Quality Gates

VerifiedCaution

Automated code quality validation that runs configurable checks (formatting, linting, type checking, tests, security) on code changes. Detects project configuration to use appropriate tools (Prettier, ESLint, TypeScript, etc.) and generates structured reports. Useful for enforcing quality standards before completing subtasks or during code review.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#quality-gates#code-quality#linting#testing#auto-fix

Recommended for

Automated summary

This skill runs configurable quality checks (formatting, linting, type checking, testing, security) on code changes and reports results, with auto-fix capabilities and blocking/non-blocking rules.

Strengths

  • Supports multiple languages and tools
  • Auto-fixes formatting and some lint issues
  • Provides structured JSON reports
  • Respects project configuration and allows overrides

Limitations

  • Relies on installed tools (prettier, eslint, etc.) and configuration files
  • Security checks are optional and tool-dependent
  • Blocking decisions may not suit all workflows
When to use it

Use after writing or modifying code, before marking a subtask complete, or during QA review to ensure consistent quality standards.

When not to use it

Do not use as a substitute for deep code review or for projects that have incompatible custom toolchains.

Security analysis

Caution
Quality score80/100

The skill legitimately uses bash commands to run quality checks, but these commands could potentially execute malicious scripts from project dependencies. No destructive or exfiltrating actions are instructed, but the dynamic nature of project tooling warrants caution.

Findings
  • •Executes project-specific tools (npx, npm audit) which may run arbitrary code from project dependencies.
  • •Auto-fix capability can modify source files.
How this analysis is made

Examples

Run quality gates
Please run the quality gates on my recent changes and fix any auto-fixable issues.
Check code quality before commit
Check formatting and lint for all files in src/ directory before I commit.
Validate entire project
Run all quality checks (format, lint, type check, tests, security) on the project and generate a report.

name: quality-gates description: Automated code quality validation with configurable checks version: 1.0.0

Quality Gates Skill

Automated code quality validation with configurable checks.

Description

This skill runs quality checks on code changes and reports results. It integrates with project-specific tooling and provides consistent validation across the siftcoder workflow.

When to Use

Invoke this skill when:

  • Code has been written or modified
  • Before marking a subtask as complete
  • During QA review phase
  • User requests manual quality check

Instructions

You are a quality gate runner. Your job is to validate code changes against project quality standards.

Quality Checks Available

  1. Format Check

    • Prettier (JS/TS/JSON/MD/CSS)
    • Black (Python)
    • gofmt (Go)
    • rustfmt (Rust)
  2. Lint Check

    • ESLint (JS/TS)
    • Flake8/Pylint (Python)
    • golangci-lint (Go)
    • Clippy (Rust)
  3. Type Check

    • TypeScript (tsc)
    • mypy (Python)
    • Go compiler
  4. Test Check

    • Jest/Vitest (JS/TS)
    • Pytest (Python)
    • go test (Go)
    • cargo test (Rust)
  5. Security Check (if available)

    • npm audit
    • Semgrep
    • Bandit (Python)

Execution Flow

  1. Detect Project Type

    Detecting project configuration...
    ├── package.json → Node.js project
    ├── tsconfig.json → TypeScript enabled
    ├── .prettierrc → Prettier configured
    └── jest.config.js → Jest for testing
    
  2. Run Configured Checks

    🔍 QUALITY GATES
    
    [1/4] Format Check (Prettier)
          Running: npx prettier --check src/
          Result: ✓ All files formatted
    
    [2/4] Lint Check (ESLint)
          Running: npx eslint src/ --format json
          Result: ⚠️ 2 warnings, 0 errors
          - src/utils.ts:15 - Unused variable 'temp'
          - src/api.ts:42 - Prefer const over let
    
    [3/4] Type Check (TypeScript)
          Running: npx tsc --noEmit
          Result: ✓ No type errors
    
    [4/4] Test Check (Jest)
          Running: npx jest --passWithNoTests
          Result: ✓ 47 tests passing
    
  3. Generate Report

    {
      "timestamp": "2026-01-10T15:30:00Z",
      "checks": {
        "format": { "status": "pass", "tool": "prettier" },
        "lint": {
          "status": "warn",
          "tool": "eslint",
          "warnings": 2,
          "errors": 0,
          "issues": [
            { "file": "src/utils.ts", "line": 15, "message": "Unused variable" }
          ]
        },
        "typeCheck": { "status": "pass", "tool": "tsc" },
        "tests": { "status": "pass", "tool": "jest", "passed": 47, "failed": 0 }
      },
      "summary": {
        "passed": 3,
        "warned": 1,
        "failed": 0,
        "blocked": false
      }
    }
    

Blocking vs Non-Blocking

Blocking (stops workflow):

  • Any type errors
  • Any lint errors (not warnings)
  • Any test failures
  • Security vulnerabilities (high/critical)

Non-Blocking (warns but continues):

  • Format issues (auto-fixed when possible)
  • Lint warnings
  • Low/medium security issues

Auto-Fix Capabilities

When possible, automatically fix issues:

🔧 AUTO-FIX APPLIED

Format:
├── src/utils.ts - Reformatted
└── src/api.ts - Reformatted

Lint (auto-fixable):
└── src/config.ts - Fixed import order

Re-running checks after fixes...

Configuration Detection

The skill respects project configuration:

  • .prettierrc / prettier.config.js
  • .eslintrc / eslint.config.js
  • tsconfig.json
  • jest.config.js / vitest.config.ts
  • pyproject.toml (for Python projects)

Per-Project Overrides

Read from .claude/siftcoder-state/config.json:

{
  "qualityGates": {
    "format": true,
    "lint": true,
    "typeCheck": true,
    "tests": true,
    "security": false,
    "blockOnWarnings": false
  }
}

Output Format

Return structured result:

{
  "passed": true|false,
  "blocked": true|false,
  "checks": { ... },
  "summary": "All quality gates passed" | "Blocked: 2 type errors",
  "autoFixed": ["file1.ts", "file2.ts"]
}

Runtime Implementation

This skill includes a minimal skill.ts entry point to satisfy plugin requirements. The primary value remains in this documentation - see sections above for:

  • Quality gate patterns
  • Configuration detection
  • Auto-fix capabilities

The runtime entry point can be extended with actual functionality as needed.

Allowed Tools

Bash, Read, Glob

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 files

This 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.md

From the root of a test project, save the file as .skill-downloads/quality-gates-mm78no23/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/quality-gates-mm78no23' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/quality-gates-mm78no23/download' --output '.skill-downloads/quality-gates-mm78no23/SKILL.md.part' && mv '.skill-downloads/quality-gates-mm78no23/SKILL.md.part' '.skill-downloads/quality-gates-mm78no23/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/quality-gates-mm78no23/SKILL.md' && test -s '.skill-downloads/quality-gates-mm78no23/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/quality-gates' && cp -R '.skill-downloads/quality-gates-mm78no23' '.claude/skills/quality-gates'

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 installation
openskills install './.skill-downloads/quality-gates-mm78no23'

openskills read 'quality-gates-mm78no23'

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 sync

Manual 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/quality-gates-mm78no23/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.

Related skills