Synchronizes project-specific instructions and patterns to improve AI assistant effectiveness.

Install

mkdir -p .claude/skills/sync-context && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10554" && unzip -o skill.zip -d .claude/skills/sync-context && rm skill.zip

Installs to .claude/skills/sync-context

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Sync project context to copilot-instructions.md by analyzing codebase patterns and conventions. Use after adding agents, commands, or significant architecture changes.
167 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Analyze codebase structure
  • Extract architecture patterns
  • Merge findings into instructions
  • Preserve manual customizations

How it works

Scans the codebase using glob patterns and grep to identify architecture and agent definitions, merging them into documentation.

Inputs & outputs

You give it
Project codebase
You get back
Updated .github/copilot-instructions.md

When to use sync-context

  • Refresh copilot-instructions.md after architecture changes
  • Identify and document code patterns
  • Sync agent definitions to project context
  • Preview instruction updates via dry-run

About this skill

Sync Context Command

Analyzes codebase and intelligently updates .github/copilot-instructions.md with current project context.

Usage

/sync-context                    # Full analysis and update
/sync-context --section agents   # Update specific section
/sync-context --dry-run          # Preview changes without saving

What It Does

  1. Analyzes current codebase structure
  2. Extracts patterns, conventions, and architecture
  3. Merges with existing copilot-instructions.md content
  4. Preserves manual customizations
  5. Updates sections that need refresh

Analysis Process

Step 1: Scan Codebase Structure

# Discover project structure
Glob("**/*.py")              # Python files
Glob("**/*.ts")              # TypeScript files
Glob("**/package.json")      # Node projects
Glob("**/pyproject.toml")    # Python projects
Glob("**/Dockerfile")        # Container configs
Glob("**/*.tf")              # Terraform

Step 2: Extract Patterns

# Code patterns
Grep("@dataclass")           # Dataclass usage
Grep("class.*Parser")        # Parser patterns
Grep("def test_")            # Test patterns
Grep("async def")            # Async patterns

# Architecture patterns
Grep("from src")             # Import structure
Grep("@router")              # API patterns
Grep("@lambda_handler")      # Lambda patterns

Step 3: Analyze Agents

# List available agents
Glob(".github/agents/*.agent.md")

# Categorize by name prefix
- workflow-*    → SDD pipeline agents (brainstorm, define, design, build, ship, iterate)
- architect-*   → System design (schema, pipeline, lakehouse, genai, the-planner)
- cloud-*       → AWS, GCP, CI/CD, deployment agents
- fabric-*      → Microsoft Fabric specialists
- python-*      → Code review, clean, document, prompt engineering
- test-*        → Testing, data quality, data contracts
- de-*          → Data engineering: Spark, dbt, Airflow, Lakeflow, streaming, SQL
- dev-*         → Codebase explorer, meeting analyst, prompt crafter

Step 4: Merge Updates

# Sections to update
- Project Structure (from scan)
- Coding Standards (from patterns)
- Agent Usage (from agent analysis)
- Commands (from commands/)
- Environment (from config files)

# Sections to preserve
- Project Context (manual)
- Core Mission (manual)
- Important Dates (manual)
- Getting Help (manual)

copilot-instructions.md Template

Generated .github/copilot-instructions.md follows this structure:

