feat(skills/ai-research): add recsys-pipeline-architect

[mturac]

Adds a new skill under cli-tool/components/skills/ai-research/:

recsys-pipeline-architect

A skill for designing composable recommendation, ranking, and feed pipelines using the six-stage Source → Hydrator → Filter → Scorer → Selector → SideEffect framework popularized by xAI's open-sourced For You algorithm (Apache 2.0; this skill is MIT and is an independent reimplementation of the pattern).

When invoked, the skill walks the agent through eight clarifying steps (use case → sources → hydrations → filters → scorers → selector → side effects → scaffold), surfaces the architectural trade-offs (multi-action vs single-score, candidate isolation vs joint scoring, online vs offline batch) explicitly, and emits a runnable scaffold in the user's stack.

Activation triggers

Building any system that returns top K items for a (user, context). Examples: content feeds, search ranking, RAG retrieval rerankers, task prioritizers, notification triage, ad selection.

What's covered

• The 6-stage framework with rationale for the ordering
• 8-step invocation workflow
• 3 architectural trade-offs surfaced explicitly
• 7 hard rules (attribution discipline, no fabricated benchmarks, no brand misuse, etc.)
• 5 anti-patterns
• 4 concrete example invocations

PR contents

• Adds one file: cli-tool/components/skills/ai-research/recsys-pipeline-architect/SKILL.md
• Follows the existing frontmatter pattern (name, description, allowed-tools) like sibling skills (e.g., parallel-agents, ai-agents-architect)

Upstream

Single-file adapter for the upstream repository: https://github.com/mturac/recsys-pipeline-architect (v0.1.0, MIT). Upstream ships 5 load-on-demand reference docs and 3 runnable example scaffolds (Strapi v5/TS/Jest, Go with generics, Python/FastAPI/pytest — every one green: 9/9 tests passing total).

Happy to move to a different category (e.g., development), shorten content, or revise frontmatter.

---

Summary by cubic

Adds the recsys-pipeline-architect skill to design composable recommendation/ranking pipelines with a six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect pattern, and generate runnable scaffolds. Expands the skills library for top‑K feeds, search rerankers, and similar use cases.

• New Features
  • Adds cli-tool/components/skills/ai-research/recsys-pipeline-architect/SKILL.md to design and scaffold recommender/ranking pipelines.
  • Area: components (cli-tool/components/); no changes to CLI, API, website, or workers.
  • New component added; regenerate catalog (docs/components.json).
  • No new environment variables or secrets.

^{Written for commit 8c7b69e. Summary will update on new commits. Review in cubic}

[vercel]

@mturac is attempting to deploy a commit to the Daniel Avila's projects Team on Vercel.

A member of the Team first needs to authorize it.

[github-actions]

👋 Thanks for contributing, @mturac!

This PR touches cli-tool/components/** and has been marked review-pending.

What happens next

1. 🤖 Automated security audit runs and posts results on this PR.
2. 👀 Maintainer review — a human reviewer validates the component with the component-reviewer agent (format, naming, security, clarity).
3. ✅ Merge — once approved, your PR is merged to main.
4. 📦 Catalog regeneration — the component catalog is rebuilt automatically.
5. 🚀 Live on aitmpl.com — your component appears on the website after deploy.

While you wait

• Check the Security Audit comment below for any issues to fix.
• Make sure your component follows the contribution guide.

This is an automated message. No action is required from you right now — a maintainer will review soon.

[cubic-dev-ai]

No issues found across 1 file

_{Re-trigger cubic}