Agent skill

Context Detection

by MadAppGang in MadAppGang/claude-code

A skill your agent uses when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g…

MITAuto-check passed

Install Context Detection

skills CLI
$ npx skills add MadAppGang/claude-code --skill context-detection -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MadAppGang/claude-code context-detection --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/dev/skills/context-detection .claude/skills/context-detection && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
context-detection
GitHub stars
285
Token cost
~5.4k tokens
SKILL.md length
451 words
Files
2 (incl. scripts)
Skills in repo
69
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g…

  • Works in 4 steps: Explicit User Preference (Highest… → Current File Context → Configuration Files (Primary Detection) → …
  • Detecting project technology stack from files/configs/directory structure
  • SKILL.md covers Quick Start: Skill Discovery…, Overview, Detection Priority and Multi-Stack Detection Algorithm, plus 5 more sections
  • Runs JavaScript scripts from its folder; calls jq, node and python

What it does

Context Detection is an agent skill from MadAppGang/claude-code. Use when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g., React + Go).

Its SKILL.md is about 5.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/discover-skills.js`).

It works with React. The repository describes itself as: claude code plugins marketplace. The licence is MIT.

When your agent uses it

  • Detecting project technology stack from files/configs/directory structure
  • Auto-loading framework-specific skills
  • Analyzing multi-stack fullstack projects (e.g.

Example prompts

  • “/context-detection”

Requirements

  • Python 3
  • Node.js
  • Pre-approved tools (allowed-tools): Bash(node *)

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Explicit User Preference (Highest Priority)
  2. Current File Context
  3. Configuration Files (Primary Detection)
  4. Directory Structure Patterns (Supporting Evidence)

What it can do on your machine

Read from SKILL.md and the folder at commit 6097ad4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(node *)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • jq
    • node
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Context Detection loads about 5.4k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 451 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~5.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from MadAppGang/claude-code at commit 6097ad4, republished under its MIT licence (© MadAppGang). 451 words, ~5,376 tokens.

Download SKILL.mdSave it as .claude/skills/context-detection/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
context-detection
description
Use when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g., React + Go).
allowed-tools
Bash(node *)
version
1.1.0
keywords
context detection, stack detection, technology stack, project analysis, auto-detection, framework detection, skill discovery
plugin
dev
updated
2026-02-03
used_by
stack-detector agent, all dev commands

Context Detection Skill

Quick Start: Skill Discovery Script

Run the helper script to discover ALL skills available to a project:

bash
node "${CLAUDE_PLUGIN_ROOT}/skills/context-detection/scripts/discover-skills.js" "$(pwd)"

This searches all 7 official Claude Code skill locations:

  1. Personal: ~/.claude/skills/
  2. Project: .claude/skills/
  3. Nested (monorepos): **/.claude/skills/
  4. Legacy commands: .claude/commands/
  5. Marketplace plugins: ~/.claude/plugins/marketplaces/{m}/plugins/{p}/skills/
  6. Local plugins: .claude-plugin/skills/, plugins/*/skills/
  7. Enterprise (managed settings)

Output: JSON with summary stats and full skill metadata.

For detailed documentation on the script, see scripts/discover-skills.js.


Overview

The context detection skill provides systematic patterns for analyzing any project to determine its technology stack(s). It enables the dev plugin to auto-load appropriate framework-specific skills based on what's actually in the project.

Key Innovation: Multi-stack detection for fullstack projects (e.g., React + Go).


Detection Priority

Detection follows a priority order from most explicit to most inferred:

1. Explicit User Preference (Highest Priority)

Source: .claude/settings.json

json
{
  "pluginSettings": {
    "dev": {
      "stack": ["react-typescript", "golang"],
      "features": {
        "testing": "vitest",
        "api": "rest"
      }
    }
  }
}

When to use:

  • User wants to override auto-detection
  • Project has ambiguous structure
  • Custom stack combinations
2. Current File Context

