Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicnpx agentmods add skills/vasilyu1983/ai-agents-public/data-lake-platformWrote 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/vasilyu1983/ai-agents-public/data-lake-platform)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/data-lake-platform"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/data-lake-platform/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/vasilyu1983/ai-agents-public/data-lake-platform"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/data-lake-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 48 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 194 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 208 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.05642 |
| Opus 5 | $0.00020 | $0.02821 |
| Sonnet 5 | $0.00008 | $0.01128 |
| Haiku 4.5 | $0.00004 | $0.00564 |
Grade A, and why
data-lake-platform 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 12d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Lake Platform
Build and operate production data lakes and lakehouses: ingest, transform, store in open formats, and serve analytics reliably.
Quick Reference
| Task | Resource | When to Use |
|---|---|---|
| Pick a table format and spec version | references/storage-formats.md | Choosing Iceberg v2/v3, Delta 4.x, Hudi, Paimon, or DuckLake |
| Pick a catalog / control plane | references/governance-catalog.md | Choosing Polaris, Glue, Nessie, Unity, Gravitino, or Open Catalog |
| Design ingestion or CDC path | references/ingestion-patterns.md | dlt, Airbyte, Debezium, Flink CDC |
| Scaffold or inspect an Iceberg table | scripts/scaffold_iceberg_table.py, scripts/inspect_iceberg_metadata.sh |
New table DDL or auditing an existing table's file/metadata layout |
| Sanity-check an interoperability or version claim | data/sources.json + Fact-Checking below |
Any claim about spec-version GA status, engine support, or vendor feature |
Quick-Start Decision Table
| Situation | Default choice |
|---|---|
| Open multi-engine analytics | Iceberg + REST catalog (Polaris/Glue/Nessie) + Trino |
| Databricks primary compute | Delta 4.x + Unity Catalog; add UniForm only if external readers exist |
| CDC-heavy mutable, Spark-centered | Hudi (CoW or MoR) + Kafka/Debezium |
| Streaming-first mutable, Flink-centered | Paimon + Flink CDC |
| Single-engine embedded / analyst workstation | DuckLake (v1.0 GA Apr 2026) or DuckDB + Parquet/Iceberg |
| Low-latency BI, high concurrency dashboards | ClickHouse or StarRocks serving layer |
| Local/CI prototyping with open-table portability | DuckDB + Iceberg extension |
Format State as of July 2026
| Feature | Apache Iceberg (1.11.x) | Delta Lake 4.3 | Apache Hudi (1.0 stable / 1.1 dev) | Apache Paimon (1.3.x) |
|---|---|---|---|---|
| Spec version | v3 GA on managed platforms; Trino writes still experimental | Protocol v3; Liquid Clustering GA | 1.x table version | 1.x |
| Deletion vectors | GA (v3 spec; bitmap on Puffin) | GA | N/A (MoR log) | N/A (MoR log) |
| Catalog posture | REST-first; Polaris TLP Feb 2026 | Catalog-managed tables mature (4.1-4.3); Unity Catalog Delta APIs route all ops | Mixed | Flink-first, expanding |
| Coordinated commits | Via catalog (Polaris/Glue/Nessie) | GA since 4.1; streaming + CDC on catalog-managed tables since 4.3 | N/A | N/A |
| Branches and tags | First-class | Limited | Workflow-specific | Workflow-specific |
| Multi-engine reads | Strong (Trino, Spark, DuckDB, Flink) | Improving via UniForm + native Flink connector (4.2+); Trino v3 writes still experimental | Improving | Growing; validate |
| Trino v3 support | Experimental: read/write of base data works; row-level updates, deletes, and OPTIMIZE on v3 tables are not supported | Readers via UniForm | N/A | N/A |
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/openai.yaml 340 B
