sync-context
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.zipInstalls 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.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
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
- Analyzes current codebase structure
- Extracts patterns, conventions, and architecture
- Merges with existing copilot-instructions.md content
- Preserves manual customizations
- 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}
| Stage | Technology | Purpose |
|---|---|---|
| {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
| Category | Agents | Use When |
|---|---|---|
| Workflow | brainstorm-agent, define-agent, ... | Building features with SDD |
| Code Quality | python-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
| Pattern | Usage | Example File |
|---|---|---|
| {pattern} | {where used} | {file path} |
Commands
{Auto-generated from commands/ folder}
| Command | Purpose |
|---|---|
| /build-feature | Full SDD pipeline |
| /memory | Save session insights |
| {command} | {purpose} |
Environment Variables
{Auto-generated from .env.example, config files}
| Variable | Purpose |
|---|---|
| {var} | {purpose} |
MCP Tools Available
{Auto-generated from settings}
| MCP Server | Purpose |
|---|---|
| context7-mcp | Library documentation |
| exa | Code 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
| Flag | Description |
|---|---|
--dry-run | Preview changes without saving |
--section {name} | Update only specific section |
--force | Replace all sections (ignores preserve rules) |
--verbose | Show 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:
- Project Context - Add business context
- Important Dates - Add milestone dates
- Architecture - Add business-specific details
- 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
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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| sync-context (this skill) | 0 | 3mo | Review | Intermediate |
| notion-knowledge-capture | 10 | 9mo | No flags | Intermediate |
| feishu-doc | 14 | 5mo | No flags | Intermediate |
| openspec-continue-change | 4 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
notion-knowledge-capture
makenotion
Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.
feishu-doc
openclaw
Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.
openspec-continue-change
studyzy
通过创建下一个产出物继续处理 OpenSpec 变更。当用户想要推进其变更、创建下一个产出物或继续其工作流程时使用。
kimi-cli-help
MoonshotAI
Answer Kimi Code CLI usage, configuration, and troubleshooting questions. Use when user asks about Kimi Code CLI installation, setup, configuration, slash commands, keyboard shortcuts, MCP integration, providers, environment variables, how something works internally, or any questions about Kimi Code CLI itself.
openspec-archive-change
studyzy
归档实验性工作流中已完成的变更。当用户想要在实现完成后最终确定并归档变更时使用。
feishu-perm
m1heng
Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.