Source: File extension of current editing context

yaml
extension_mappings:
  ".tsx": ["react-typescript", "testing-frontend"]
  ".vue": ["vue-typescript", "testing-frontend"]
  ".go": ["golang", "testing-strategies"]
  ".dingo": ["dingo", "golang", "testing-strategies"]
  ".rs": ["rust", "testing-strategies"]
  ".py": ["python", "testing-strategies"]

When to use:

  • User is editing a specific file
  • Immediate context for implementation
  • Quick detection without full project scan
3. Configuration Files (Primary Detection)

Source: Project configuration files

yaml
config_file_patterns:
  package.json:
    check: "dependencies.react exists"
    skills: ["react-typescript", "state-management", "testing-frontend"]
    mode: "frontend"

  package.json:
    check: "dependencies.vue exists"
    skills: ["vue-typescript", "state-management", "testing-frontend"]
    mode: "frontend"

  go.mod:
    check: "file exists"
    skills: ["golang", "api-design", "database-patterns"]
    mode: "backend"

  go.mod + *.dingo:
    check: "go.mod exists AND any .dingo files present"
    skills: ["dingo", "golang", "api-design", "database-patterns"]
    mode: "backend"
    note: "Dingo projects always include golang skill since Dingo transpiles to Go"

  Cargo.toml:
    check: "file exists"
    skills: ["rust", "api-design"]
    mode: "backend"

  pyproject.toml:
    check: "file exists"
    skills: ["python", "api-design"]
    mode: "backend"

  bun.lockb:
    check: "file exists AND no react/vue in package.json"
    skills: ["bunjs", "api-design"]
    mode: "backend"

When to use:

  • First time analyzing a project
  • Most reliable detection method
  • Determine versions and dependencies
4. Directory Structure Patterns (Supporting Evidence)

Source: Common directory layouts

yaml
directory_patterns:
  "src/routes/":
    indicator: "React Router structure"
    skills: ["react-typescript"]

  "src/components/":
    indicator: "Component-based frontend"
    skills: ["react-typescript", "vue-typescript"]

  "cmd/":
    indicator: "Go standard project layout"
    skills: ["golang"]

  "src/main.rs":
    indicator: "Rust binary crate"
    skills: ["rust"]

  "frontend/":
    indicator: "Separate frontend directory (fullstack)"
    note: "Check for backend/ as well"

  "backend/":
    indicator: "Separate backend directory (fullstack)"
    note: "Check for frontend/ as well"

When to use:

  • Confirming config file detection
  • Identifying fullstack projects
  • Disambiguating multi-purpose projects

Multi-Stack Detection Algorithm

CRITICAL: Always check for MULTIPLE stacks. Projects can be fullstack.

bash
# Step 1: Find ALL config files (not just first match)
find_all_configs() {
  configs=()
  [ -f "package.json" ] && configs+=("package.json")
  [ -f "go.mod" ] && configs+=("go.mod")
  [ -f "Cargo.toml" ] && configs+=("Cargo.toml")
  [ -f "pyproject.toml" ] && configs+=("pyproject.toml")
  [ -f "bun.lockb" ] && configs+=("bun.lockb")

  # Check for Dingo files (go.mod must also exist)
  # Note: "dingo" is a detection indicator, not an actual config file name
  if [ -f "go.mod" ] && find . -name "*.dingo" -type f ! -path "./.git/*" ! -path "./node_modules/*" ! -path "./vendor/*" -print -quit | grep -q .; then
    configs+=("dingo")
  fi

  echo "${configs[@]}"
}

# Step 2: Analyze EACH config file
analyze_all_configs() {
  local detected_stacks=()

  # Check package.json
  if [ -f "package.json" ]; then
    if grep -q '"react"' package.json; then
      detected_stacks+=("react-typescript")
    elif grep -q '"vue"' package.json; then
      detected_stacks+=("vue-typescript")
    fi
  fi

  # Check go.mod (and optionally Dingo)
  if [ -f "go.mod" ]; then
    # Check if this is a Dingo project
    if find . -name "*.dingo" -type f ! -path "./.git/*" ! -path "./node_modules/*" ! -path "./vendor/*" -print -quit | grep -q .; then
      detected_stacks+=("dingo")
      # Dingo always co-loads golang
      detected_stacks+=("golang")
    else
      detected_stacks+=("golang")
    fi
  fi