- assets/cross-platform/template-cost-optimization.md 11 KB
- assets/cross-platform/template-data-pipeline.md 9.1 KB
- assets/cross-platform/template-data-quality-backfill-runbook.md 2.6 KB
- assets/cross-platform/template-data-quality-governance.md 8.5 KB
- assets/cross-platform/template-data-quality.md 9.6 KB
- assets/cross-platform/template-incremental-loading.md 9.1 KB
- assets/cross-platform/template-ingestion-governance-checklist.md 3.7 KB
- assets/cross-platform/template-medallion-architecture.md 4.6 KB
- assets/cross-platform/template-migration-checklist.md 9.8 KB
- assets/cross-platform/template-partitioning-strategy.md 8.7 KB
- assets/cross-platform/template-schema-evolution.md 9.4 KB
- assets/ingestion/airbyte/template-airbyte-connection.md 7.9 KB
- assets/ingestion/dlt/template-dlt-database-source.md 10 KB
- assets/ingestion/dlt/template-dlt-incremental.md 11 KB
- assets/ingestion/dlt/template-dlt-pipeline.md 4.9 KB
- assets/ingestion/dlt/template-dlt-rest-api.md 9.5 KB
- assets/ingestion/dlt/template-dlt-warehouse-loading.md 12 KB
- assets/orchestration/template-dagster-pipeline.md 7.3 KB
- assets/query-engines/clickhouse/template-clickhouse-ingestion.md 7.9 KB
- assets/query-engines/clickhouse/template-clickhouse-materialized-views.md 8.4 KB
- assets/query-engines/clickhouse/template-clickhouse-optimization.md 9.4 KB
- assets/query-engines/clickhouse/template-clickhouse-replication.md 12 KB
- assets/query-engines/clickhouse/template-clickhouse-setup.md 11 KB
- assets/query-engines/doris/template-doris-setup.md 7.1 KB
- assets/query-engines/duckdb/template-duckdb-analytics.md 8.0 KB
- assets/query-engines/duckdb/template-duckdb-data-import.md 9.7 KB
- assets/query-engines/starrocks/template-starrocks-setup.md 3.7 KB
- assets/storage/delta/template-delta-table.md 6.8 KB
- assets/storage/hudi/template-hudi-table.md 7.4 KB
- assets/storage/iceberg/template-iceberg-maintenance.md 8.2 KB
- assets/storage/iceberg/template-iceberg-table.md 8.0 KB
- assets/storage/parquet/template-parquet-optimization.md 7.7 KB
- assets/streaming/template-kafka-ingestion.md 7.1 KB
- assets/transformation/dbt/template-dbt-project.md 7.0 KB
- assets/transformation/sqlmesh/template-sqlmesh-dag.md 993 B
- assets/transformation/sqlmesh/template-sqlmesh-incremental.md 1.5 KB
- assets/transformation/sqlmesh/template-sqlmesh-layering-and-access.md 6.1 KB
- assets/transformation/sqlmesh/template-sqlmesh-model.md 17 KB
- assets/transformation/sqlmesh/template-sqlmesh-production.md 23 KB
- assets/transformation/sqlmesh/template-sqlmesh-project.md 7.1 KB
- assets/transformation/sqlmesh/template-sqlmesh-security.md 19 KB
- assets/transformation/sqlmesh/template-sqlmesh-testing.md 11 KB
- assets/visualization/metabase/connection-checklist.md 780 B
- assets/visualization/metabase/dashboard-request.md 632 B
- assets/visualization/metabase/incident-playbook.md 1.0 KB
- data/sources.json 17 KB
- learnings.consolidated.md 594 B
- learnings.md 380 B
- references/architecture-patterns.md 11 KB
- references/bi-visualization-patterns.md 9.5 KB
- references/cost-optimization.md 3.8 KB
- references/data-mesh-patterns.md 15 KB
- references/data-quality-patterns.md 14 KB
- references/governance-catalog.md 10 KB
- references/ingestion-patterns.md 7.8 KB
- references/operational-playbook.md 6.1 KB
- references/orchestration-patterns.md 8.5 KB
- references/query-engine-patterns.md 6.8 KB
- references/security-access-patterns.md 14 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.
- 12d ago First seen · 269 lines · 41 tokens per session scan A 18b96db65785
data-lake-platform is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 41 tokens to every session and 5,642 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
AgentDB Performance Optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
AgentDB Vector Search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.