ce-demo-reel
Demo Reel
Detect project type, recommend a capture tier, record visual evidence, upload to a public URL, and return markdown for PR inclusion.
Evidence means USING THE PRODUCT, not running tests. "I ran npm test" is test evidence. Evidence capture is running the actual CLI command, opening the web app, making the API call, or triggering the feature. The distinction is absolute -- test output is never labeled "Demo" or "Screenshots."
If real product usage is impractical (requires API keys, cloud deploy, paid services, bot tokens), say so explicitly: "Real evidence would require [X]. Recommending [fallback approach] instead." Do not silently skip to "no evidence needed" or substitute test output.
Never generate fake or placeholder image/GIF URLs. If upload fails, report the failure.
Never Record Secrets
Recordings must never contain credentials — not in commands, output, URL bars, or on-screen UI. If the demo needs a credential, set it before the recording starts, outside the recorded region.
Core principle: secrets should affect the environment, not the visible transcript. Hidden real setup beats visible fake setup — fake setup breaks the demo and still leaks the secret's shape.
- Plan it out of frame. Route every surface where a secret could appear (env exports, CLI flag values, command output, auth headers, URL params, DevTools, config pages) out of the recorded region. Use VHS
Hide/Show; invoke CLIs via env vars, not secret flag values; stay on user-facing pages. Show the authenticated result, not the auth step. - Do not substitute placeholders inside the recording. Typing a fake
sk-xxxxxproduces a misleading artifact; recapture with the real credential set out of frame instead. Two specific failures:- Re-exporting a fake value visibly (
export API_KEY=REDACTED) overwrites the real env var, so the demo breaks (401,Unauthorized,0 credits remaining, empty output). You leak the variable name and ship a broken product.
- Re-exporting a fake value visibly (
More from everyinc/compound-engineering-plugin
compound-docs
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
1.5Kcoding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
929dhh-rails-style
This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.
702frontend-design
Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.
622git-worktree
This skill manages Git worktrees for isolated parallel development. It handles creating, listing, switching, and cleaning up worktrees with a simple interactive interface, following KISS principles.
622gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
622