Delegate independent tasks to specialized agents working concurrently with isolated context.
C3 Config
c3-config
Use when configuring project preferences in .c3/settings.yaml - diagram tools, layer guidance, guardrails, and handoff steps
SKILL.md
Full skill instructions
C3 Config
Overview
Create and refine .c3/settings.yaml for project-specific preferences through Socratic questioning.
Announce at start: "I'm using the c3-config skill to configure project settings."
Quick Reference
| Section | Purpose |
|---|---|
diagrams: | Diagram tool and usage patterns (global) |
context: | Context layer configuration |
container: | Container layer configuration |
component: | Component layer configuration |
guard: | Team guardrails and constraints |
adr: | ADR and Implementation Plan settings |
handoff: | Post-design handoff steps |
audit: | Audit findings handoff preference |
Settings Structure
diagrams: |
mermaid
sequence: API interactions, request flows
flowchart: decision logic, error handling
context:
useDefaults: true
guidance: |
your context guidance
include: |
additional items to include
exclude: |
items to exclude
litmus: |
custom litmus test (optional)
diagrams: |
custom diagram guidance (optional)
container:
useDefaults: true
guidance: |
your container guidance
# Same keys as context
component:
useDefaults: true
guidance: |
your component guidance
# Same keys as context
guard: |
discovered incrementally
adr:
requirePlan: true
coherenceCheck: true
planGranularity: detailed # detailed | summary
handoff: |
after ADR accepted:
1. create implementation tasks
2. notify team
target: vibe_kanban # or: linear, jira, github, manual
audit: |
handoff: tasks # tasks | manual | agents
For merge logic details, see references/settings-merge.md.
Socratic Refinement
Refine sections through targeted questions:
Diagrams:
- "What diagramming tool does your team use?"
- "What types of diagrams are most useful?"
Layer Configuration (Context/Container/Component):
- "Use default include/exclude rules, or customize?"
- "Items that should ALWAYS be at this layer?"
- "Items that should NEVER be at this layer?"
Guardrails:
- "Architectural decisions that should never be revisited?"
- "Technologies or patterns that are off-limits?"
ADR Settings:
- "Should Implementation Plan be required?" (default: yes)
- "Verify ADR-Plan coherence before handoff?" (default: yes)
- "Code Changes granularity?" (detailed: file:function, summary: file-only)
Handoff:
- "What happens after an ADR is accepted?"
- "How should tasks be tracked?" (GitHub, Jira, Linear, vibe_kanban, etc.)
Audit:
- "How should audit findings be handled?" (manual, tasks, agents)
Process
1. Check Existing Settings
ls .c3/settings.yaml 2>/dev/null && echo "EXISTS" || echo "MISSING"
- EXISTS: Load and show current settings
- MISSING: Create with defaults
2. Initialize or Load
If missing, create with sensible defaults. If exists, load and ask: "Which section would you like to refine?"
3. Socratic Refinement
Focus on gaps, one section at a time. User can skip any section.
4. Write Settings
Save to .c3/settings.yaml and verify sections exist.
Invocation Contexts
| Context | Behavior |
|---|---|
| Standalone | Full Socratic refinement of all sections |
| Via c3-adopt | Create defaults, offer refinement |
Key Principles
- Sensible defaults - Works out-of-box, customization optional
- Incremental discovery - Guardrails grow over time
- Flexible format - YAML with prose values
- User-editable - Human-readable/editable
- Non-blocking - Missing settings doesn't break other skills
Checklist
- Checked for existing
.c3/settings.yaml - Initialized or loaded current settings
- Each section reviewed via Socratic questions
- Handoff steps configured
- Settings file saved and verified
Related
references/settings-merge.md- Merge logic detailsc3-adopt- Calls c3-config during initializationc3-design- Reads settings at start
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
