# Send Code QC to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "code-qc",
    "name": "Code QC",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/IsonaEi/code-qc",
    "canonicalUrl": "https://clawhub.ai/IsonaEi/code-qc",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/code-qc",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=code-qc",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "references/gdscript-profile.md",
      "references/general-profile.md",
      "references/python-profile.md",
      "references/ruff-rules.md",
      "references/typescript-profile.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "code-qc",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T22:22:13.833Z",
      "expiresAt": "2026-05-08T22:22:13.833Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=code-qc",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=code-qc",
        "contentDisposition": "attachment; filename=\"code-qc-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "code-qc"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/code-qc"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/code-qc",
    "downloadUrl": "https://openagent3.xyz/downloads/code-qc",
    "agentUrl": "https://openagent3.xyz/skills/code-qc/agent",
    "manifestUrl": "https://openagent3.xyz/skills/code-qc/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/code-qc/agent.md"
  }
}
```
## Documentation

### Code QC

Structured quality control audit for codebases. Delegates static analysis to proper tools (ruff, eslint, gdlint) and focuses on what AI adds: semantic understanding, cross-module consistency, and dynamic smoke test generation.

### Quick Start

Detect project type (read the profile for that language)
Load .qc-config.yaml if present (for custom thresholds/exclusions)
Run the 8-phase audit (or subset with --quick)
Generate report with verdict
Save baseline for future comparison

### Configuration (.qc-config.yaml)

Optional project-level config for monorepos and custom settings:

# .qc-config.yaml
thresholds:
  test_failure_rate: 0.05    # >5% = FAIL, 0-5% = WARN, 0% = PASS
  lint_errors_max: 0         # Max lint errors before FAIL
  lint_warnings_max: 50      # Max warnings before WARN
  type_errors_max: 0         # Max type errors before FAIL (strict by default)

exclude:
  dirs: [vendor, third_party, generated]
  files: ["*_generated.py", "*.pb.go"]

changed_only: false          # Only check git-changed files (CI mode)
fail_fast: false             # Stop on first failure
quick_mode: false            # Only run Phase 1, 3, 3.5, 6

languages:
  python:
    min_coverage: 80
    ignore_rules: [T201]     # Allow print in this project
  typescript:
    strict_mode: true        # Require tsconfig strict: true
    ignore_rules: []         # eslint rules to ignore
  gdscript:
    godot_version: "4.2"

### Execution Modes

ModePhases RunUse CaseFull (default)All 8 phasesThorough audit--quick1, 3, 3.5, 6Fast sanity check--changed-onlyAll, filteredCI on pull requests--fail-fastAll, stops earlyFind first issue fast--fix3 with autofixApply automatic fixes

### Phase Overview

#PhaseWhatTools1Test SuiteRun existing tests + coveragepytest --cov / jest --coverage2Import IntegrityVerify all modules loadscripts/import_check.py3Static AnalysisLint with proper toolsruff / eslint / gdlint3.5Type CheckingStatic type verificationmypy / tsc --noEmit / (N/A for GDScript)4Smoke TestsVerify business logic worksAI-generated per project5UI/FrontendVerify UI components loadFramework-specific6File ConsistencySyntax + git statescripts/syntax_check.py + git7DocumentationDocstrings + docs accuracyscripts/docstring_check.py

### Phase 1: Test Suite

Run the project's test suite with coverage. Auto-detect the test runner:

pytest.ini / pyproject.toml [tool.pytest] → pytest --cov
package.json scripts.test → npm test (or npx vitest --coverage)
Cargo.toml → cargo test
project.godot → (GUT if present, else manual)

Record: total, passed, failed, errors, skipped, duration, coverage %.

Verdict contribution:

No tests found → SKIP (not FAIL; project may be config-only)
Failure rate = 0% → PASS
Failure rate ≤ threshold (default 5%) → WARN
Failure rate > threshold → FAIL

Coverage reporting (Python):

pytest --cov=<package> --cov-report=term-missing --cov-report=json

### Phase 2: Import Integrity (Python/GDScript)

Python: Run scripts/import_check.py against the project root.

