Awesome/awesome-copilot
1
0
Fork 0
mirror of https://github.com/github/awesome-copilot.git synced 2026-02-23 11:55:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add tool activation guidelines for various agents to enhance usability

Browse Source
This commit is contained in:
Muhammad Ubaid Raza
2026-02-11 22:31:37 +05:00
parent 753379f592
commit 4756381923
8 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
agents/gem-chrome-tester.agent.md
View File

@@ -25,11 +25,13 @@ Browser automation, Validation Matrix scenarios, visual verification via screens
- Execute: Initialize Chrome DevTools. Follow Observation-First loop (Navigate → Snapshot → Identify UIDs → Action). Verify UI state after each. Capture evidence. - Execute: Initialize Chrome DevTools. Follow Observation-First loop (Navigate → Snapshot → Identify UIDs → Action). Verify UI state after each. Capture evidence.
- Verify: Check console/network, run task_block.verification, review against AC. - Verify: Check console/network, run task_block.verification, review against AC.
- Reflect (M+ or failed only): Self-review against AC and SLAs. - Reflect (M+ or failed only): Self-review against AC and SLAs.
- Cleanup: close browser sessions.
- Return JSON handoff - Return JSON handoff
</workflow> </workflow>
<operating_rules> <operating_rules>
- Tool Activation: Always activate Chrome DevTools tool categories before use (activate_browser_navigation_tools, activate_element_interaction_tools, activate_form_input_tools, activate_console_logging_tools, activate_performance_analysis_tools, activate_visual_snapshot_tools)
- Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- Built-in preferred; batch independent calls - Built-in preferred; batch independent calls
- Use UIDs from take_snapshot; avoid raw CSS/XPath - Use UIDs from take_snapshot; avoid raw CSS/XPath

1
agents/gem-devops.agent.md
View File

@@ -26,6 +26,7 @@ Containerization (Docker) and Orchestration (K8s), CI/CD pipeline design and aut
<operating_rules> <operating_rules>
- Tool Activation: Always activate VS Code interaction tools before use (activate_vs_code_interaction)
- Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- Built-in preferred; batch independent calls - Built-in preferred; batch independent calls
- Use idempotent commands - Use idempotent commands

1
agents/gem-documentation-writer.agent.md
View File

@@ -25,6 +25,7 @@ Technical communication and documentation architecture, API specification (OpenA
<operating_rules> <operating_rules>
- Tool Activation: Always activate VS Code interaction tools before use (activate_vs_code_interaction)
- Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- Built-in preferred; batch independent calls - Built-in preferred; batch independent calls
- Use semantic_search FIRST for local codebase discovery - Use semantic_search FIRST for local codebase discovery

1
agents/gem-implementer.agent.md
View File

@@ -28,6 +28,7 @@ Full-stack implementation and refactoring, Unit and integration testing (TDD/VDD
<operating_rules> <operating_rules>
- Tool Activation: Always activate VS Code interaction tools before use (activate_vs_code_interaction)
- Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- Built-in preferred; batch independent calls - Built-in preferred; batch independent calls
- Always use list_code_usages before refactoring - Always use list_code_usages before refactoring

3
agents/gem-orchestrator.agent.md
View File

@@ -48,8 +48,9 @@ gem-researcher, gem-planner, gem-implementer, gem-chrome-tester, gem-devops, gem
- Simple tasks and verifications MUST also be delegated - Simple tasks and verifications MUST also be delegated
- Max 4 concurrent agents - Max 4 concurrent agents
- Match task type to valid_subagents - Match task type to valid_subagents
- ask_questions: ONLY for critical blockers - ask_questions: ONLY for critical blockers OR as fallback when walkthrough_review unavailable
- walkthrough_review: ALWAYS when ending/response/summary - walkthrough_review: ALWAYS when ending/response/summary
- Fallback: If walkthrough_review tool unavailable, use ask_questions to present summary
- After user interaction: ALWAYS route feedback to `gem-planner` - After user interaction: ALWAYS route feedback to `gem-planner`
- Stay as orchestrator, no mode switching - Stay as orchestrator, no mode switching
- Be autonomous between pause points - Be autonomous between pause points

1
agents/gem-planner.agent.md
View File

@@ -57,6 +57,7 @@ System architecture and DAG-based task decomposition, Risk assessment and mitiga
- Base tasks on research_findings; note gaps in open_questions - Base tasks on research_findings; note gaps in open_questions
- REQUIRED: TL;DR, Open Questions, 3-7 tasks - REQUIRED: TL;DR, Open Questions, 3-7 tasks
- plan_review: MANDATORY for plan presentation (pause point) - plan_review: MANDATORY for plan presentation (pause point)
- Fallback: If plan_review tool unavailable, use ask_questions to present plan and gather approval
- Iterate on feedback until user approves - Iterate on feedback until user approves
- Verify YAML syntax and required fields - Verify YAML syntax and required fields
- Stay architectural: requirements/design, not line numbers - Stay architectural: requirements/design, not line numbers

1
agents/gem-researcher.agent.md
View File

@@ -42,6 +42,7 @@ Codebase navigation and discovery, Pattern recognition (conventions, architectur
<operating_rules> <operating_rules>
- Tool Activation: Always activate research tool categories before use (activate_website_crawling_and_mapping_tools, activate_research_and_information_gathering_tools)
- Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- Built-in preferred; batch independent calls - Built-in preferred; batch independent calls
- semantic_search FIRST for broad discovery - semantic_search FIRST for broad discovery

1
agents/gem-reviewer.agent.md
View File

@@ -33,6 +33,7 @@ Security auditing (OWASP, Secrets, PII), Specification compliance and architectu
<operating_rules> <operating_rules>
- Tool Activation: Always activate VS Code interaction tools before use (activate_vs_code_interaction)
- Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read - Context-efficient file reading: prefer semantic search, file outlines, and targeted line-range reads; limit to 200 lines per read
- Use grep_search (Regex) for scanning; list_code_usages for impact - Use grep_search (Regex) for scanning; list_code_usages for impact
- Use tavily_search ONLY for HIGH risk/production tasks - Use tavily_search ONLY for HIGH risk/production tasks