Developer support systems including forums, office hours, and FAQ management
Routes developer questions to the right support channel (forums, office hours, tickets) based on urgency and type. Automatically escalates unresolved issues and creates FAQs from recurring problems.
/plugin marketplace add pluginagentmarketplace/custom-plugin-devrel-engineer/plugin install devrel-engineer-plugin@pluginagentmarketplace-devrel-engineerThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/support-templates.yamlreferences/SUPPORT_GUIDE.mdscripts/support_analyzer.pyBuild effective support systems that help developers succeed and scale.
parameters:
required:
- support_type: enum[question, bug, feature, escalation]
- context: string
optional:
- urgency: enum[low, medium, high, critical]
- channel: enum[forum, discord, ticket, office_hours]
output:
response:
answer: string
resources: array[Link]
follow_up: array[Action]
| Channel | Response Time | Best For |
|---|---|---|
| Docs/FAQ | Instant | Self-service |
| Forum/Discord | 4-24 hours | Community Q&A |
| Office Hours | Scheduled | Complex issues |
| Support Tickets | 24-48 hours | Bugs/urgent |
Tier 0: Self-Service
├── Documentation
├── FAQ
├── Knowledge Base
└── Search
Tier 1: Community
├── Forums
├── Discord/Slack
└── Stack Overflow
Tier 2: DevRel Team
├── Office Hours
├── Direct Outreach
└── Webinars
Tier 3: Engineering
├── Bug Reports
├── Feature Requests
└── Architecture Reviews
Q: How do I authenticate with the API?
A: You can authenticate using API keys or OAuth 2.0:
**API Keys** (simplest)
curl -H "Authorization: Bearer YOUR_API_KEY" ...
**OAuth 2.0** (for user data)
[See our OAuth guide →](/docs/oauth)
Related: [Authentication errors](/docs/errors#auth)
retry_patterns:
unresolved_question:
strategy: "Escalate to specialist"
user_frustrated:
strategy: "Personal outreach, expedite"
recurring_issue:
strategy: "Create FAQ, update docs"
| Failure Mode | Detection | Recovery |
|---|---|---|
| Slow response | >24h wait | Prioritize, apologize |
| Wrong answer | User correction | Fix, thank user |
| No resolution | Multiple back-forth | Escalate |
□ Problem clearly understood?
□ Docs checked first?
□ Similar issues in history?
□ Reproducible steps?
□ Workaround available?
□ Escalation path clear?
test_developer_support:
unit_tests:
- test_response_time:
assert: "<24h for community"
- test_answer_accuracy:
assert: "Solves problem"
integration_tests:
- test_escalation_flow:
assert: "Reaches specialist"
| Metric | Target |
|---|---|
| Response time | <24 hours |
| Resolution rate | >80% |
| CSAT score | >4.0/5 |
| Ticket deflection | >60% |
metrics:
- tickets_resolved: integer
- response_time_avg: duration
- csat_score: float
- deflection_rate: float
See assets/ for support templates.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.