Agent skill

overlay-loader

Stars 6
Forks 3

Install this agent skill to your Project

npx add-skill https://github.com/BerryKuipers/claude-code-toolkit/tree/main/.claude/skills/overlay-loader

SKILL.md

Overlay Loader Skill

Loads project-specific overlay configuration from .claude/overlays/<project>/config.yml.

When to Use

  • At session start (via session-start hook)
  • When switching project context
  • When initializing wrapper commands

Execution

Step 1: Detect Project

Determine project name from:

  1. $CLAUDE_PROJECT environment variable
  2. Git remote URL parsing (e.g., wescobar from github.com/.../Wescobar)
  3. Directory name as fallback

Step 2: Load Overlay Config

bash
PROJECT_NAME=$(basename "$(git remote get-url origin 2>/dev/null | sed 's/\.git$//')" | tr '[:upper:]' '[:lower:]')
OVERLAY_PATH=".claude/overlays/${PROJECT_NAME}/config.yml"

if [ -f "$OVERLAY_PATH" ]; then
  echo "Loading overlay: $PROJECT_NAME"
  cat "$OVERLAY_PATH"
else
  echo "No overlay found for: $PROJECT_NAME"
fi

Step 3: Apply Configuration

From the loaded config, extract and apply:

  • allowed_agents: List of upstream agents permitted for this project
  • disabled_agents: Agents that should warn if invoked
  • enabled_mcp_servers: MCP servers to activate
  • thresholds: Quality gate thresholds (coverage, complexity)
  • verification_gates: Pre/post implementation checks

Output

Return a summary for the session context:

Project: wescobar
Prefix: wsc
Allowed agents: planner, architect, code-reviewer, security-reviewer, e2e-runner, tdd-guide
MCP servers: supabase, vercel
Test coverage min: 70%

Integration

This skill is called by:

  • session-start.sh hook (optional)
  • bk-* wrapper commands (to validate agent usage)
  • Orchestrator when delegating to agents

Expand your agent's capabilities with these related and highly-rated skills.

BerryKuipers/claude-code-toolkit

validate-typescript

Run TypeScript compiler type-checking (tsc --noEmit) to validate type safety and catch type errors. Returns structured output with error counts, categories (type/syntax/import errors), and affected files. Used for quality gates and pre-commit validation.

6 3
Explore
BerryKuipers/claude-code-toolkit

validate-coverage-threshold

Validate test coverage meets minimum thresholds (default 80% overall, 80% statements, 75% branches, 80% functions). Parses coverage reports from coverage/coverage-summary.json or test output. Returns pass/fail status with detailed metrics and identifies uncovered files.

6 3
Explore
BerryKuipers/claude-code-toolkit

quality-gate

Comprehensive quality validation for TypeScript/JavaScript projects - runs TypeScript checks, tests, coverage analysis, build validation, and linting with structured JSON results

6 3
Explore
BerryKuipers/claude-code-toolkit

run-comprehensive-tests

Execute comprehensive test suite (Vitest/Jest) with coverage reporting and failure analysis. Returns structured output with test counts (total/passed/failed), coverage percentage, duration, and detailed failure information. Used for quality gates and CI/CD validation.

6 3
Explore
BerryKuipers/claude-code-toolkit

validate-build

Run production build validation (npm run build, vite build, tsc) to ensure code compiles and builds successfully. Returns structured output with build status, duration, size metrics, and error details. Used for quality gates and deployment readiness checks.

6 3
Explore
BerryKuipers/claude-code-toolkit

validate-lint

Run ESLint and Prettier validation to check code style, formatting, and best practices. Returns structured output with error/warning counts, rule violations, and affected files. Used for code quality gates and pre-commit validation.

6 3
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results