opencode-skills-collection 3.0.16 → 3.0.18

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-05-16T01:50:15.647Z",
+  "updatedAt": "2026-05-18T02:03:30.579Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -1082,6 +1082,7 @@
     "readme",
     "recallmax",
     "receiving-code-review",
+    "recsys-pipeline-architect",
     "recursive-context-pruning-token-budgeting",
     "red-team-tactics",
     "red-team-tools",

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,459+ skills."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,460+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 1,459+ skills
+# Jetski/Cortex + Gemini: safe integration with 1,460+ skills
 
 This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.
 
@@ -23,7 +23,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.
 
-With 1,459+ skills, this approach fills the context window before user messages are even added, causing truncation.
+With 1,460+ skills, this approach fills the context window before user messages are even added, causing truncation.
 
 ---
 
@@ -31,14 +31,16 @@ With 1,459+ skills, this approach fills the context window before user messages
 
 Core principles:
 
-- **Light manifest**: use `data/skills_index.json` to know *which* skills exist without loading full text.
+- **Stable manifest**: use the canonical root `skills_index.json` to know *which* skills exist without loading full text.
+- **Compatibility mirror**: treat `data/skills_index.json` as an exact mirror of the canonical manifest.
 - **Lazy loading**: read `SKILL.md` **only** for skills actually invoked in a conversation (for example, when `@skill-id` appears).
 - **Explicit limits**: enforce a maximum number of skills/tokens loaded per turn, with clear fallbacks.
 - **Path safety**: verify manifest paths remain inside `SKILLS_ROOT` before reading `SKILL.md`.
+- **Schema contract**: validate manifest entries against [`schemas/skills-index.v1.schema.json`](../../schemas/skills-index.v1.schema.json).
 
 The recommended flow is:
 
-1. **Bootstrap**: on agent startup, read `data/skills_index.json` and build an `id -> meta` map.
+1. **Bootstrap**: on agent startup, read `skills_index.json` (and `data/skills_index.json` if your host expects compatibility reads) and build an `id -> meta` map.
 2. **Message parsing**: before calling the model, extract all `@skill-id` references from user/system messages.
 3. **Resolution**: map the found IDs into `SkillMeta` objects using the bootstrap map.
 4. **Lazy load**: read `SKILL.md` files only for these IDs (up to a configurable maximum).
@@ -48,7 +50,9 @@ The recommended flow is:
 
