +106,7 @@ From experience with this repository:
## Documentation ## Documentation
- `docs/AGENTS.md`: Subagent orchestration troubleshooting - `docs/AGENTS.md`: Subagent orchestration troubleshooting
- `weather-orchestration/weather-orchestration-architecture.md`: Weather system flow diagram - `orchestration-workflow/orchestration-workflow.md`: Weather system flow diagram
- `docs/COMPARISION.md`: Commands vs Agents vs Skills invocation patterns - `docs/COMPARISION.md`: Commands vs Agents vs Skills invocation patterns
## Reports ## Reports
README.md
+2 -2
View File
@@ -5,7 +5,7 @@ practice makes claude perfect
![Best Practice](!/tags/best-practice.svg) *Click on this badge to show the latest best practice*<br> ![Best Practice](!/tags/best-practice.svg) *Click on this badge to show the latest best practice*<br>
![Implemented](!/tags/implemented.svg) *Click on this badge to show implementation in this repo*<br> ![Implemented](!/tags/implemented.svg) *Click on this badge to show implementation in this repo*<br>
[![Orchestration Workflow](!/tags/orchestration-workflow.svg)](https://github.com/shanraisshan/claude-code-best-practice#orchestration-workflow) *Click on this badge to see the Command → Agent → Skills orchestration workflow* ![Orchestration Workflow](!/tags/orchestration-workflow.svg) *Click on this badge to see the Command → Agent → Skills orchestration workflow*
<p align="center"> <p align="center">
<img src="!/claude-jumping.svg" alt="Claude Code mascot jumping" width="120" height="100"> <img src="!/claude-jumping.svg" alt="Claude Code mascot jumping" width="120" height="100">
@@ -130,7 +130,7 @@ Multi-step workflows using the **Command → Agent → Skills** architecture pat
**Why it works:** Progressive disclosure • Single execution context • Clean separation • Reusability **Why it works:** Progressive disclosure • Single execution context • Clean separation • Reusability
See [weather-orchestration-architecture](weather-orchestration/weather-orchestration-architecture.md) for implementation details. See [orchestration-workflow](orchestration-workflow/orchestration-workflow.md) for implementation details.
## AI TERMS ## AI TERMS
implementation/claude-subagents-implementation.md
+2 -2
View File
@@ -27,8 +27,8 @@ name: weather
description: Use this agent PROACTIVELY when you need to fetch and transform description: Use this agent PROACTIVELY when you need to fetch and transform
weather data for Karachi, Pakistan. This agent fetches real-time temperature weather data for Karachi, Pakistan. This agent fetches real-time temperature
from wttr.in API and applies transformation rules from from wttr.in API and applies transformation rules from
weather-orchestration/input.md, writing results to orchestration-workflow/input.md, writing results to
weather-orchestration/output.md. orchestration-workflow/output.md.
tools: WebFetch, Read, Write tools: WebFetch, Read, Write
model: sonnet model: sonnet
color: green color: green
weather-orchestration/input.md → orchestration-workflow/input.md
View File
weather-orchestration/weather-orchestration-architecture.md → orchestration-workflow/orchestration-workflow.md
+12 -12
View File
@@ -1,6 +1,6 @@
# Weather Karachi System Flow # Orchestration Workflow
This document describes the complete flow of the weather data fetching and transformation system. This document describes the **Command → Agent → Skills** orchestration workflow, demonstrated through a weather data fetching and transformation system.
