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 opensearch-function-scoring-algorithmsgit 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/opensearch-function-scoring-algorithms)<a href="https://agentmods.dev/skills/pproenca/dot-skills/opensearch-function-scoring-algorithms"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/opensearch-function-scoring-algorithms/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/opensearch-function-scoring-algorithms"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/opensearch-function-scoring-algorithms.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 | $0.00224 | $0.03611 |
| Opus 5 | $0.00112 | $0.01806 |
| Sonnet 5 | $0.00045 | $0.00722 |
| Haiku 4.5 | $0.00022 | $0.00361 |
Grade A, and why
opensearch-function-scoring-algorithms 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 6d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketplace-Research OpenSearch Function Scoring Best Practices
A reference distillation of research-backed algorithms for ranking in two-sided marketplaces (Airbnb, Uber Eats, DoorDash, Etsy, eBay, Booking.com) implemented on OpenSearch or Elasticsearch. Contains 56 rules across 9 categories, prioritised by cascade effect in the search ranking pipeline. Each rule explains the WHY (the cascade or the bias it corrects), shows incorrect-vs-correct code (OpenSearch JSON queries, Painless scripts, Python pre-processing, evaluation methodology), and links to the canonical source — KDD/SIGIR/WSDM papers, the OpenSearch documentation, and the engineering blogs of the marketplaces that proved these patterns at scale.
When to Apply
Reach for this skill when:
- Designing a new marketplace search system on OpenSearch or Elasticsearch from scratch
- Tuning function_score / rank_feature / script_score queries that aren't moving the needle
- Setting up hybrid retrieval (BM25 + dense vectors) with Reciprocal Rank Fusion
- Choosing between HNSW and IVF for billion-scale ANN indexes
- Adding personalization via listing/user embeddings or two-tower architectures
- Correcting position bias in click logs before retraining an LTR model
- Designing exposure-fairness or new-listing cold-start exposure allocation
- Composing decay functions (gauss / exp / linear) over geo + date + freshness
- Diversifying the top window with MMR, DPP, or per-host caps
- Debugging "why does my top-10 show 8 listings from one host?" or "why does ranking favor popular incumbents?"
- Building offline evaluation infrastructure — graded judgment sets, NDCG@k pipelines, ablation studies, regression query suites
- Designing A/B tests for ranking changes — MDE / power / sample-size pre-computation, CUPED variance reduction, online-offline correlation calibration
- Attributing lift to specific scoring components — "did my new bias-correction help, or was it the embeddings, or both?"
The rules apply to any OpenSearch/Elasticsearch-backed marketplace search regardless of vertical — accommodation, food delivery, restaurants, services, jobs, secondhand goods, real estate. Triggers include "marketplace ranking", "search relevance", "function_score", "rank_feature", "script_score", "kNN", "hybrid search", "RRF", "learning to rank", "embedding-based retrieval", "two-tower", "position bias", "MMR", "supply fairness", "Pareto multi-objective", "NDCG", "judgment set", "ablation study", "CUPED", "A/B sample size", "ranking eval", and "why are my search results bad".
What ships with it
60 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 19 KB
- assets/templates/_template.md 1.7 KB
- metadata.json 5.0 KB
- references/_sections.md 4.4 KB
- references/bias-click-models.md 3.2 KB
- references/bias-counterfactual-eval.md 4.5 KB
- references/bias-interleaved-evaluation.md 4.6 KB
- references/bias-popularity-debiasing.md 3.9 KB
- references/bias-position-ips.md 4.0 KB
- references/bias-thompson-sampling.md 4.3 KB
- references/decay-exp-freshness.md 3.3 KB
- references/decay-gauss-geo.md 3.2 KB
- references/decay-multi-field-composition.md 3.9 KB
- references/decay-offset-noise.md 2.7 KB
- references/decay-scale-calibration.md 3.1 KB
- references/div-category-diversity.md 4.0 KB
- references/div-dpp-quality-diversity.md 4.2 KB
- references/div-max-per-host.md 3.4 KB
- references/div-mmr-rerank.md 4.2 KB
- references/div-window-penalty.md 3.9 KB
- references/eval-ab-sample-size-mde.md 5.0 KB
- references/eval-ablation-attribution.md 5.2 KB
- references/eval-cuped-variance-reduction.md 5.3 KB
- references/eval-graded-judgment-set.md 4.2 KB
- references/eval-ndcg-primary-metric.md 4.5 KB
- references/eval-online-offline-correlation.md 4.8 KB
- references/eval-regression-query-suite.md 5.5 KB
- references/market-cold-start-exploration.md 3.8 KB
- references/market-conversion-weighted-ranking.md 3.3 KB
- references/market-host-quality-signals.md 3.9 KB
- references/market-inventory-health.md 3.6 KB
- references/market-pareto-multi-objective.md 4.1 KB
- references/market-price-relevance.md 3.9 KB
- references/market-supply-fairness-lorenz.md 4.0 KB
- references/pers-contextual-features.md 3.4 KB
- references/pers-cross-encoder-rerank.md 3.1 KB
- references/pers-listing-embeddings.md 3.6 KB
- references/pers-multi-modal-embeddings.md 3.5 KB
- references/pers-real-time-session-vector.md 3.5 KB
- references/pers-tower-split-offline-online.md 3.9 KB
- references/pers-type-embeddings-cold-start.md 3.4 KB
- references/qual-bayesian-average.md 3.0 KB
- references/qual-completeness-score.md 3.0 KB
- references/qual-log1p-vs-saturation.md 2.9 KB
- references/qual-rank-feature-saturation.md 3.0 KB
- references/qual-rank-feature-sigmoid.md 2.8 KB
- references/qual-wilson-lower-bound.md 2.7 KB
- references/recall-hnsw-vs-ivf.md 2.3 KB
- references/recall-hybrid-rrf.md 2.2 KB
- references/recall-multi-stage.md 2.4 KB
- references/recall-prefilter-knn.md 2.2 KB
- references/recall-query-expansion.md 2.7 KB
- references/recall-two-tower-ebr.md 2.4 KB
- references/rel-avoid-boost-inflation.md 2.5 KB
- references/rel-bm25-k1-b-tuning.md 2.7 KB
- references/rel-bm25f-field-weights.md 2.3 KB
- references/rel-listwise-loss.md 2.6 KB
- references/rel-multi-match-strategy.md 2.5 KB
- references/rel-rescore-over-bool-should.md 3.1 KB
- references/rel-script-score-over-function-score.md 3.1 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.
- 6d ago First seen · 167 lines · 224 tokens per session scan A f3e421f956a4
opensearch-function-scoring-algorithms is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 224 tokens to every session and 3,611 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.