# {Project Name}

## Project Context

{Manual: What this project does and why}

---

## Architecture Overview

{Auto-generated from codebase scan}

```text
{Data flow diagram}
StageTechnologyPurpose
{stage}{tech}{purpose}

Project Structure

{Auto-generated from Glob scans}

{project}/
├── src/
│   ├── {folders discovered}
├── tests/
├── .github/
│   ├── agents/
│   ├── kb/
│   ├── sdd/
│   ├── skills/
│   └── storage/

Agent Usage Guidelines

{Auto-generated from agents/ folder}

Available Agents by Category

CategoryAgentsUse When
Workflowbrainstorm-agent, define-agent, ...Building features with SDD
Code Qualitypython-code-reviewer, test-generator, ...Improving code
{category}{agents}{trigger}

Coding Standards

{Auto-generated from detected patterns}

Language: {Python/TypeScript/etc}

  • Version: {detected from config}
  • Style: {detected patterns}
  • Testing: {detected framework}

Detected Patterns

PatternUsageExample File
{pattern}{where used}{file path}

Commands

{Auto-generated from commands/ folder}

CommandPurpose
/build-featureFull SDD pipeline
/memorySave session insights
{command}{purpose}

Environment Variables

{Auto-generated from .env.example, config files}

VariablePurpose
{var}{purpose}

MCP Tools Available

{Auto-generated from settings}

MCP ServerPurpose
context7-mcpLibrary documentation
exaCode context search
{mcp}{purpose}

Important Dates

{Manual: Project-specific dates}


Getting Help

{Auto-generated from structure}

  • Documentation: Start with relevant docs
  • Agents: Review .github/agents/
  • Commands: Use /help for available commands

---

## Section Update Rules

| Section | Source | Update Mode |
| ------- | ------ | ----------- |
| Project Context | Manual | Preserve |
| Architecture | Codebase scan | Replace |
| Project Structure | Glob patterns | Replace |
| Agent Usage | agents/ folder | Replace |
| Coding Standards | Pattern detection | Merge |
| Commands | commands/ folder | Replace |
| Environment | Config files | Merge |
| MCP Tools | settings.json | Replace |
| Important Dates | Manual | Preserve |
| Getting Help | Structure | Replace |

**Replace**: Fully regenerate from source
**Merge**: Add new, preserve custom
**Preserve**: Never auto-modify

---

## Execution Flow

```text
1. Read existing .github/copilot-instructions.md
   │
   ▼
2. Parse into sections
   │
   ▼
3. Analyze codebase (parallel)
   ├── Glob for structure
   ├── Grep for patterns
   ├── Read config files
   └── List agents/commands
   │
   ▼
4. Generate new sections
   │
   ▼
5. Apply update rules
   ├── Replace auto sections
   ├── Merge semi-auto sections
   └── Preserve manual sections
   │
   ▼
6. Validate (dry-run or save)
   │
   ▼
7. Write updated .github/copilot-instructions.md

Example Output

UPDATE .github/copilot-instructions.md
━━━━━━━━━━━━━━━━

Analyzing codebase...
✓ Found 47 Python files
✓ Found 12 test files
✓ Found 28 agents
✓ Found 8 commands

Detected patterns:
✓ Dataclass pattern (15 usages)
✓ Parser pattern (4 files)
✓ Generator pattern (8 usages)

Section updates:
• Architecture: UPDATED (new components detected)
• Project Structure: UPDATED (3 new folders)
• Agent Usage: UPDATED (2 new agents)
• Coding Standards: MERGED (1 new pattern)
• Commands: UPDATED (1 new command)
• Project Context: PRESERVED (manual content)

━━━━━━━━━━━━━━━━
.github/copilot-instructions.md updated successfully

Flags

FlagDescription
--dry-runPreview changes without saving
--section {name}Update only specific section
--forceReplace all sections (ignores preserve rules)
--verboseShow detailed analysis

Best Practices

When to Run

  • After adding new agents or commands
  • After significant architecture changes
  • After adding new file types
  • When onboarding new team members

What to Customize

After running, manually update:

  1. Project Context - Add business context
  2. Important Dates - Add milestone dates
  3. Architecture - Add business-specific details
  4. Coding Standards - Add team conventions

Version Control

# Review changes before committing
git diff .github/copilot-instructions.md

# Commit with context
git add .github/copilot-instructions.md
git commit -m "chore: update copilot-instructions.md with latest project structure"

When not to use it

  • When architecture is unstable
  • During initial project setup

Prerequisites

Existing copilot-instructions.md

Limitations

  • Requires manual updates for project context and dates

How it compares

Intelligently updates documentation while preserving manual sections, unlike manual documentation maintenance.

Compared to similar skills

sync-context side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
sync-context (this skill)03moReviewIntermediate
notion-knowledge-capture109moNo flagsIntermediate
feishu-doc145moNo flagsIntermediate
openspec-continue-change46moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry