Agent skill
btr-curate
Add context to LOCAL BTR tree (NOT ByteRover/brv). Use `btr` CLI or `mcp__btr__*` MCP tools. Add or update context in the BTR tree with AI-powered metadata extraction. Use when the user wants to "add to context tree", "store this in BTR", "curate to BTR", or needs to organize knowledge with intelligent tagging.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/btr-curate
SKILL.md
BTR Curate
⚠️ CRITICAL: BTR ≠ ByteRover
This skill uses btr (local context tree), NOT brv (ByteRover CLI).
| Command | Tool | Syntax |
|---|---|---|
| ✓ CORRECT | btr |
btr curate <domain> <topic> --content "..." |
| ✗ WRONG | brv |
Different tool, different syntax, requires auth |
PREFER MCP tools when available:
mcp__btr__curate_context- Structured, type-safemcp__btr__query_context- Validated search
Only use Bash btr commands if MCP tools are unavailable.
Add or update context with intelligent metadata extraction.
Preferred Method
-
FIRST: Use MCP tools if available
mcp__btr__curate_context(domain="auth", topic="jwt-flow", content="...", tags=["security"]) -
FALLBACK: Use
btrCLI via Bashbashbtr curate auth jwt-flow --content "..." --tags security -
NEVER: Use
brv(different product entirely)
Quick Start
btr curate <domain> <topic> --content "<content>" [--tags tag1,tag2]
Instructions
- Analyze the content to curate
- Suggest appropriate domain and topic
- Auto-extract relevant tags from content
- Generate a brief summary
- Run the CLI command
- Confirm successful curation
Auto-Tagging Guidelines
Extract tags based on:
- Technology names (react, typescript, postgresql)
- Patterns (singleton, middleware, decorator)
- Concepts (authentication, caching, validation)
- Categories (security, performance, best-practice)
Interactive Mode
For complex content, use interactive mode:
btr curate --interactive
This walks through domain selection, topic naming, and tag extraction step by step.
Domain Selection Guide
| Content Type | Suggested Domain |
|---|---|
| Login, tokens, sessions | auth |
| REST endpoints, GraphQL | api |
| SQL, ORM, migrations | database |
| Components, hooks, CSS | frontend |
| Unit tests, integration tests | testing |
| CI/CD, containers, monitoring | devops |
| Design decisions, patterns | architecture |
| Security rules, validation | security |
| Performance tuning | performance |
Topic Naming Conventions
Use kebab-case with descriptive names:
Good:
jwt-refresh-token-flowpostgres-connection-pool-configreact-form-validation-hook
Avoid:
jwt(too generic)myStuff(not descriptive)temp_notes(not permanent-sounding)
Updating Existing Context
To update an existing topic:
btr curate auth jwt-validation --content "..." --update
The --update flag merges new content with existing content.
Content Guidelines
When curating content, include:
- The What: Actual code or configuration
- The Why: Reason for this approach
- The When: When to use this pattern
- Usage Examples: How to apply it
- Caveats: Any gotchas or limitations
Example Curation Flow
User provides a code snippet for database connection pooling.
- Analyze content: PostgreSQL connection pool configuration
- Suggest domain:
database - Suggest topic:
postgres-connection-pooling - Extract tags:
postgresql,connection-pool,performance,configuration - Execute:
bash
btr curate database postgres-connection-pooling \ --content "..." \ --tags postgresql,connection-pool,performance,configuration - Confirm: "Curated to database/postgres-connection-pooling with 4 tags"
For metadata extraction scripts, see scripts/extract-metadata.py.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?