experiment-protocol
Design and run controlled experiments using the experiment-registry MCP server — domain-agnostic, pluggable, mechanically enforced. Use when you need evidence that a change actually improves behaviour.
evidence-first-debugging
Use when debugging software, investigating incidents, diagnosing flaky tests, or analyzing performance regressions — enforces structured observation recording with evidence IDs, causality validation, and verification gates to prevent correlation-causation pollution. Use when an agent might otherwise summarize or speculate instead of reporting observed evidence.
ralph-guide
Guidance for customizing Ralph workflows, formulas, learning capture, and troubleshooting. Use for questions about Ralph loop, formulas, harvesting learnings, or running multiple Ralphs.
how-to-delegate
Scientific delegation framework for orchestrators — provide observations and success criteria while preserving agent autonomy. Use when assigning work to sub-agents, before invoking the Agent tool, or when preparing delegation prompts for specialist agents.
triaging-mutants
Use when mutation testing reveals survived mutants — guides deep analysis of whether each mutant signals a missing test, a design improvement opportunity, or an equivalent mutation
mdr-745-specialist
EU MDR 2017/745 regulation specialist and consultant for medical device requirement management. Provides comprehensive MDR compliance expertise, gap analysis, technical documentation guidance, clinical evidence requirements, and post-market surveillance implementation. Use for MDR compliance assessment, classification decisions, technical file preparation, and regulatory requirement interpretation.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
supabase-evidence
Initialize and manage the evidence collection directory for professional security audits with documented proof of findings.
xr-lab-assistant
Building or modifying IOS-XR/XRd labs or network topologies, creating router configurations, starting or stopping testbeds, running show commands, exploring protocol behavior, or troubleshooting boot and config issues.
asciinema-recorder
Record Claude Code sessions with asciinema. TRIGGERS - record session, asciinema record, capture terminal, demo recording.
gplay-testers-orchestration
Beta testing groups and tester management for Google Play closed testing tracks. Use when managing testers and beta groups.
style-forensics
Forensic style analysis of a writing sample. Measures sentence length, rhythm, punctuation DNA, vocabulary, tone, rhetorical devices, and verbal tics. Outputs a Style DNA report. Use when asked to analyze writing style, extract voice metrics, or create a style fingerprint. Not for writing in a voice (use style-writer). Not for codifying brand guidelines (use brand-voice).
telemetry-sanitized-skill-invocation
Record SkillTool usage with sanitized telemetry fields so built-in, bundled, and custom skills are distinguished while avoiding PII leakage.
e2e-test
Run end-to-end tests for easy-db-lab. Automatically detects what to test based on code changes in the current branch, or allows manual specification of test scope. Use when validating changes, running CI tests, or verifying full system functionality. Runs in background, reports results, and automatically debugs failures.
agent-test
Dynamic end-to-end test runner for easy-db-lab that calls easy-db-lab commands directly. Analyzes branch changes, proposes a test plan, executes commands step-by-step, and investigates failures inline. Use instead of bin/end-to-end-test when you want intelligent, adaptive testing with real-time debugging.
telemetry-sanitized-skill-invocation
Record SkillTool usage with sanitized telemetry fields so built-in, bundled, and custom skills are distinguished while avoiding PII leakage.
time-based-microcompact-trigger
Fall back to time-based microcompaction when the idle gap exceeds the configured threshold and directly clear the oldest compactable tool results.
time-based-microcompact-trigger
Fall back to time-based microcompaction when the idle gap exceeds the configured threshold and directly clear the oldest compactable tool results.
telemetry-terminology-similarity
Score telemetry field name similarity across syntactic, taxonomic, and semantic layers. TRIGGERS - field name collision, terminology overlap, schema dedup, naming inconsistency, telemetry naming, log field similarity.