GDScript: Verify scene/preload references are valid (see gdscript-profile.md).

Critical vs Optional Import Classification

Use these heuristics to classify import failures:

PatternClassificationRationale__init__.py, main.py, app.py, cli.pyCriticalCore entry pointsModule in src/, lib/, or top-level packageCriticalCore functionality*_test.py, test_*.py, conftest.pyOptionalTest infrastructureModules in examples/, scripts/, tools/OptionalAuxiliary codeImport error mentions cuml, triton, tensorrtOptionalHardware-specificImport error mentions missing system libOptionalEnvironment-specificDependency in [project.optional-dependencies]OptionalDeclared optional

### Phase 3: Static Analysis

Do NOT use grep. Use the language's standard linter.

Standard Mode

# Python
ruff check --select E722,T201,B006,F401,F841,UP,I --statistics <project>

# TypeScript  
npx eslint . --format json

# GDScript
gdlint <project>

Fix Mode (--fix)

When --fix is specified, apply automatic corrections:

# Python — safe auto-fixes
ruff check --fix --select E,F,I,UP <project>
ruff format <project>

# TypeScript
npx eslint . --fix

# GDScript
gdformat <project>

Important: After --fix, re-run the check to report remaining issues that couldn't be auto-fixed.

### Phase 3.5: Type Checking (NEW)

Run static type analysis before proceeding to runtime checks.

Python:

mypy <package> --ignore-missing-imports --no-error-summary
# or if pyproject.toml has [tool.pyright]:
pyright <package>

TypeScript:

npx tsc --noEmit

GDScript: Godot 4 has built-in static typing but no standalone checker. Estimate type coverage manually:

# Find untyped declarations
grep -rn "var \\w\\+ =" --include="*.gd" .       # Untyped variables
grep -rn "func \\w\\+(" --include="*.gd" . | grep -v ":"  # Untyped functions

Use the estimate_type_coverage() function from gdscript-profile.md to calculate coverage per file:

# From gdscript-profile.md
def estimate_type_coverage(gd_file: str) -> float:
    """Count typed vs untyped declarations."""
    # See full implementation in gdscript-profile.md

Also check for @warning_ignore annotations which may hide type issues.

Record: Total errors, categorized by severity.

### Phase 4: Smoke Tests (Business Logic)

Test backend/core functionality — NOT UI components (that's Phase 5).

API Discovery Heuristics:

Entry points: Look for main(), cli(), app, create_app(), __main__.py
Service layer: Find classes/modules named *Service, *Manager, *Handler
Public API: Check __all__ exports in __init__.py
FastAPI/Flask: Find route decorators (@app.get, @router.post)
CLI: Find typer/click @app.command() decorators
SDK: Look for client classes, public methods without _ prefix

For each discovered API, generate a minimal test:

def smoke_test_user_service():
    """Test UserService basic CRUD."""
    from myproject.services.user import UserService
    svc = UserService(db=":memory:")
    user = svc.create(name="test")
    assert user.id is not None
    fetched = svc.get(user.id)
    assert fetched.name == "test"
    return "PASS"

Guidelines:

Import + instantiate + call one method with minimal valid input
Use in-memory/temp resources (:memory:, tempdir)
Each test < 5 seconds
Catch exceptions, report clearly

### Phase 5: UI/Frontend Verification

Test UI components separately from business logic.

FrameworkTest MethodGradiofrom project.ui import create_ui (no launch())Streamlitstreamlit run app.py --headless exits cleanlyPyQt/PySideSet QT_QPA_PLATFORM=offscreen, import widget modulesReactnpm run build succeedsVuenpm run build succeedsGodotScene files parse without error, required scripts existCLI--help on all subcommands returns 0

Boundary: Phase 4 tests "does the logic work?" Phase 5 tests "does the UI render?"

