create-blueprint
Research a specific system and create or update its blueprints/ documentation
What this skill does
## Name
blueprints:create-blueprint - Generate or update blueprint documentation for a specific system
## Synopsis
```text
/blueprint <system-name>
```
## Description
Research a specific system in the codebase and create or update its technical blueprint documentation in the `blueprints/` directory at the **repository root**.
## Important: Blueprint Location
**CRITICAL:** Blueprints MUST be created at the repository root, never in subdirectories or packages.
- `{repo-root}/blueprints/{system-name}.md`
- `{repo-root}/packages/foo/blueprints/{system-name}.md`
- `{repo-root}/src/blueprints/{system-name}.md`
Blueprints are repository-wide system design documents. A single system may span multiple packages or directories, but there should be ONE blueprint at the repo root describing the entire system.
## Implementation
You are tasked with creating or updating technical blueprint documentation for a specific system.
## Process
### 1. Identify the Target System
The user will specify which system to document. This could be:
- A feature name (e.g., "authentication", "caching")
- A directory path (e.g., "lib/commands/mcp")
- A component name (e.g., "MCP server", "hook dispatcher")
### 2. Deep Research Phase
Thoroughly investigate the system:
1. **Find all relevant files** using Glob and Grep
2. **Read the implementation** to understand:
- Entry points and public APIs
- Internal architecture and data flow
- Dependencies and integrations
- Configuration options
- Error handling and edge cases
3. **Check for existing documentation**:
- README files in the directory
- Inline code comments
- Existing blueprints/ files
- Test files (they document expected behavior)
### 3. Check for Duplicates
Before creating a new blueprint, check what already exists:
1. **List all blueprints**: Use `Glob("blueprints/*.md")` to see all existing blueprint files
2. **Search by keyword**: Use `Grep` to search frontmatter in `blueprints/` for related topics
3. **Read related blueprints**: Use `Read("blueprints/{related-name}.md")` to check for overlap
4. **Identify overlapping systems** that should be documented together
### 4. Write the Blueprint
Use the `Write` tool to create or update the blueprint file at `blueprints/{system-name}.md`.
The file MUST include YAML frontmatter:
```markdown
---
name: system-name
summary: Brief one-line description
---
# {System Name}
...
```
The blueprint content should follow this structure:
```markdown
---
name: system-name
summary: Brief one-line description
---
# {System Name}
{Brief one-line description}
## Overview
{2-3 paragraphs explaining the system's purpose, why it exists, and its role in the larger system}
## Architecture
{Describe the system structure}
### Components
- **{Component A}** - {description}
- **{Component B}** - {description}
### Data Flow
{How data moves through the system}
### Dependencies
- {Dependency 1} - {why it's needed}
- {Dependency 2} - {why it's needed}
## API / Interface
### Public Functions/Methods
#### `functionName(params)`
{Description}
**Parameters:**
- `param1` (type) - {description}
**Returns:** {description}
### Commands
{If applicable, document CLI commands}
### Configuration
{Document configuration options}
## Behavior
### Normal Operation
{How the system behaves under normal conditions}
### Error Handling
{How errors are handled}
### Edge Cases
{Notable edge cases and how they're handled}
## Files
Key implementation files:
- `path/to/main.ts` - {brief description}
- `path/to/helper.ts` - {brief description}
## Related Systems
- [{Related System}](./related-system.md) - {relationship description}
```
## Output
After completing the research and documentation:
1. Create/update the blueprint using `Write("blueprints/{system-name}.md", content)`
2. Report what was documented and any related systems that may need documentation
**Note:** The blueprint index at `.claude/rules/blueprints/blueprints-index.md` is automatically regenerated by the SessionStart hook - you don't need to manually update it.
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.