Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pproenca/dot-skills --skill marketplace-recsys-feature-engineeringgit clone --depth 1 https://github.com/pproenca/dot-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pproenca/dot-skills/marketplace-recsys-feature-engineering)<a href="https://agentmods.dev/skills/pproenca/dot-skills/marketplace-recsys-feature-engineering"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/marketplace-recsys-feature-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pproenca/dot-skills/marketplace-recsys-feature-engineering"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/marketplace-recsys-feature-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00218 | $0.03337 |
| Opus 5 | $0.00109 | $0.01669 |
| Sonnet 5 | $0.00044 | $0.00667 |
| Haiku 4.5 | $0.00022 | $0.00334 |
Grade A, and why
marketplace-recsys-feature-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketplace Engineering Recsys Feature Engineering Best Practices
Comprehensive first-principles guide for deriving usable recommender features from the raw assets of a two-sided trust marketplace — listing photos, owner-supplied listing metadata, and sitter wizard responses — for item-to-item, user-to-item, and user-to-user solutions. Contains 44 rules across 8 categories ordered by cascade impact on the feature-engineering lifecycle, plus one playbook that composes the rules into an end-to-end feature discovery workflow.
This skill is the upstream precursor to marketplace-personalisation (AWS Personalize) and marketplace-search-recsys-planning (OpenSearch retrieval). Those skills treat features as inputs they already have; this skill is about deciding what features to build from the raw assets, which decisions they serve, and how to prove each one is worth its maintenance cost.
When to Apply
Reference this skill when:
- Planning what to extract from listing photos, descriptions, or amenity lists to power i2i similarity or u2i ranking
- Designing or revising the sitter onboarding wizard with recsys features as the primary output
- Deciding whether to build a vision embedding pipeline, a text encoder, or neither — and in what order
- Composing existing base features into item-to-item, user-to-item, or user-to-user scoring
- Auditing an existing feature store for coverage, drift, PII, duplication, or orphan features
- Choosing a ship/kill criterion for a new recsys feature and designing the ablation A/B test
- Answering the question: "we want to improve the similar-homes shelf — what feature should we build?"
Setup
This skill has no user-specific configuration — it is self-contained. References are live URLs to engineering blogs from Airbnb, Pinterest, DoorDash, Uber, Netflix, and Google, to open-source libraries (Feast, Sentence-Transformers, Hugging Face CLIP, H3), to foundational academic papers (Airbnb KDD 2018, Pinterest ItemSage, YouTube Semantic IDs, PinSage), and to Google's Rules of Machine Learning.
What ships with it
51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 17 KB
- assets/templates/_template.md 1.2 KB
- gotchas.md 661 B
- metadata.json 4.2 KB
- README.md 6.9 KB
- references/_sections.md 4.0 KB
- references/audit-measure-coverage-before-modelling.md 2.0 KB
- references/audit-quantify-freshness-per-asset.md 2.0 KB
- references/audit-sample-every-asset-type-end-to-end.md 2.0 KB
- references/audit-separate-raw-assets-from-derived-features.md 1.9 KB
- references/audit-verify-rights-and-privacy-before-extraction.md 2.0 KB
- references/derive-cache-user-embedding-with-short-ttl.md 2.1 KB
- references/derive-decompose-affinity-into-interpretable-subscores.md 2.2 KB
- references/derive-fuse-modalities-before-item-similarity.md 2.2 KB
- references/derive-precompute-i2i-nearest-neighbours-offline.md 2.1 KB
- references/derive-score-u2u-as-symmetric-mutual-fit.md 2.1 KB
- references/derive-use-two-tower-for-user-item-affinity.md 2.6 KB
- references/firstp-ask-what-signal-a-human-uses.md 2.2 KB
- references/firstp-kill-features-a-popularity-baseline-already-captures.md 2.1 KB
- references/firstp-prefer-directly-observed-over-learned.md 2.0 KB
- references/firstp-reject-features-you-cannot-serve-at-inference.md 2.3 KB
- references/firstp-start-from-the-decision-not-the-algorithm.md 2.4 KB
- references/firstp-tie-every-feature-to-a-specific-solution.md 1.8 KB
- references/listing-declare-categorical-fields-for-bounded-vocabularies.md 2.4 KB
- references/listing-embed-description-with-pretrained-sentence-encoder.md 1.9 KB
- references/listing-encode-pet-requirements-as-structured-triples.md 2.1 KB
- references/listing-extract-stay-duration-shape-not-just-length.md 2.0 KB
- references/listing-hash-geo-to-hierarchies-not-raw-lat-lon.md 1.8 KB
- references/listing-multi-hot-encode-amenity-lists.md 2.1 KB
- references/playbooks/discovering.md 13 KB
- references/prove-dedicate-random-exploration-slice-to-new-features.md 2.0 KB
- references/prove-kill-features-that-dont-earn-maintenance.md 2.1 KB
- references/prove-measure-lift-against-feature-ablated-variant.md 1.9 KB
- references/prove-retain-feature-free-baseline-permanently.md 2.0 KB
- references/prove-ship-one-feature-at-a-time.md 2.0 KB
- references/quality-freeze-feature-schemas-per-model-version.md 2.3 KB
- references/quality-gate-features-on-coverage-and-drift.md 2.5 KB
- references/quality-scrub-pii-before-features-leave-secure-zone.md 2.1 KB
- references/quality-serve-training-and-inference-from-one-store.md 2.5 KB
- references/quality-version-feature-definitions-in-one-registry.md 2.2 KB
- references/vision-detect-room-types-before-detecting-amenities.md 2.2 KB
- references/vision-extract-per-object-counts-not-just-presence.md 2.1 KB
- references/vision-fine-tune-on-your-domain-when-clip-underperforms.md 2.2 KB
- references/vision-pool-embeddings-across-a-listings-photo-set.md 1.9 KB
- references/vision-quantify-image-quality-separately-from-content.md 2.0 KB
- references/vision-use-clip-for-zero-shot-listing-embeddings.md 2.0 KB
- references/wizard-capture-experience-as-counts-and-dates.md 2.5 KB
- references/wizard-make-skips-genuine-and-log-them.md 2.2 KB
- references/wizard-order-questions-by-information-gain.md 2.2 KB
- references/wizard-prefer-multiple-choice-over-free-text.md 2.3 KB
- references/wizard-separate-hard-constraints-from-soft-preferences.md 2.3 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 143 lines · 218 tokens per session scan A a901fa90d6c7
marketplace-recsys-feature-engineering is a skill published in the GitHub repository pproenca/dot-skills (207 stars, last pushed 28d ago), licensed MIT. It adds 218 tokens to every session and 3,337 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.