  # Check Cargo.toml
  if [ -f "Cargo.toml" ]; then
    detected_stacks+=("rust")
  fi

  # Check pyproject.toml
  if [ -f "pyproject.toml" ]; then
    detected_stacks+=("python")
  fi

  # Check bun.lockb (only if NOT frontend)
  if [ -f "bun.lockb" ] && ! grep -q '"react"\|"vue"' package.json 2>/dev/null; then
    detected_stacks+=("bunjs")
  fi

  echo "${detected_stacks[@]}"
}

# Step 3: Determine mode
determine_mode() {
  local stacks=("$@")
  local has_frontend=false
  local has_backend=false

  for stack in "${stacks[@]}"; do
    case "$stack" in
      react-typescript|vue-typescript)
        has_frontend=true
        ;;
      golang|rust|python|bunjs|dingo)
        has_backend=true
        ;;
    esac
  done

  if [ "$has_frontend" = true ] && [ "$has_backend" = true ]; then
    echo "fullstack"
  elif [ "$has_frontend" = true ]; then
    echo "frontend"
  elif [ "$has_backend" = true ]; then
    echo "backend"
  else
    echo "unknown"
  fi
}

# Step 4: Map stacks to skills
map_stacks_to_skills() {
  local stacks=("$@")
  local skills=(
    # Core skills (ALWAYS included)
    "universal-patterns"
    "testing-strategies"
    "debugging-strategies"
  )

  for stack in "${stacks[@]}"; do
    case "$stack" in
      react-typescript)
        skills+=("react-typescript" "state-management" "testing-frontend")
        ;;
      vue-typescript)
        skills+=("vue-typescript" "state-management" "testing-frontend")
        ;;
      golang)
        skills+=("golang" "api-design" "database-patterns")
        ;;
      dingo)
        skills+=("dingo" "golang" "api-design" "database-patterns")
        ;;
      rust)
        skills+=("rust" "api-design")
        ;;
      python)
        skills+=("python" "api-design")
        ;;
      bunjs)
        skills+=("bunjs" "api-design")
        ;;
    esac
  done

  # Deduplicate
  echo "${skills[@]}" | tr ' ' '\n' | sort -u
}

# Step 5: Complete detection
detect_project_stack() {
  # Check explicit preference first
  local explicit_stack=$(jq -r '.pluginSettings.dev.stack // empty' .claude/settings.json 2>/dev/null)
  if [ -n "$explicit_stack" ]; then
    echo "Using explicit stack from .claude/settings.json"
    return
  fi

  # Auto-detect all stacks
  local detected_stacks=($(analyze_all_configs))

  if [ ${#detected_stacks[@]} -eq 0 ]; then
    echo "ERROR: No stack detected"
    return 1
  fi

  # Determine mode
  local mode=$(determine_mode "${detected_stacks[@]}")

  # Map to skills
  local skills=($(map_stacks_to_skills "${detected_stacks[@]}"))

  # Output result
  echo "Detected: ${detected_stacks[*]}"
  echo "Mode: $mode"
  echo "Skills: ${skills[*]}"
}

Framework-Specific Detection

React Detection
bash
detect_react() {
  # Check package.json
  if [ -f "package.json" ]; then
    # React in dependencies or devDependencies
    if jq -e '.dependencies.react // .devDependencies.react' package.json >/dev/null 2>&1; then
      # Check for TypeScript
      local has_typescript=false
      if jq -e '.dependencies["@types/react"] // .devDependencies["@types/react"]' package.json >/dev/null 2>&1; then
        has_typescript=true
      fi