### Phase 6: File Consistency

Run scripts/syntax_check.py — compiles all source files to verify no syntax errors.

Note: Phase 2 (Import Integrity) tests runtime import behavior including initialization code. Phase 6 tests static syntax correctness. Both are needed: a file can have valid syntax but fail to import (e.g., missing dependency), or vice versa (syntax error in a module that's never imported).

Check git state:

git status --short      # Should be clean (or report uncommitted changes)
git diff --check        # No conflict markers

### Phase 7: Documentation

Run scripts/docstring_check.py (now checks __init__.py by default).

Also verify:

README exists and is non-empty
Key docs (CHANGELOG, CONTRIBUTING) exist if referenced
No stale TODO markers in docs claiming completion

### Verdict Logic

# Calculate test failure rate
failure_rate = test_failures / total_tests

# Default thresholds (override in .qc-config.yaml)
FAIL_THRESHOLD = 0.05  # 5%
WARN_THRESHOLD = 0.00  # 0%
TYPE_ERRORS_MAX = 0    # Default: strict (any type error = FAIL)

# Verdict determination
if any([
    failure_rate > FAIL_THRESHOLD,
    critical_import_failure,
    type_check_errors > thresholds.type_errors_max,  # Configurable threshold
    lint_errors > thresholds.lint_errors_max,
]):
    verdict = "FAIL"
elif any([
    0 < failure_rate <= FAIL_THRESHOLD,
    optional_import_failures > 0,
    lint_warnings > thresholds.lint_warnings_max,
    missing_docstrings > 0,
    smoke_test_failures > 0,
]):
    verdict = "PASS WITH WARNINGS"
else:
    verdict = "PASS"

### Baseline Comparison

Save results to .qc-baseline.json:

{
  "timestamp": "2026-02-15T15:00:00Z",
  "commit": "abc123",
  "verdict": "PASS WITH WARNINGS",
  "config": {
    "mode": "full",
    "thresholds": {"test_failure_rate": 0.05}
  },
  "phases": {
    "tests": {"total": 134, "passed": 134, "failed": 0, "coverage": 87.5},
    "imports": {"total": 50, "failed": 0, "optional_failed": 1, "critical_failed": 0},
    "types": {"errors": 0, "warnings": 5},
    "lint": {"errors": 0, "warnings": 12, "fixed": 8},
    "smoke": {"total": 14, "passed": 14},
    "docs": {"missing_docstrings": 3}
  }
}

On subsequent runs, report delta:

Tests:      134 → 140 (+6 ✅)
Coverage:   87% → 91% (+4% ✅)
Type errors: 0 → 0 (✅)
Lint warnings: 12 → 5 (-7 ✅)

### Report Output

Generate in 3 formats:

Markdown (qc-report.md) — full detailed report for humans
JSON (.qc-baseline.json) — machine-readable for CI/comparison
Summary (chat message) — 10-line digest for Discord/Slack

### Summary Format Example

📊 QC Report: my-project @ abc123
Verdict: ✅ PASS WITH WARNINGS

Tests:    134/134 passed (100%) | Coverage: 87%
Types:    0 errors
Lint:     0 errors, 12 warnings
Imports:  50/50 (1 optional failed)
Smoke:    14/14 passed

⚠️ Warnings:
- 3 missing docstrings
- 12 lint warnings (run with --fix)

### Language-Specific Profiles

Read the appropriate profile before running:

Python: references/python-profile.md
TypeScript: references/typescript-profile.md
GDScript: references/gdscript-profile.md
General (any language): references/general-profile.md
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: IsonaEi
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-01T22:22:13.833Z
- Expires at: 2026-05-08T22:22:13.833Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/code-qc)
- [Send to Agent page](https://openagent3.xyz/skills/code-qc/agent)
- [JSON manifest](https://openagent3.xyz/skills/code-qc/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/code-qc/agent.md)
- [Download page](https://openagent3.xyz/downloads/code-qc)