菜单
Recommends movies and TV shows to watch on streaming services. Gives 3-5 curated picks based on genre, mood, format, and streaming platform. Use when the user asks what to watch, wants streaming recommendations, or needs help picking a movie or show.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when a plan, spec, design doc, brainstorm, or walkthrough needs review before anyone implements it — especially when it may be over-engineered, over-abstracted, or scoped past a lean MVP. Triggers include "review this plan", "is this over-engineered", "is this too much for an MVP", "sanity check this design", "trim this spec", and handoff moments before writing-plans, superplan, or superbuild.
Use when a design, spec, or brainstorm needs to leave this thread — to be reviewed by another agent, to feed adversarial-review, or to catch up / hand off the work to a brand-new thread or a different AI. Triggers: "review packet", "context dump", "second opinion", "paste into ChatGPT/Codex/Gemini", "hand this off", "catch up a new thread", "continue this in another agent", "I'm running out of context".
Use when turning a repo, pull request, plan/design doc, architecture, article, blog post, book, lecture, or transcript into an interactive learning artifact — a self-contained offline walkthrough.html and/or a deployable learning hub. Triggers include "onboarding guide", "walk me through this PR/codebase/design", "interactive explainer", "teaching site", "publish docs to GitHub Pages".
Use when a plan has been built with superbuild or autobuild and you need to validate that every feature was implemented correctly, wired properly, and actually works end-to-end. Use after superbuild or autobuild completes, or when the user wants proof the build matches the plan.
Use when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if complete) or via codebase scan.
Transforms technical documents into rigorous learning journeys with collegiate-level mastery requirements. Uses Bloom's taxonomy progression, 80%+ mastery thresholds, and multi-level verification before advancing. Treats learning as a high school to college graduation progression. Use when user wants deep understanding, not surface familiarity.
| name | streaming-recommendations |
| description | Recommends movies and TV shows to watch on streaming services. Gives 3-5 curated picks based on genre, mood, format, and streaming platform. Use when the user asks what to watch, wants streaming recommendations, or needs help picking a movie or show. |
| metadata | {"version":"1.0","author":"adamcobb","tags":["entertainment","streaming","recommendations"]} |
Recommend 3-5 movies or TV shows to watch on streaming services, tailored to the user's genre, mood, format preference, and available platforms.
Extract any preferences the user already provided. Look for these four dimensions:
| Dimension | Examples |
|---|---|
| Format | Movie, TV show, or either |
| Genre | Action, comedy, sci-fi, drama, horror, thriller, documentary, animation, romance, fantasy, mystery, crime |
| Streaming service | Netflix, Hulu, Disney+, HBO Max, Prime Video, Apple TV+, Peacock, Paramount+, Tubi, or "any" |
| Mood / vibe | Light & fun, intense & gripping, thought-provoking, heartwarming, dark & gritty, nostalgic, suspenseful |
If any of the four dimensions are missing, ask one multiple-choice question at a time in this priority order. Skip any dimension already provided:
Format — "Are you in the mood for a movie or a TV show?"
Genre — "What genre sounds good?"
Streaming service — "Which service are you watching on?"
Mood — "What vibe are you going for?"
If the user provides all four upfront (e.g., "recommend a funny movie on Netflix, something light"), skip straight to Step 3.
"Surprise me" on genre or mood means pick freely — lean toward highly-rated or trending picks.
Always use web search to find current recommendations. Streaming catalogs change constantly — never rely solely on training data.
Build search queries combining the user's filters:
"best light comedy movies on Netflix 2026""top intense sci-fi TV shows on HBO Max 2026"Search 2-3 queries to cross-reference availability and find quality picks. Prioritize:
Return 3-5 recommendations using this format for each:
### {emoji} Title (Year)
**Genre:** Genre1, Genre2 | **Rating:** Score (Source)
**Streaming on:** Service Name
Synopsis in 2-3 sentences. Spoiler-free. Written to sell the vibe, not just
summarize the plot. Make it compelling.
**Why you'll like it:** One sentence connecting this pick back to the user's
stated mood and preferences.
Formatting rules:
🎬 for movies, 📺 for TV showsYou asked for: An intense sci-fi TV show on Netflix
📺 3 Body Problem (2024)
Genre: Sci-Fi, Mystery | Rating: 7.7 IMDb Streaming on: Netflix
A mystery that spans decades and continents as a group of brilliant scientists confront the greatest threat in humanity's history. The stakes escalate relentlessly, blending real physics with jaw-dropping sci-fi concepts.
Why you'll like it: You wanted intense and gripping — this one doesn't let you breathe from the first episode.
📺 Silo (2023)
Genre: Sci-Fi, Drama | Rating: 8.0 IMDb Streaming on: Apple TV+
In a ruined and toxic future, thousands live in a giant underground silo. When the sheriff investigates what's outside, she uncovers shocking truths that could destroy the community.
Why you'll like it: Slow-burn intensity that builds and builds — perfect for that edge-of-your-seat craving.