 ## 3. Structure of `skills_index.json`
 
-The file `data/skills_index.json` is an array of objects, for example:
+The file `skills_index.json` is an array of objects, for example:
+
+> `data/skills_index.json` is the compatibility mirror and should stay in sync with the canonical root manifest.
 
 ```json
 {
@@ -78,6 +82,10 @@ To resolve the path to a skill definition:
 
 ## 4. Integration pseudocode (TypeScript)
 
+The parser should validate against:
+
+- [`schemas/skills-index.v1.schema.json`](../../schemas/skills-index.v1.schema.json)
+
 > Full example in: [`docs/integrations/jetski-gemini-loader/`](../../docs/integrations/jetski-gemini-loader/).
 
 ### 4.1. Core Types
@@ -265,7 +273,7 @@ To prevent recurrence:
 ## 9. Summary
 
 - Do not concatenate all `SKILL.md` files into a single prompt.
-- Use `data/skills_index.json` as a lightweight manifest.
+- Use `skills_index.json` as the canonical lightweight manifest.
 - Load skills **on demand** based on `@skill-id`.
 - Set clear limits (max skills per turn, token threshold).
 

package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md

@@ -9,7 +9,8 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
 ## What this example demonstrates
 
 - How to:
-  - load the global manifest `data/skills_index.json` once at startup;
+  - load the canonical manifest `skills_index.json` once at startup;
+  - optionally support `data/skills_index.json` for compatibility-only hosts.
   - scan conversation messages for `@skill-id` patterns;
   - resolve those ids to entries in the manifest;
   - read only the corresponding `SKILL.md` files from disk (lazy loading);
@@ -20,7 +21,12 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
 
-This pattern avoids context overflow when you have 1,459+ skills installed.
+This pattern avoids context overflow when you have 1,460+ skills installed.
+
+Manifest contract references:
+
+- [`../../../schemas/skills-index.v1.schema.json`](../../../schemas/skills-index.v1.schema.json)
+- [`../../users/discovery-manifest.md`](../../users/discovery-manifest.md)
 
 ---
 
@@ -49,9 +55,9 @@ import {
 
 const REPO_ROOT = "/path/to/antigravity-awesome-skills";
 const SKILLS_ROOT = REPO_ROOT;
-const INDEX_PATH = path.join(REPO_ROOT, "data", "skills_index.json");
+const INDEX_PATH = path.join(REPO_ROOT, "skills_index.json");
 
-// 1. Bootstrap once at agent startup
+// 1. Bootstrap once at agent startup (optionally validate `data/skills_index.json` for compatibility hosts).
 const skillIndex = loadSkillIndex(INDEX_PATH);
 
 // 2. Before calling the model, build messages with lazy‑loaded skills
@@ -85,7 +91,8 @@ Adapt the paths and model call to your environment.
 
 - **Do not** iterate through `skills/*/SKILL.md` and load everything at once.
 - This example:
-  - assumes skills live under the same repo root as `data/skills_index.json`;
+  - assumes skills live under the same repo root as `skills_index.json`;
+  - keeps `data/skills_index.json` for compatibility readers only;
   - uses a plain Node.js ESM module so it can be imported directly without a TypeScript runtime.
 - In a real host:
   - wire `buildModelMessages` into the point where you currently assemble the prompt before `TrajectoryChatConverter`;

package/bundled-skills/docs/maintainers/repo-growth-seo.md

@@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t
 
 Preferred positioning:
 
-> Installable GitHub library of 1,459+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,460+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
 
 Key framing:
 
@@ -20,7 +20,7 @@ Key framing:
 
 Preferred description:
 
-> Installable GitHub library of 1,459+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
+> Installable GitHub library of 1,460+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
 
 Preferred homepage:
 
@@ -28,7 +28,7 @@ Preferred homepage:
 
 Preferred social preview:
 
-- use a clean preview image that says `1,459+ Agentic Skills`;
+- use a clean preview image that says `1,460+ Agentic Skills`;
 - mention Claude Code, Cursor, Codex CLI, and Gemini CLI;
 - avoid dense text and tiny logos that disappear in social cards.
 

package/bundled-skills/docs/maintainers/skills-update-guide.md

@@ -39,10 +39,12 @@ The START_APP.bat file includes integrated update functionality that:
 # 1. Generate skills index
 python tools/scripts/generate_index.py
 
-# 2. Copy to web app
+# 2. Copy canonical manifest to web app
 copy skills_index.json apps\web-app\public\skills.json
 ```
 
+`tools/scripts/generate_index.py` writes the canonical root `skills_index.json` and mirrors the same array payload to `data/skills_index.json` for compatibility readers.
+
 ## Prerequisites
 
 For manual updates, you need:
@@ -67,9 +69,10 @@ For manual updates, you need:
 ## What Gets Updated
 
 The update process refreshes:
-- Skills index (`skills_index.json`)
+- Canonical skills index (`skills_index.json`)
+- Compatibility mirror (`data/skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 1,459+ skills from the skills directory
+- All 1,460+ skills from the skills directory
 
 ## When to Update
 

package/bundled-skills/docs/users/bundles.md

@@ -673,4 +673,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: March 2026 | Total Skills: 1,459+ | Total Bundles: 37_
+_Last updated: March 2026 | Total Skills: 1,460+ | Total Bundles: 37_

package/bundled-skills/docs/users/claude-code-skills.md

@@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the
 
 ## Why use this repo for Claude Code
 
-- It includes 1,459+ skills instead of a narrow single-domain starter pack.
+- It includes 1,460+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.

