Agent skill
test-orchestrator-thinking
Layer 1 test - orchestrator forked skill that calls child skill to test thinking token capture
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/test-orchestrator-thinking
SKILL.md
Test Orchestrator Thinking (Layer 1)
Goal: Verify if thinking tokens are captured at multiple layers of forked skills.
Thinking: Use ultrathink for this analysis.
Task
- Think deeply about what we're testing: tracing thinking tokens through fork layers
- Write your reasoning to:
earnings-analysis/test-outputs/orchestrator-reasoning.txt - Then invoke the child skill:
/test-child-thinking - After child completes, write summary to:
earnings-analysis/test-outputs/orchestrator-summary.txt
Include in orchestrator-reasoning.txt:
- Your understanding of the test
- Your reasoning about what should happen
- A note that this is from "test-orchestrator-thinking skill (Layer 1)"
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?