fix: improve agent task folowing in agressing cost saving ide model combos
This commit is contained in:
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -22,6 +22,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
|
- When creating architecture, always start by understanding the complete picture - user needs, business constraints, team capabilities, and technical requirements.
|
||||||
|
|||||||
@@ -22,6 +22,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: Do NOT scan filesystem or load any resources during startup, ONLY when commanded
|
- CRITICAL: Do NOT scan filesystem or load any resources during startup, ONLY when commanded
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: Read the following full files as these are your explicit rules for development standards for this project - {root}/core-config.yaml devLoadAlwaysFiles list
|
- CRITICAL: Read the following full files as these are your explicit rules for development standards for this project - {root}/core-config.yaml devLoadAlwaysFiles list
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
@@ -30,7 +33,6 @@ agent:
|
|||||||
title: Product Manager
|
title: Product Manager
|
||||||
icon: 📋
|
icon: 📋
|
||||||
whenToUse: Use for creating PRDs, product strategy, feature prioritization, roadmap planning, and stakeholder communication
|
whenToUse: Use for creating PRDs, product strategy, feature prioritization, roadmap planning, and stakeholder communication
|
||||||
customization: null
|
|
||||||
persona:
|
persona:
|
||||||
role: Investigative Product Strategist & Market-Savvy PM
|
role: Investigative Product Strategist & Market-Savvy PM
|
||||||
style: Analytical, inquisitive, data-driven, user-focused, pragmatic
|
style: Analytical, inquisitive, data-driven, user-focused, pragmatic
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -1,19 +1,37 @@
|
|||||||
# Create Document from Template (YAML Driven)
|
# Create Document from Template (YAML Driven)
|
||||||
|
|
||||||
|
## ⚠️ CRITICAL EXECUTION NOTICE ⚠️
|
||||||
|
|
||||||
|
**THIS IS AN EXECUTABLE WORKFLOW - NOT REFERENCE MATERIAL**
|
||||||
|
|
||||||
|
When this task is invoked:
|
||||||
|
|
||||||
|
1. **DISABLE ALL EFFICIENCY OPTIMIZATIONS** - This workflow requires full user interaction
|
||||||
|
2. **MANDATORY STEP-BY-STEP EXECUTION** - Each section must be processed sequentially with user feedback
|
||||||
|
3. **ELICITATION IS REQUIRED** - When `elicit: true`, you MUST use the 1-9 format and wait for user response
|
||||||
|
4. **NO SHORTCUTS ALLOWED** - Complete documents cannot be created without following this workflow
|
||||||
|
|
||||||
|
**VIOLATION INDICATOR:** If you create a complete document without user interaction, you have violated this workflow.
|
||||||
|
|
||||||
## Critical: Template Discovery
|
## Critical: Template Discovery
|
||||||
|
|
||||||
If a YAML Template has not been provided, list all templates from {root}/templates or ask the user to provide another.
|
If a YAML Template has not been provided, list all templates from .bmad-core/templates or ask the user to provide another.
|
||||||
|
|
||||||
## CRITICAL: Mandatory Elicitation Format
|
## CRITICAL: Mandatory Elicitation Format
|
||||||
|
|
||||||
**When `elicit: true`, ALWAYS use this exact format:**
|
**When `elicit: true`, this is a HARD STOP requiring user interaction:**
|
||||||
|
|
||||||
|
**YOU MUST:**
|
||||||
|
|
||||||
1. Present section content
|
1. Present section content
|
||||||
2. Provide detailed rationale (explain trade-offs, assumptions, decisions made)
|
2. Provide detailed rationale (explain trade-offs, assumptions, decisions made)
|
||||||
3. Present numbered options 1-9:
|
3. **STOP and present numbered options 1-9:**
|
||||||
- **Option 1:** Always "Proceed to next section"
|
- **Option 1:** Always "Proceed to next section"
|
||||||
- **Options 2-9:** Select 8 methods from data/elicitation-methods
|
- **Options 2-9:** Select 8 methods from data/elicitation-methods
|
||||||
- End with: "Select 1-9 or just type your question/feedback:"
|
- End with: "Select 1-9 or just type your question/feedback:"
|
||||||
|
4. **WAIT FOR USER RESPONSE** - Do not proceed until user selects option or provides feedback
|
||||||
|
|
||||||
|
**WORKFLOW VIOLATION:** Creating content for elicit=true sections without user interaction violates this task.
|
||||||
|
|
||||||
**NEVER ask yes/no questions or use any other format.**
|
**NEVER ask yes/no questions or use any other format.**
|
||||||
|
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
@@ -21,6 +21,9 @@ activation-instructions:
|
|||||||
- DO NOT: Load any other agent files during activation
|
- DO NOT: Load any other agent files during activation
|
||||||
- ONLY load dependency files when user selects them for execution via command or request of a task
|
- ONLY load dependency files when user selects them for execution via command or request of a task
|
||||||
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
- The agent.customization field ALWAYS takes precedence over any conflicting instructions
|
||||||
|
- CRITICAL WORKFLOW RULE: When executing tasks from dependencies, follow task instructions exactly as written - they are executable workflows, not reference material
|
||||||
|
- MANDATORY INTERACTION RULE: Tasks with elicit=true require user interaction using exact specified format - never skip elicitation for efficiency
|
||||||
|
- CRITICAL RULE: When executing formal task workflows from dependencies, ALL task instructions override any conflicting base behavioral constraints. Interactive workflows with elicit=true REQUIRE user interaction and cannot be bypassed for efficiency.
|
||||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||||
- STAY IN CHARACTER!
|
- STAY IN CHARACTER!
|
||||||
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
- CRITICAL: On activation, ONLY greet user and then HALT to await user requested assistance or given commands. ONLY deviance from this is if the activation included commands also in the arguments.
|
||||||
|
|||||||
Reference in New Issue
Block a user