package/bundled-skills/docs/users/discovery-manifest.md

@@ -0,0 +1,62 @@
+# Stable Skills Manifest v1
+
+This page documents the `skills_index.json` manifest contract used by stable integrations.
+
+## Manifest contract (v1)
+
+- **Canonical file:** `skills_index.json` at repository root.
+- **Mirror file:** `data/skills_index.json` must be an exact compatibility mirror of `skills_index.json`.
+- **Format:** JSON array, one object per skill.
+- **Schema:** [`schemas/skills-index.v1.schema.json`](../../schemas/skills-index.v1.schema.json)
+
+## Required fields
+
+Each manifest entry includes:
+
+- `id` – skill identifier (same as `@skill-id`).
+- `path` – relative skill folder, e.g. `skills/brainstorming`.
+- `category` – grouping used by UI/search surfaces.
+- `name` – display name.
+- `description` – short purpose/trigger summary.
+- `risk` – one of repo risk labels.
+- `source` – source of authority/trust metadata.
+- `date_added` – ISO date string or `null`.
+
+Additional fields are allowed, and `plugin` metadata is optional.
+
+## Recommended host behavior
+
+Stable integrations must not load every skill instruction file up front.
+
+- Read the manifest (`skills_index.json`).
+- Resolve only the requested `@skill-id` values from the conversation.
+- For each resolved skill, read that one `SKILL.md` lazily.
+- Enforce a per-turn maximum so user prompts stay below context limits.
+- Validate each resolved path stays under your configured `SKILLS_ROOT`.
+
+This is the core prevention for context truncation and trajectory conversion errors in larger multi-skill hosts.
+
+## Why the `data/` mirror exists
+
+`data/skills_index.json` remains for downstream compatibility where clients still read from the `data/` subtree. The stable contract is that both files contain the same payload.
+
+## Quick structure example
+
+```json
+{
+  "id": "brainstorming",
+  "path": "skills/brainstorming",
+  "category": "planning",
+  "name": "brainstorming",
+  "description": "Use before any creative or constructive work.",
+  "risk": "safe",
+  "source": "official",
+  "date_added": "2026-02-27"
+}
+```
+
+## Related docs
+
+- [`docs/integrations/jetski-cortex.md`](../integrations/jetski-cortex.md)
+- [`docs/integrations/jetski-gemini-loader/README.md`](../integrations/jetski-gemini-loader/README.md)
+- [`docs/users/windows-truncation-recovery.md`](windows-truncation-recovery.md)

package/bundled-skills/docs/users/faq.md

@@ -70,9 +70,16 @@ This is **not** how this repository is designed to be used, and it will almost c
 
 Instead, hosts should:
 
-- use `data/skills_index.json` as a **lightweight manifest** for discovery; and
+- use `skills_index.json` as the **canonical array-format manifest** for discovery;
+- use `data/skills_index.json` as the compatibility mirror in `data/` when needed;
+- validate each discovered `path` against `SKILLS_ROOT` before reading; and
 - load individual `SKILL.md` files **only when a skill is invoked** (e.g. via `@skill-id` in the conversation).
 
+Manifest contract references:
+
+- [`schemas/skills-index.v1.schema.json`](../../schemas/skills-index.v1.schema.json)
+- [`discovery-manifest.md`](discovery-manifest.md)
+
 For a concrete example (including pseudo‑code) see:
 
 - [`docs/integrations/jetski-cortex.md`](../integrations/jetski-cortex.md)

package/bundled-skills/docs/users/gemini-cli-skills.md

@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
 
 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
-- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,459+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,460+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
 
 ## Install Gemini CLI Skills

package/bundled-skills/docs/users/getting-started.md

@@ -1,4 +1,4 @@
-# Getting Started with Antigravity Awesome Skills (V11.2.0)
+# Getting Started with Antigravity Awesome Skills (V11.3.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 

package/bundled-skills/docs/users/kiro-integration.md

@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
 
 Kiro's agentic capabilities are enhanced by skills that provide:
 
-- **Domain expertise** across 1,459+ specialized areas
+- **Domain expertise** across 1,460+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture

package/bundled-skills/docs/users/usage.md

@@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l
 
 When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 1,459+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
+✅ **Downloaded 1,460+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
 ✅ **Made them available** to your AI assistant  
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
 
@@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide
 
 **Analogy:**
 
-- You installed a toolbox with 1,459+ tools (✅ done)
+- You installed a toolbox with 1,460+ tools (✅ done)
 - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
 - You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin
 
@@ -212,7 +212,7 @@ Let's actually use a skill right now. Follow these steps:
 
 ## Step 5: Picking Your First Skills (Practical Advice)
 
-Don't try to use all 1,459+ skills at once. Here's a sensible approach:
+Don't try to use all 1,460+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -343,17 +343,23 @@ Usually no, but if your AI doesn't recognize a skill:
 
 ### "Can I load all skills into the model at once?"
 
-No. Even though you have 1,459+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,460+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 
-- use `data/skills_index.json` (the manifest) to discover which skills exist; and
+- use `skills_index.json` (canonical discovery manifest) to discover which skills exist; and
+- use `data/skills_index.json` only when your host reads from `data/` for compatibility;
 - only load the `SKILL.md` files for the specific `@skill-id` values you actually use in a conversation.
 
 If you are building your own host/agent (e.g. Jetski/Cortex + Gemini), see:
 
 - [`docs/integrations/jetski-cortex.md`](../integrations/jetski-cortex.md)
 
+The v1 manifest shape is defined in:
+
+- [`schemas/skills-index.v1.schema.json`](../../schemas/skills-index.v1.schema.json)
+- [`discovery-manifest.md`](discovery-manifest.md)
+
 ### "Can I create my own skills?"
 