      # Get version
      local react_version=$(jq -r '.dependencies.react // .devDependencies.react' package.json | sed 's/[^0-9.]//g')

      echo "react-typescript"
      echo "version: $react_version"
      echo "typescript: $has_typescript"
      return 0
    fi
  fi

  return 1
}
Vue Detection
bash
detect_vue() {
  if [ -f "package.json" ]; then
    if jq -e '.dependencies.vue' package.json >/dev/null 2>&1; then
      local vue_version=$(jq -r '.dependencies.vue' package.json | sed 's/[^0-9.]//g')
      echo "vue-typescript"
      echo "version: $vue_version"
      return 0
    fi
  fi

  return 1
}
Go Detection
bash
detect_go() {
  if [ -f "go.mod" ]; then
    local go_version=$(grep '^go ' go.mod | awk '{print $2}')
    local module_name=$(grep '^module ' go.mod | awk '{print $2}')

    echo "golang"
    echo "version: $go_version"
    echo "module: $module_name"
    return 0
  fi

  return 1
}
Rust Detection
bash
detect_rust() {
  if [ -f "Cargo.toml" ]; then
    local package_name=$(grep '^\[package\]' -A 5 Cargo.toml | grep '^name' | cut -d'"' -f2)
    local edition=$(grep '^\[package\]' -A 5 Cargo.toml | grep '^edition' | cut -d'"' -f2)

    echo "rust"
    echo "edition: $edition"
    echo "package: $package_name"
    return 0
  fi

  return 1
}
Python Detection
bash
detect_python() {
  if [ -f "pyproject.toml" ]; then
    local has_fastapi=$(grep -i 'fastapi' pyproject.toml)
    local has_django=$(grep -i 'django' pyproject.toml)

    echo "python"
    [ -n "$has_fastapi" ] && echo "framework: fastapi"
    [ -n "$has_django" ] && echo "framework: django"
    return 0
  fi

  return 1
}
Bun Detection
bash
detect_bun() {
  # Bun backend (NOT frontend with Bun runtime)
  if [ -f "bun.lockb" ]; then
    # Check if this is a frontend project
    if [ -f "package.json" ]; then
      if jq -e '.dependencies.react // .dependencies.vue' package.json >/dev/null 2>&1; then
        # This is frontend using Bun runtime, not Bun backend
        return 1
      fi
    fi

    # This is a Bun backend project
    echo "bunjs"
    return 0
  fi

  return 1
}

Quality Checks by Stack

Quality checks are automatically determined based on detected stack(s):

Show full SKILL.md (180 more words)Show less
Frontend Quality Checks
yaml
react-typescript:
  - command: "bun run format"
    tool: "Biome"
    purpose: "Code formatting"
  - command: "bun run lint"
    tool: "Biome"
    purpose: "Linting"
  - command: "bun run typecheck"
    tool: "TypeScript"
    purpose: "Type checking"
  - command: "bun test"
    tool: "Vitest"
    purpose: "Unit tests"

vue-typescript:
  - command: "bun run format"
    tool: "Biome"
  - command: "bun run lint"
    tool: "Biome"
  - command: "bun run typecheck"
    tool: "TypeScript"
  - command: "bun test"
    tool: "Vitest"
Backend Quality Checks
yaml
golang:
  - command: "go fmt ./..."
    purpose: "Format Go code"
  - command: "go vet ./..."
    purpose: "Static analysis"
  - command: "golangci-lint run"
    purpose: "Comprehensive linting"
  - command: "go test ./..."
    purpose: "Run tests"

dingo:
  - command: "dingo fmt"
    purpose: "Format Dingo source files"
  - command: "dingo go"
    purpose: "Transpile Dingo to Go"
  - command: "go vet ./.dingo/..."
    purpose: "Static analysis on generated Go"
  - command: "golangci-lint run ./.dingo/..."
    purpose: "Comprehensive linting on generated Go"
  - command: "go test ./.dingo/..."
    purpose: "Run tests on generated Go"

rust:
  - command: "cargo fmt --check"
    purpose: "Check formatting"
  - command: "cargo clippy -- -D warnings"
    purpose: "Linting"
  - command: "cargo test"
    purpose: "Run tests"

python:
  - command: "black --check ."
    purpose: "Check formatting"
  - command: "ruff check ."
    purpose: "Linting"
  - command: "mypy ."
    purpose: "Type checking"
  - command: "pytest"
    purpose: "Run tests"

bunjs:
  - command: "bun run format"
    tool: "Biome"
  - command: "bun run lint"
    tool: "Biome"
  - command: "bun run typecheck"
    tool: "TypeScript"
  - command: "bun test"
    tool: "Bun test runner"
Fullstack Quality Checks

For fullstack projects, run checks for BOTH stacks:

yaml
fullstack (react + go):
  frontend:
    directory: "./frontend"
    checks:
      - "cd frontend && bun run format"
      - "cd frontend && bun run lint"
      - "cd frontend && bun run typecheck"
      - "cd frontend && bun test"
  backend:
    directory: "."
    checks:
      - "go fmt ./..."
      - "go vet ./..."
      - "golangci-lint run"
      - "go test ./..."

