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-search-recsys-planninggit 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-search-recsys-planning)<a href="https://agentmods.dev/skills/pproenca/dot-skills/marketplace-search-recsys-planning"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/marketplace-search-recsys-planning/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-search-recsys-planning"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/marketplace-search-recsys-planning.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 | $0.00135 | $0.03318 |
| Opus 5 | $0.00068 | $0.01659 |
| Sonnet 5 | $0.00027 | $0.00664 |
| Haiku 4.5 | $0.00014 | $0.00332 |
Grade A, and why
marketplace-search-recsys-planning 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketplace Engineering Two-Sided Search and Recsys Planning Best Practices
Comprehensive planning, design and diagnostic guide for search and recommendation systems in two-sided trust marketplaces. Covers OpenSearch index, query and ranking patterns, the methodology for planning retrieval work, the handoff points to recommendation-specific tooling, and the instrumentation and dashboard layer that turns measurement into ongoing decision making. Contains 57 rules across 10 categories ordered by cascade impact, plus two playbooks (plan a new system from scratch, diagnose an existing one) and explicit living-artefact conventions (decisions log, golden set, gotchas).
When to Apply
Reference this skill when:
- Planning a new marketplace retrieval project from scratch
- Reviewing an existing retrieval system that feels stale, unfair, or unpersonalised
- Designing the OpenSearch index mapping, analyzers, or query DSL
- Choosing retrieval primitives per product surface (search, recs, hybrid, curated)
- Deciding which search quality metrics to track and dashboard
- Running the weekly search-quality review ritual
- Diagnosing a silent regression in ranking, coverage, or zero-result rate
- Deciding when a retrieval problem is actually a personalisation problem
This skill is the precursor to marketplace-personalisation. Start here for
planning and search work; hand off to the personalisation skill when the diagnosed
bottleneck is impression tracking, feedback-loop bias, or AWS Personalize-specific
design.
Living Context
This skill treats the system as evolving. Three living artefacts carry context across sessions, releases, and team changes — read them before making suggestions, update them after every shipped change:
gotchas.md(in this skill folder) — append-only diagnostic lessons. Every gotcha has a date and a short description of what surprised the team and how it was resolved.- Decisions log (maintained in the product repo, typically
decisions/*.md) — every ranking change, schema tweak, and synonym edit recorded with its hypothesis, offline and online evidence, ship criterion, outcome, and rollback path. See ruleplan-maintain-a-decisions-log. - Golden query set (frozen per eval cycle, committed to the product repo) — the
reference set of queries against which every ranking change is offline-evaluated
before an online test. See rule
plan-version-the-golden-set.
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 16 KB
- assets/templates/_template.md 2.4 KB
- gotchas.md 1.5 KB
- metadata.json 3.1 KB
- README.md 7.1 KB
- references/_sections.md 3.9 KB
- references/arch-avoid-mono-stack-retrieval.md 1.8 KB
- references/arch-design-for-cold-start-from-day-one.md 1.8 KB
- references/arch-design-zero-result-fallback.md 2.1 KB
- references/arch-map-surface-to-retrieval-primitive.md 1.8 KB
- references/arch-route-surfaces-deliberately.md 2.2 KB
- references/arch-split-candidate-generation-from-ranking.md 2.5 KB
- references/blend-combine-search-and-personalisation-scores.md 2.0 KB
- references/blend-keep-hybrid-blending-explainable.md 1.7 KB
- references/blend-never-return-zero-results.md 1.9 KB
- references/blend-use-search-alone-for-specific-intent.md 1.6 KB
- references/index-design-mappings-conservatively.md 1.8 KB
- references/index-match-index-and-query-time-analyzers.md 1.7 KB
- references/index-separate-searchable-from-display-fields.md 1.8 KB
- references/index-stream-listing-updates-via-cdc.md 2.0 KB
- references/index-use-index-templates-for-consistency.md 2.1 KB
- references/index-use-keyword-and-text-as-multi-fields.md 1.4 KB
- references/index-use-language-analyzers-for-language-fields.md 1.6 KB
- references/intent-audit-live-query-logs-first.md 1.8 KB
- references/intent-distinguish-transactional-from-exploratory.md 1.6 KB
- references/intent-map-queries-to-intent-classes.md 1.8 KB
- references/intent-reject-one-search-for-everything.md 1.9 KB
- references/intent-separate-known-item-from-discovery.md 1.8 KB
- references/intent-treat-no-search-as-first-class-choice.md 1.8 KB
- references/measure-define-session-success-per-surface.md 1.7 KB
- references/measure-run-interleaving-as-cheap-ab-proxy.md 1.7 KB
- references/measure-track-ndcg-mrr-zero-result-rate.md 1.5 KB
- references/measure-track-reformulation-rate-as-failure-signal.md 1.8 KB
- references/measure-use-click-models-for-implicit-judgments.md 2.0 KB
- references/monitor-alert-on-decision-triggers.md 2.2 KB
- references/monitor-build-search-health-dashboard.md 2.0 KB
- references/monitor-log-every-query-with-full-context.md 1.9 KB
- references/monitor-run-weekly-search-quality-review.md 1.7 KB
- references/monitor-scrub-pii-from-query-logs.md 2.3 KB
- references/monitor-track-ranking-stability-churn.md 1.8 KB
- references/plan-audit-before-you-build.md 1.9 KB
- references/plan-build-golden-query-set-first.md 1.7 KB
- references/plan-find-bottleneck-before-optimising.md 1.9 KB
- references/plan-handoff-to-personalisation-skill.md 1.9 KB
- references/plan-maintain-a-decisions-log.md 2.0 KB
- references/plan-version-the-golden-set.md 1.7 KB
- references/playbooks/improving.md 14 KB
- references/playbooks/planning.md 11 KB
- references/query-build-autocomplete-on-separate-index.md 1.4 KB
- references/query-classify-before-routing.md 1.9 KB
- references/query-curate-synonyms-by-domain.md 1.7 KB
- references/query-normalise-before-anything-else.md 1.8 KB
- references/query-use-fuzzy-matching-for-typos.md 1.2 KB
- references/query-use-language-analyzers-for-stemming.md 1.3 KB
- references/rank-apply-diversity-at-rank-time.md 1.8 KB
- references/rank-deploy-ltr-only-after-golden-set-exists.md 1.9 KB
- references/rank-normalise-scores-across-retrieval-primitives.md 2.2 KB
- references/rank-tune-bm25-parameters-last.md 1.4 KB
- references/rank-use-function-score-for-business-signals.md 1.8 KB
- references/retrieve-choose-embedding-model-deliberately.md 2.2 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 · 193 lines · 135 tokens per session scan A 1d7a041b7e0d
marketplace-search-recsys-planning is a skill published in the GitHub repository pproenca/dot-skills (207 stars, last pushed 27d ago), licensed MIT. It adds 135 tokens to every session and 3,318 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…