QA Learn — Testing skill for Claude Code
Capture durable knowledge from completed work — update the graph, invalidate what evidence contradicts, record the retrospective.
How to install QA Learn
Installs to ~/.claude/commands/svvbathini-w-test-harness-qa-learn.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/SVVBathini-w/Test-Harness/HEAD/.claude/commands/qa-learn.md -o ~/.claude/commands/svvbathini-w-test-harness-qa-learn.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Learn does
description: Capture durable knowledge from completed work — update the graph, invalidate what evidence contradicts, record the retrospective argument-hint: [slug] allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Task, Skill model: haiku
Capture knowledge from: **$ARGUMENTS**
Follow `CLAUDE.md` sections 7, 26 and 28, and the `knowledge-capture` skill. Phase 12.
Step 1 — Review what happened
Read `analysis/discovery.json`, `registry/heals.json`, `registry/defects.json`, and for
Alternatives in Testing
- Axiom — Development Changelog — Purpose: Historical record of Axiom development milestones, TDD testing results, and architectural decisions 671 ★
- Design Compare — Capture two websites with Playwright and produce a structured side-by-side design comparison — layout, color 309 ★
- Specweave — Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to 158 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Verify Work
Execute a work item's testing-plan.md after implementation — run the planned activities, record results, commi
Notion Skills
Claude Skills marketplace for productive Notion workflows: knowledge capture, meeting intelligence, research d
Agent OS Setup
Bootstrap the Agent OS data home + verify harness on this machine (product graph, registry, Playwright, auth c
X Bookmarks Skill Graph
A skill-graph knowledge system for organizing X (Twitter) bookmarks as an interconnected graph of ideas. Testi
Superskill
One-entry orchestrator for coding agents: jailed vault, FTS knowledge graph, 18-axis review, in-harness Chrome
Wave Sweep
Close out a release wave. After several agents land PRs and CI settles, harvest unfiled findings into the trac
Related Agents
Runtime Observer
Interprets imported runtime evidence (traces, metrics, profiles, topology) against the static graph and report
Project Knowledge Curator
Use this agent when you need to create, update, or maintain comprehensive project documentation and knowledge
Mauro Context Curator
Distills verified Voyage evidence into durable Mauro knowledge candidates and Chronicle records. Use after cod