Continuity Test — Testing skill for Claude Code
Memory retrieval regression test — runs curated query→memory cases through hybrid search (use: /continuity-test [--weight core] [--baseline save diff path]).
How to install Continuity Test
Installs to ~/.claude/skills/mffnxman-memory-spine-continuity-test/SKILL.md
mkdir -p ~/.claude/skills/mffnxman-memory-spine-continuity-test && curl -fsSL https://raw.githubusercontent.com/mffnxman/memory-spine/HEAD/commands/continuity-test.md -o ~/.claude/skills/mffnxman-memory-spine-continuity-test/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Continuity Test does
description: "Memory retrieval regression test — runs curated query→memory cases through hybrid search (use: /continuity-test [--weight core] [--baseline save|diff path])"
Continuity Test
The user invoked `/continuity-test`. Regression harness for the memory retrieval system — runs curated query→expected-memory cases through `search_hybrid` and reports pass rate + MRR.
Pass criterion: any of `expected` files appears in top-K (default 3).
Usage
/continuity-test
Alternatives in Testing
- #29 — #52, #103) 92.5k ★
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- AI Contribution Skills (Engram) — branch-pr: clean branch and PR workflow 2.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Godspeed
Routing classifier + multi-agent orchestrator for Claude Code. 3-4ms Node fast-path hook, per-prompt S0-S5 tie
Performance Test
Run performance profiling and load testing using the performance-engineer agent — API response times, Node.js
Sdd Reconcile.Prompt
Fold already-shipped, undocumented code changes back into a baseline domain's spec as a retroactive, diff-wind
AI Test Platform
An AI-driven test execution platform where QA engineers save structured test cases per project and an AI agent
Claude Codepro
by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen
Webtest Orch
Token-efficient e2e orchestration skill for Claude Code: explore once, replay deterministically. Playwright +
Related Agents
Lens QA
QA lens of the production readiness audit. Judges what is untested and what that costs - critical-path coverag
Agent Eval Engineer
Use to design and run regression evaluations for an agent, skill, tool, or prompt — happy-path, edge-case, adv
QA Strategist
Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, erro