Automated summary
Verifies that `zbb generate` succeeds and emits consumable TypeScript into generated/ and hub-sdk/generated/ before implementation starts.
Strengths
- Ships a runnable set of bash checks, each paired with an explicit pass criterion.
- The failure section maps every error back to its root cause and says where to fix it (api.yml, never generated/).
- Includes a concrete before/after example of hoisting an inline response schema into a `$ref`.
- Handles connector-specific expectations: a `<Class>Connector` interface and an exported `ConnectionProfile`.
Limitations
- Assumes the internal `zbb` CLI and a specific repo layout (generated/, hub-sdk/, connectionProfile.yml).
- No automated script — every check must be run and interpreted by hand.
- Only validates the shape of generated output, not type correctness or runtime behavior.
Use it after the API spec gate passes and before writing the module implementation (Gate 3).
Not useful on projects that don't use the `zbb` generator, or when debugging runtime test failures rather than generation problems.
Security analysis
SafeNo concerns found
How this analysis is madeExamples
Run the Gate 2 type-generation checks for the orders module: confirm `zbb generate` exits 0, that generated/api, generated/model and hub-sdk/generated/api are populated, and that manifest.json covers every operationId. Report pass/fail per check.`zbb generate` failed Gate 2 with InlineResponse types in generated/. Show me how to hoist the inline 200 response schema in api.yml into components/schemas and re-run generation.This is a connector module. After `zbb generate`, check that a `<Class>Connector` interface exists in generated/api/index.ts and that ConnectionProfile is exported from generated/model/index.ts, then tell me if Gate 3 can start.name: gate-type-generation
description: Gate 2 — zbb generate succeeds and writes consumable TypeScript into generated/ and hub-sdk/generated/. Use after Gate 1, before Gate 3 implementation.
Gate 2: Type generation
After Gate 1, bundleSpec produced a self-contained spec. Gate 2 runs the codegen and checks the output is shaped how the implementation and tests will need it.
What to check
# 1. Regenerate from the spec
zbb generate
# Exit code must be 0.
# 2. Module-side generated/ exists and is populated
test -d generated/api && ls generated/api/*.ts >/dev/null || echo "✗ generated/api/ empty"
test -d generated/model && ls generated/model/*.ts >/dev/null || echo "✗ generated/model/ empty"
test -f generated/api/manifest.json || echo "✗ generated/api/manifest.json missing"
# 3. hub-sdk-side generated/ exists (used by test/e2e via describeModule<T>)
test -f hub-sdk/generated/api/index.ts || echo "✗ hub-sdk/generated/api/index.ts missing"
# 4. No inline-response leakage
grep -rln "InlineResponse\|InlineRequestBody" generated/ hub-sdk/generated/ 2>/dev/null && \
echo "✗ Inline*Response types present — hoist inline schemas in api.yml"
# 5. Connector interface is present (for connector modules)
grep -E "export interface [A-Z][a-zA-Z]+Connector" generated/api/index.ts || \
echo "✗ <Class>Connector interface not generated"
# 6. ConnectionProfile / ConnectionState model types present (connectors only)
test -f connectionProfile.yml && grep -q "export interface ConnectionProfile" generated/model/index.ts \
|| echo " (skip: not a connector or model export shape changed)"
# 7. Module manifest agrees with package.json
jq -r .name package.json
jq -r '.operations | keys[]' generated/api/manifest.json | head
# Should map every operationId from api.yml to <Api>.<method>; missing entries mean spec/operations drifted.
# 8. No leftover stale files (after a forced clean)
git status --short generated/ hub-sdk/generated/ 2>/dev/null
# These directories are gitignored; output should be empty.
Pass criteria
zbb generateexits 0generated/api/,generated/model/,hub-sdk/generated/api/all populatedgenerated/api/manifest.jsonexists and reflects every operationId- No
InlineResponse*/InlineRequestBody*types anywhere - For connectors: a
<Class>Connectorinterface exists andConnectionProfileis exported fromgenerated/model/index.ts
On failure
The failing task tells you the cause:
bundleSpecfailed insidezbb generate— go back to Gate 1generateApifailed — codegen rejects a schema or operation. Read the error verbatim; the fix is inapi.yml, never ingenerated/buildHubSdkfailed — same root cause as above; the hub-sdk generator runs on the same bundled specInlineResponse*appears — a response body has an inline schema. Hoist it:# BEFORE '200': content: application/json: schema: type: object properties: { id: { type: string }, name: { type: string } } # AFTER '200': content: application/json: schema: { $ref: '#/components/schemas/Foo' }- Stale state —
zbb clean && zbb generateto force from cold
Related
- @.claude/skills/api-regeneration/SKILL.md — what
zbb generateruns and how to read its output - @.claude/skills/gate-api-spec/SKILL.md — Gate 1
- @.claude/skills/gate-implementation/SKILL.md — Gate 3 (next)
- @.claude/skills/build-quality/SKILL.md — full lifecycle context
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/gate-2-type-generation-mrx3xwmk/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/gate-2-type-generation-mrx3xwmk' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/gate-2-type-generation-mrx3xwmk/download' --output '.skill-downloads/gate-2-type-generation-mrx3xwmk/SKILL.md.part' && mv '.skill-downloads/gate-2-type-generation-mrx3xwmk/SKILL.md.part' '.skill-downloads/gate-2-type-generation-mrx3xwmk/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/gate-2-type-generation-mrx3xwmk/SKILL.md' && test -s '.skill-downloads/gate-2-type-generation-mrx3xwmk/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/gate-type-generation' && cp -R '.skill-downloads/gate-2-type-generation-mrx3xwmk' '.claude/skills/gate-type-generation'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/gate-2-type-generation-mrx3xwmk'openskills read 'gate-2-type-generation-mrx3xwmk'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/gate-2-type-generation-mrx3xwmk/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.