Skill Path Generation

Convert detected stacks to skill file paths using ${PLUGIN_ROOT} placeholder:

bash
generate_skill_paths() {
  local stacks=("$@")
  local skill_paths=(
    # Core skills (ALWAYS)
    '${PLUGIN_ROOT}/skills/core/universal-patterns/SKILL.md'
    '${PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md'
    '${PLUGIN_ROOT}/skills/core/debugging-strategies/SKILL.md'
  )

  for stack in "${stacks[@]}"; do
    case "$stack" in
      react-typescript)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/frontend/react-typescript/SKILL.md'
          '${PLUGIN_ROOT}/skills/frontend/state-management/SKILL.md'
          '${PLUGIN_ROOT}/skills/frontend/testing-frontend/SKILL.md'
        )
        ;;
      vue-typescript)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/frontend/vue-typescript/SKILL.md'
          '${PLUGIN_ROOT}/skills/frontend/state-management/SKILL.md'
          '${PLUGIN_ROOT}/skills/frontend/testing-frontend/SKILL.md'
        )
        ;;
      golang)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/backend/golang/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/database-patterns/SKILL.md'
        )
        ;;
      dingo)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/backend/dingo/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/golang/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/database-patterns/SKILL.md'
        )
        ;;
      rust)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/backend/rust/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md'
        )
        ;;
      python)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/backend/python/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md'
        )
        ;;
      bunjs)
        skill_paths+=(
          '${PLUGIN_ROOT}/skills/backend/bunjs/SKILL.md'
          '${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md'
        )
        ;;
    esac
  done

  # Print unique paths
  printf '%s\n' "${skill_paths[@]}" | sort -u
}

CRITICAL: Always use ${PLUGIN_ROOT} placeholder, NOT hardcoded paths. This placeholder is expanded at runtime to the actual plugin directory.


Error Handling

No Stack Detected
yaml
error: "no_stack_detected"
trigger: "No config files found AND no recognizable directory structure"
recovery:
  1. Prompt user for manual stack selection
  2. Offer generic "unknown" stack with only core skills
  3. Save user choice to ${SESSION_PATH}/context.json
  4. Proceed with core skills only
Ambiguous Detection
yaml
error: "ambiguous_stack"
trigger: "Multiple possible interpretations"
recovery:
  1. Present all possibilities to user
  2. Ask for confirmation
  3. Save confirmed stack to context
Incomplete Detection
yaml
error: "incomplete_detection"
trigger: "Found some indicators but missing key files"
recovery:
  1. Report partial detection
  2. Load available skills
  3. Warn user about potential missing skills

Usage Examples

Example 1: React Frontend

Project Structure:

project/
├── package.json (with react: "^19.0.0")
├── src/
│   ├── routes/
│   └── components/
└── .tsx files

Detection Result:

json
{
  "detected_stack": "react-typescript",
  "mode": "frontend",
  "stacks": ["react-typescript"],
  "skill_paths": [
    "${PLUGIN_ROOT}/skills/core/universal-patterns/SKILL.md",
    "${PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md",
    "${PLUGIN_ROOT}/skills/frontend/react-typescript/SKILL.md",
    "${PLUGIN_ROOT}/skills/frontend/state-management/SKILL.md",
    "${PLUGIN_ROOT}/skills/frontend/testing-frontend/SKILL.md"
  ]
}
Example 2: Go Backend