<table width="100%"> <table width="100%">
<tr> <tr>
@@ -53,7 +53,7 @@ The weather system demonstrates the **Command → Agent → Skills** architectur
│ │ │ │
▼ ▼ ▼ ▼
┌─────────────────────────┐ ┌─────────────────────────┐ ┌─────────────────────────┐ ┌─────────────────────────┐
│ wttr.in API │ │ weather-orchestration/ │ │ wttr.in API │ │ orchestration-workflow/ │
│ Fetch Temperature │ │ Read Transform Rules │ │ Fetch Temperature │ │ Read Transform Rules │
│ for Karachi │ └─────────────────────────┘ │ for Karachi │ └─────────────────────────┘
└─────────────────────────┘ │ └─────────────────────────┘ │
@@ -65,7 +65,7 @@ The weather system demonstrates the **Command → Agent → Skills** architectur
│ │
▼ ▼
┌─────────────────────────┐ ┌─────────────────────────┐
│ weather-orchestration/output.md │ │ orchestration-workflow/output.md │
│ Write Results │ │ Write Results │
└─────────────────────────┘ └─────────────────────────┘
│ │
@@ -109,17 +109,17 @@ The agent has skills preloaded into its context at startup. It follows the instr
#### `weather-transformer` (Skill) #### `weather-transformer` (Skill)
- **Location**: `.claude/skills/weather-transformer/SKILL.md` - **Location**: `.claude/skills/weather-transformer/SKILL.md`
- **Purpose**: Instructions for applying mathematical transformations - **Purpose**: Instructions for applying mathematical transformations
- **Input Source**: `weather-orchestration/input.md` (transformation rules) - **Input Source**: `orchestration-workflow/input.md` (transformation rules)
- **Output Destination**: `weather-orchestration/output.md` (formatted results) - **Output Destination**: `orchestration-workflow/output.md` (formatted results)
### 4. Data Files ### 4. Data Files
#### `weather-orchestration/input.md` #### `orchestration-workflow/input.md`
- **Purpose**: Stores transformation rules - **Purpose**: Stores transformation rules
- **Format**: Natural language instructions (e.g., "add +10 in the result") - **Format**: Natural language instructions (e.g., "add +10 in the result")
- **Access**: Read by weather agent following weather-transformer skill - **Access**: Read by weather agent following weather-transformer skill
#### `weather-orchestration/output.md` #### `orchestration-workflow/output.md`
- **Purpose**: Stores formatted transformation results - **Purpose**: Stores formatted transformation results
- **Format**: Structured markdown with sections: - **Format**: Structured markdown with sections:
- Original Temperature - Original Temperature
@@ -135,9 +135,9 @@ The agent has skills preloaded into its context at startup. It follows the instr
4. **Skill Execution** (within agent context): 4. **Skill Execution** (within agent context):
- **Step 1**: Agent follows `weather-fetcher` skill instructions to fetch temperature from wttr.in - **Step 1**: Agent follows `weather-fetcher` skill instructions to fetch temperature from wttr.in
- **Step 2**: Agent follows `weather-transformer` skill instructions to: - **Step 2**: Agent follows `weather-transformer` skill instructions to:
- Read transformation rules from `weather-orchestration/input.md` - Read transformation rules from `orchestration-workflow/input.md`
- Apply rules to the fetched temperature - Apply rules to the fetched temperature
- Write formatted results to `weather-orchestration/output.md` - Write formatted results to `orchestration-workflow/output.md`
5. **Result Display**: Summary shown to user with: 5. **Result Display**: Summary shown to user with:
- Temperature unit requested - Temperature unit requested
- Original temperature - Original temperature
@@ -157,9 +157,9 @@ Input: /weather-orchestrator
│ ├─ Step 1 (weather-fetcher skill): │ ├─ Step 1 (weather-fetcher skill):
│ │ └─ Fetches from wttr.in → 26°C │ │ └─ Fetches from wttr.in → 26°C
│ ├─ Step 2 (weather-transformer skill): │ ├─ Step 2 (weather-transformer skill):
│ │ ├─ Reads: weather-orchestration/input.md ("add +10") │ │ ├─ Reads: orchestration-workflow/input.md ("add +10")
│ │ ├─ Calculates: 26 + 10 = 36°C │ │ ├─ Calculates: 26 + 10 = 36°C
│ │ └─ Writes: weather-orchestration/output.md │ │ └─ Writes: orchestration-workflow/output.md
│ └─ Returns: Complete report │ └─ Returns: Complete report
└─ Output: └─ Output:
├─ Unit: Celsius ├─ Unit: Celsius
weather-orchestration/output.md → orchestration-workflow/output.md
View File