Automated summary
A single entry point that picks and runs the right qa-* script (dev, pass, or full), then checks TypeScript, tests, and build before reporting results.
Strengths
- Automatically selects the QA level based on context (development, feature completion, pre-ship)
- Enforces an upfront TypeScript check that fails fast on type errors
- Produces a standardized report with test counts and a failure summary
- Clear rules for when to fix, when to flag without blocking, and when to look for a systemic cause
Limitations
- Assumes the scripts scripts/qa-dev.mjs, qa-pass.mjs, and qa-full.mjs already exist, plus a dev server on port 3100
- Does not describe what those scripts actually check or which test types they cover
- The fix/flag decision tree is heuristic (3 and 5 failure thresholds) and may not fit every project
Use it when you want a consistent, full quality pass after finishing a feature or right before shipping.
Avoid it on projects that lack the qa-* scripts or the described Node/TypeScript setup, or when you only need to test a single file.
Security analysis
SafeThe skill is a thin orchestration layer: it selects a QA level, runs `npx tsc --noEmit` and an existing `scripts/qa-[level].mjs`, then reports results. All execution is local and non-destructive, and it explicitly tells the agent not to fake results or skip the type check. The only meaningful risk is that it invokes repository scripts the reader can't see, which is normal for an in-repo tooling skill.
- •Runs repo-local scripts (scripts/qa-*.mjs via `node`) and `npx tsc` without inspecting their contents — risk is inherited from the host repository, not introduced by this skill
- •Assumes a dev server at http://localhost:3100; no credentials or data are sent anywhere
- •No network exfiltration, no destructive filesystem commands, no obfuscated payloads, no safety-disable instructions
Examples
/qa — run a quality check on the auth refactor I just finished.Run a quick QA check, I just want to know if anything is obviously broken.Run everything — full QA before I ship this session.name: qa description: Unified QA pass using existing qa-* scripts. Runs appropriate quality checks based on scope (dev/pass/full). Use when user says /qa, "run tests", "quality check", "is it broken", or before shipping work.
QA (Unified Quality Assurance Pass)
Purpose
Single entry point for all QA scripts. Pick the right level based on context.
Levels
| Level | Script | When | Duration |
| ------ | --------------------- | -------------------------------- | -------- |
| dev | scripts/qa-dev.mjs | Quick sanity during development | ~30s |
| pass | scripts/qa-pass.mjs | After completing a feature | ~2min |
| full | scripts/qa-full.mjs | Before shipping / end of session | ~5min |
Procedure
Phase 1: Select Level
- Default:
pass(covers most cases) - If user says "quick": use
dev - If user says "full" or "everything": use
full - If about to
/shipor/close-session: usefull
Phase 2: Pre-Flight
- Confirm dev server at
http://localhost:3100 - Run
npx tsc --noEmit --skipLibCheckfirst (type errors = instant fail) - If tsc fails: fix type errors, then continue
Phase 3: Execute
node scripts/qa-[level].mjs
Capture output. Parse results.
Phase 4: Report
## QA [level] Results [date]
TypeScript: PASS/FAIL
Tests: X passed, Y failed, Z skipped
Build: PASS/FAIL (if full level)
### Failures (if any)
- [test name]: [error summary]
Phase 5: Fix or Flag
- If < 3 failures and they're in code you touched: fix them
- If failures are in unrelated code: flag but don't block
- If > 5 failures: something systemic, investigate root cause
Constraints
- Never skip tsc check
- Never report "all good" without actually running the script
- If script doesn't exist or errors on startup, report that (don't fake results)
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/unified-qa-procedure-mrx3xwl4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/unified-qa-procedure-mrx3xwl4/download' --output '.skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md.part' && mv '.skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md.part' '.skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md' && test -s '.skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/qa' && cp -R '.skill-downloads/unified-qa-procedure-mrx3xwl4' '.claude/skills/qa'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/unified-qa-procedure-mrx3xwl4'openskills read 'unified-qa-procedure-mrx3xwl4'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/unified-qa-procedure-mrx3xwl4/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
ClickHouse Performance Comparison
Testing
Evaluate ClickHouse performance test results, check PR performance changes, compare with history, and assess whether a result is actionable.
Analyze CI Performance Reports
Testing
Analyze CI performance comparison reports for a ClickHouse PR. Cross-references master history to distinguish real regressions from flaky tests.
Santa Method
Testing
Multi-agent adversarial verification with two independent reviewers. Output is checked twice and iteratively fixed until both pass before shipping.