Project Structure:

project/
├── go.mod
├── cmd/
│   └── server/
└── internal/

Detection Result:

json
{
  "detected_stack": "golang",
  "mode": "backend",
  "stacks": ["golang"],
  "skill_paths": [
    "${PLUGIN_ROOT}/skills/core/universal-patterns/SKILL.md",
    "${PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/golang/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/database-patterns/SKILL.md"
  ]
}
Example 3: Fullstack (React + Go)

Project Structure:

project/
├── frontend/
│   ├── package.json (with react)
│   └── src/
├── go.mod
├── cmd/
└── internal/

Detection Result:

json
{
  "detected_stack": "react-typescript + golang",
  "mode": "fullstack",
  "stacks": ["react-typescript", "golang"],
  "skill_paths": [
    "${PLUGIN_ROOT}/skills/core/universal-patterns/SKILL.md",
    "${PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md",
    "${PLUGIN_ROOT}/skills/frontend/react-typescript/SKILL.md",
    "${PLUGIN_ROOT}/skills/frontend/state-management/SKILL.md",
    "${PLUGIN_ROOT}/skills/frontend/testing-frontend/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/golang/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/database-patterns/SKILL.md"
  ],
  "quality_checks": {
    "frontend": ["cd frontend && bun run format", "..."],
    "backend": ["go fmt ./...", "..."]
  }
}
Example 4: Dingo Backend

Project Structure:

project/
├── go.mod
├── cmd/
│   └── api/
│       └── main.dingo
├── internal/
│   ├── handlers/
│   │   └── user.dingo
│   └── services/
│       └── user.dingo
└── .dingo/                  # Generated .go files (gitignored)

Detection Result:

json
{
  "detected_stack": "dingo + golang",
  "mode": "backend",
  "stacks": ["dingo", "golang"],
  "skill_paths": [
    "${PLUGIN_ROOT}/skills/core/universal-patterns/SKILL.md",
    "${PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/dingo/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/golang/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/api-design/SKILL.md",
    "${PLUGIN_ROOT}/skills/backend/database-patterns/SKILL.md"
  ],
  "quality_checks": {
    "backend": [
      "dingo fmt",
      "dingo go",
      "go vet ./.dingo/...",
      "golangci-lint run ./.dingo/...",
      "go test ./.dingo/..."
    ]
  }
}

Integration with Agents

stack-detector Agent

The stack-detector agent implements this skill:

  1. Reads this skill file for detection patterns
  2. Applies detection algorithm
  3. Generates skill paths using ${PLUGIN_ROOT}
  4. Writes result to ${SESSION_PATH}/context.json
  5. Returns summary to orchestrator
Orchestrator Commands

Commands read context.json and pass skill paths to implementation agents:

Task: universal-developer
Prompt: |
  SESSION_PATH: ${SESSION_PATH}

  Read these skills before implementing:
  - ${PLUGIN_ROOT}/skills/frontend/react-typescript/SKILL.md
  - ${PLUGIN_ROOT}/skills/frontend/testing-frontend/SKILL.md

  Then implement: Create user profile component
Implementation Agents

Agents use Read tool to load skill files:

1. Read skill file paths from prompt
2. Use Read tool to load each skill
3. Extract relevant patterns
4. Apply patterns during implementation

Version History

v1.0.0 (2026-01-05)
  • Initial release
  • Multi-stack detection support
  • Framework-specific patterns for React, Vue, Go, Rust, Python, Bun
  • Quality check mapping
  • Skill path generation with ${PLUGIN_ROOT}

© MadAppGang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in plugins/dev/skills/context-detection of MadAppGang/claude-code.

  • SKILL.md
  • scripts/discover-skills.js

Open the folder on GitHubat commit 6097ad4

Compare with similar skills

Context Detection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Context Detection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Context Detection this skillMadAppGang/claude-code285—~5.4kAutomated safety check: PassMIT
Web Artifacts Builderanthropics/skills180k41 repos~769Automated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
React Doctormakeplane/plane61k12 repos~657Automated safety check: PassAGPL-3.0
React Router Developmentremix-run/react-router57k1 repos~1.5kAutomated safety check: PassMIT
React UI State PatternsChrisWiles/claude-code-showcase6.1k8 repos~1.6kAutomated safety check: PassNone

Similar skills

  • Web Artifacts Builder

    anthropics/skills

    Official

    Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.