 Yes! Use the `@skill-creator` skill:

package/bundled-skills/docs/users/visual-guide.md

@@ -34,7 +34,7 @@ antigravity-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,459+ skills live here
+├── 📁 skills/                          ← 1,460+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,459+ total)
+│   └── ... (1,460+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,459+ SKILLS          │
+                    │  1,460+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,459+ total)                │
+│   └── ... (1,460+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/docs/users/windows-truncation-recovery.md

@@ -60,10 +60,13 @@ If you installed skills into a different location, also back up that custom dire
 ## Recommended prevention
 
 - Do not concatenate every `SKILL.md` into one system prompt.
-- Use `data/skills_index.json` as a lightweight manifest.
+- Use the stable manifest contract:
+  - `skills_index.json` as canonical discovery source;
+  - `data/skills_index.json` only as compatibility mirror.
 - Load `SKILL.md` files only when a skill is actually requested.
 - Set explicit limits for skills per turn.
 - Prefer `overflowBehavior: "error"` in the reference Jetski/Gemini loader so the host fails clearly instead of silently overfilling the context window.
+- See the schema and contract details in [`discovery-manifest.md`](discovery-manifest.md).
 
 See:
 

package/bundled-skills/recsys-pipeline-architect/SKILL.md

@@ -0,0 +1,117 @@
+---
+name: recsys-pipeline-architect
+description: "Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework"
+category: data-ai
+risk: safe
+source: community
+source_repo: mturac/recsys-pipeline-architect
+source_type: community
+date_added: "2026-05-16"
+author: mturac
+tags: [recommender-system, ranking, feed-algorithm, recsys, personalization, for-you-feed, rag-reranker, pipeline-architecture]
+tools: [claude, codex, cursor, gemini, opencode, cline, continue, windsurf]
+license: "MIT"
+license_source: "https://github.com/mturac/recsys-pipeline-architect/blob/main/LICENSE"
+---
+
+# recsys-pipeline-architect
+
+## Overview
+
+A spec-and-scaffold skill for building composable recommendation, ranking, and feed pipelines. It encodes the six-stage **Source → Hydrator → Filter → Scorer → Selector → SideEffect** framework popularized by xAI's open-sourced [For You algorithm](https://github.com/xai-org/x-algorithm) (Apache 2.0). This skill is an independent reimplementation of the *pattern* — no code is copied from the original — licensed MIT. Use it whenever you need "the top K items for a (user, context)": social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.
+
+## When to Use This Skill
+
+- Use when the user wants to build any system that picks "the top K items for a user/context"
+- Use when the user asks "how should I rank X" or describes a feed/personalization problem
+- Use when the user has a scoring function and needs the pipeline plumbing around it
+- Use when the user wants to migrate from a single relevance score to multi-action prediction with tunable weights
+- Use when the user is wrapping an LLM/ML scorer and needs filters, hydrators, side-effects, and a runnable scaffold in their stack (TypeScript / Go / Python)
+
+## How It Works
+
+### Step 1: Clarify the use case
+
+Ask the user three questions (only what is missing):
+
+1. What are the items being ranked? (posts, products, tasks, alerts, documents...)
+2. What is the input context? (user ID, search query, current document, time window...)
+3. What language / runtime? (TypeScript/Node, Go, Python, Rust...)
+
+### Step 2: Walk the eight steps of the spec
+
+The full SKILL walks through: clarify use case → identify candidate sources → list required hydrations → list filters → design scorer chain → selector → side effects → generate scaffold. Each step surfaces the architectural trade-offs (multi-action vs single-score, candidate isolation vs joint scoring, online vs offline batch) so the user makes them explicitly rather than defaulting silently.
+
+### Step 3: Emit a runnable scaffold
+
+The upstream repository ships three runnable example scaffolds — every one green on its test suite:
+
+- **Strapi v5 plugin** (TypeScript, Jest, 3/3 pass) — adds `GET /api/feed/for-you` with multi-action scoring and author diversity
+- **Zentra-compatible pipeline** (Go with generics, 3/3 pass) — engine.Module-compatible, standalone-usable
+- **PMAI task prioritizer** (Python / FastAPI / pytest, 3/3 pass) — `GET /tasks/next?user_id=42&limit=10`
+
+When the user's stack doesn't match, the skill generates from scratch following the interface definitions in `references/interfaces.md` (TypeScript, Go, Python, Rust).
+
+## Examples
+
+### Example 1: Strapi content feed
