CFP submissions, talk preparation, and conference speaking strategies
Generates conference CFP submissions with titles, abstracts, outlines, and speaker bios.
/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/cfp-template.yamlreferences/CFP_GUIDE.mdscripts/cfp_generator.pyLand speaking opportunities and deliver memorable conference talks.
parameters:
required:
- submission_type: enum[cfp, abstract, bio, outline]
- talk_topic: string
optional:
- conference_name: string
- talk_length: enum[lightning, standard, keynote]
output:
cfp_submission:
title: string
abstract: string
outline: array[Section]
speaker_bio: string
Title: Catchy + Clear + Benefit
"How We Reduced API Latency by 90%"
Abstract: Problem → Solution → Takeaway
"APIs slowing you down? Learn the three
techniques we used to cut latency from
2s to 200ms. Walk away with actionable
patterns for your own services."
Outline: Show you've thought it through
1. The latency problem (5 min)
2. Technique 1: Caching (10 min)
3. Technique 2: Query optimization (10 min)
4. Technique 3: Edge computing (10 min)
5. Results and takeaways (5 min)
| Element | Why It Works |
|---|---|
| Specific results | "90% faster" vs "faster" |
| Clear takeaways | Audience knows what they'll learn |
| Novel angle | Fresh perspective |
| Speaker credibility | Show you've done this |
| Weeks Out | Task |
|---|---|
| 8 | Outline complete |
| 6 | First draft slides |
| 4 | Full run-through |
| 2 | Refinement + practice |
| 1 | Final polish |
| Day of | Tech check |
retry_patterns:
cfp_rejected:
strategy: "Request feedback, revise angle"
max_attempts: 3
low_acceptance_rate:
strategy: "Build portfolio at meetups first"
demo_fails:
strategy: "Pre-recorded backup"
| Failure Mode | Detection | Recovery |
|---|---|---|
| CFP rejection | Email received | Request feedback |
| Demo fails | Crashes on stage | Pre-recorded backup |
| Time runs over | 5-min warning | Skip to conclusion |
□ CFP deadline confirmed?
□ Abstract under word limit?
□ Slides tested on 1080p?
□ Demo backed up?
□ Talk rehearsed 3+ times?
□ Travel confirmed?
test_conference_speaking:
unit_tests:
- test_cfp_elements:
assert: "Title, abstract, outline present"
- test_abstract_length:
assert: "150-300 words"
integration_tests:
- test_talk_delivery:
assert: "Within time limit"
| Metric | Target |
|---|---|
| CFP acceptance rate | >20% |
| Talk rating | >4/5 |
| Repeat invitations | 1+ |
metrics:
- cfps_submitted: integer
- cfps_accepted: integer
- talks_delivered: integer
- average_rating: float
See assets/ for CFP 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.