    180k GitHub starsUsed in 41 repos~769 tokens
    Frontend & DesignAuto-check passed
  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • React Doctor

    makeplane/plane

    Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it.

    61k GitHub starsUsed in 12 repos~657 tokens
    Frontend & DesignAuto-check passed
  • React Router Development

    remix-run/react-router

    Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.

    57k GitHub starsUsed in 1 repo~1.5k tokens
    Frontend & DesignAuto-check passed
  • React UI State Patterns

    ChrisWiles/claude-code-showcase

    Sets patterns for React interfaces: when to show loading spinners or skeletons, how to surface errors, how to disable buttons during async work and how to handle empty lists.

    6.1k GitHub starsUsed in 8 repos~1.6k tokens
    Frontend & DesignAuto-check passed
  • Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.

    33k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed

More from MadAppGang/claude-code

All 69 skills in this repo
  • Content Brief

    MadAppGang/claude-code

    Content brief template and creation methodology for SEO-optimized content.

    285 GitHub starsUsed in 1 repo~959 tokens
    Auto-check passed
  • Content Optimizer

    MadAppGang/claude-code

    On-page SEO optimization techniques including keyword density, meta tags, heading structure, and readability.

    285 GitHub starsUsed in 1 repo~694 tokens
    Auto-check passed
  • Keyword Cluster Builder

    MadAppGang/claude-code

    Techniques for expanding seed keywords and clustering by topic and intent.

    285 GitHub starsUsed in 1 repo~674 tokens
    Auto-check passed
  • Serp Analysis

    MadAppGang/claude-code

    SERP analysis techniques for intent classification, feature identification, and competitive intelligence.

    285 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Agent Coordination Discipline

    MadAppGang/claude-code

    A skill your agent uses when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents.

    285 GitHub stars~3.8k tokensUpdated 6 mo ago
    Auto-check passed
  • Agent Enforcement

    MadAppGang/claude-code

    Multi-agent orchestration enforcement for /team command. An agent skill from MadAppGang/claude-code.

    285 GitHub stars~895 tokensUpdated 6 mo ago
    Auto-check passed

Works with

Questions about Context Detection

What does Context Detection do?

A skill your agent uses when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g…. Context Detection is an agent skill from MadAppGang/claude-code., React + Go).

When should I use Context Detection?

Context Detection fits situations like: detecting project technology stack from files/configs/directory structure; auto-loading framework-specific skills; analyzing multi-stack fullstack projects (e.g.

How do I install Context Detection in Claude Code?

Run `npx skills add MadAppGang/claude-code --skill context-detection -a claude-code`. Or copy the skill folder (plugins/dev/skills/context-detection in MadAppGang/claude-code) into .claude/skills/context-detection in your project. Claude Code loads it when a task matches its description.

How do I install Context Detection in Codex?

Run `npx skills add MadAppGang/claude-code --skill context-detection -a codex`. Or copy the skill folder (plugins/dev/skills/context-detection in MadAppGang/claude-code) into .agents/skills/context-detection in your project. Codex loads it when a task matches its description.

Can I use Context Detection in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MadAppGang/claude-code --skill context-detection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/context-detection, .gemini/skills/context-detection, .github/skills/context-detection and .opencode/skills/context-detection in your project.

What does Context Detection need to run?

Going by SKILL.md and its folder, Context Detection needs JavaScript for the scripts in its folder and the command-line tools its instructions call (jq, node and python). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Bash(node *).

Does Context Detection access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Context Detection safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Context Detection use?

Context Detection is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Context Detection use?

About 5.4k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Context Detection?

Skills that share tags, products or a category with Context Detection: Web Artifacts Builder (anthropics/skills, 180k stars), Vercel Composition Patterns (supabase/supabase, 111k stars), React Doctor (makeplane/plane, 61k stars) and React Router Development (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Context Detection?

MadAppGang (a GitHub organization) maintains it in MadAppGang/claude-code, which has 285 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on March 15, 2026.

Source: MadAppGang/claude-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.