+
+User: "I'm running a Strapi v5 instance with 50k articles. I want a 'for you' feed personalized to each logged-in user based on their reading history."
+
+Skill walks through the 8 steps, generates a Strapi plugin scaffold using the Strapi example as the template.
+
+### Example 2: RAG retrieval reranker
+
+User: "My RAG returns top-50 chunks from a vector DB. I want to rerank them with a more expensive scorer and return top-5."
+
+Skill recognizes this as a single-source pipeline with a scorer chain (cheap retrieval + expensive rerank). Generates a Python async pipeline.
+
+### Example 3: Notification triage
+
+User: "We send too many notifications. I want a daily digest that picks the top 10 from the last 24h queue."
+
+Skill identifies this as an offline-batch pipeline. Generates a scheduled job scaffold.
+
+## Best Practices
+
+- ✅ Surface the multi-action vs single-score trade-off explicitly — don't default silently
+- ✅ Order filters by cost (cheap before expensive); universal filters before user-specific
+- ✅ Wrap side effects in fire-and-forget patterns (goroutines / promises without await / asyncio tasks) — never block the response
+- ✅ Keep scoring deterministic and cacheable; do diversity reranking as a separate stage
+- ✅ Attribute the pattern as "popularized by xAI's open-sourced For You algorithm" when generating output
+- ❌ Don't invent benchmark or latency numbers — say "depends on workload, run it yourself"
+- ❌ Don't name the user's generated artifact "X-like" or use "For You" branding — the pattern is free, the brand is not
+- ❌ Don't conflate this with model architecture: this skill is pipeline plumbing *around* the scorer, not the scorer itself
+
+## Limitations
+
+- This skill scaffolds pipeline plumbing; it does not train ML models — the scoring function is the user's responsibility
+- It does not operate deployed pipelines (no monitoring, no autoscaling decisions)
+- It does not predict pipeline performance (depends on data, hardware, traffic)
+- It does not choose infrastructure (vector DB, cache, queue) — those are outside scope
+
+## Security & Safety Notes
+
+- The generated scaffolds are framework code, not application logic — no shell commands, no network fetches, no credential handling
+- Filters in the generated cookbook include eligibility/paywall/geo-restriction checks; the skill recommends putting these *before* scoring (so blocked content is never scored)
+- Side-effect stages are always async / fire-and-forget; the skill documents this explicitly in the generated README to prevent users from accidentally blocking the response with cache writes or event emissions
+
+## Common Pitfalls
+
+- **Problem:** Single-score model gets overfit to one metric (clicks) and degrades on others (long sessions, retention)
+  **Solution:** Skill recommends multi-action prediction with tunable weights — change behavior by changing weights, no retraining
+
+- **Problem:** Joint scoring (transformer over the whole batch) is non-deterministic and uncacheable
+  **Solution:** Skill defaults to candidate isolation via attention masking; recommends joint only when there's a specific reason (e.g., batch-aware diversity)
+
+- **Problem:** Side effects (cache writes, impression emits) block the response
+  **Solution:** Skill generates fire-and-forget patterns and documents the constraint
+
+## Upstream
+
+This skill is a thin adapter to the upstream repository. For the full SKILL.md content, 5 reference documents (interfaces in 4 languages, multi-action scoring, candidate isolation, filter cookbook, scorer cookbook), and 3 runnable example scaffolds with passing test suites:
+
+- **Repository:** https://github.com/mturac/recsys-pipeline-architect
+- **Release:** v0.1.0
+- **Install via skills.sh:** `npx skills add mturac/recsys-pipeline-architect`
+- **Pattern source:** https://github.com/xai-org/x-algorithm (Apache 2.0; this skill is MIT)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "3.0.16",
+  "version": "3.0.18",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills_index.json

@@ -23788,6 +23788,28 @@
       "reasons": []
     }
   },
+  {
+    "id": "recsys-pipeline-architect",
+    "path": "skills/recsys-pipeline-architect",
+    "category": "data-ai",
+    "name": "recsys-pipeline-architect",
+    "description": "Designs composable recommendation, ranking, and feed pipelines using the six-stage Source\u2192Hydrator\u2192Filter\u2192Scorer\u2192Selector\u2192SideEffect framework",
+    "risk": "safe",
+    "source": "community",
+    "date_added": "2026-05-16",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    }
+  },
   {
     "id": "recursive-context-pruning-token-budgeting",
     "path": "skills/recursive-context-pruning-token-budgeting",