cross-boundary-qa
Skill9 starsChanged 5 months agoMITView on GitHub
Integration QA rules for ableton-mind boundaries across TS, Python, knowledge and recipes, including parity checks, contract drift, recipe lint and smoke gates.
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill for scripts or reports under scripts/qa/ and _workspace/qa/.
- Very specific: line 24
Write _workspace/qa/cycle-{N}-report.md with status PASS, PASS-WITH-WARNINGS or FAIL.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cross-Boundary QA
Use this skill for scripts or reports under scripts/qa/ and _workspace/qa/.
Principle
Each track owns its internals. QA owns the boundaries where independently correct pieces can still disagree.
Checks
- Tool/handler parity: compare defineTool names in src/tools with registered Python handlers.
- Contract drift: compare Zod schemas and Python dataclasses or returned payloads.
- Recipe lint: every step.tool exists, inputs match schemas and refs resolve.
- Knowledge consistency: device IDs, parameter names, indexes, units and URIs are unique and valid.
- Smoke: run bridge mock smoke in CI; run real Live smoke locally when available.
Report Format
Write _workspace/qa/cycle-{N}-report.md with status PASS, PASS-WITH-WARNINGS or FAIL. Findings lead with severity, file/line, symptom, repro command or steps, likely owner and suggested fix.
Gate Guidance
BLOCKER stops the next cycle until fixed. MAJOR can pass with warnings only if the architect records the debt. MINOR is tracked but does not block. Repeated patterns should become lint or codegen proposals.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ableton-mind-buildSkill
- ableton-remote-scriptSkill
- device-schema-extractionSkill
- mcp-distributionSkill
- mcp-server-developmentSkill
- recipe-authoringSkill
- ableton-mind-buildSkill
- ableton-mind-quality-auditSkill
- ableton-remote-scriptSkill
- command-surface-auditSkill
- cross-boundary-qaSkill
- device-schema-extractionSkill
- local-copilotSkill
- mcp-distributionSkill
- mcp-server-developmentSkill
- recipe-authoringSkill
- refactor-maintainabilitySkill
- runtime-release-auditSkill
- security-auditSkill
- test-coverage-expansionSkill
- usability-flow-auditSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.