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/WackyGem/Fleurnpx agentmods add skills/wackygem/fleur/fleur-dbt-model-readinessWrote 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/wackygem/fleur/fleur-dbt-model-readiness)<a href="https://agentmods.dev/skills/wackygem/fleur/fleur-dbt-model-readiness"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-dbt-model-readiness/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/wackygem/fleur/fleur-dbt-model-readiness"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-dbt-model-readiness.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 | $0.00062 | $0.01811 |
| Opus 5 | $0.00031 | $0.00905 |
| Sonnet 5 | $0.00012 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
fleur-dbt-model-readiness 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staging Model Readiness
在写或重写 pipeline/elt/models/staging/** 前使用本 skill。目标是先理解 raw source 的真实数据质量和数据特征,再设计 staging 清洗、字段治理和 tests。
必读入口
AGENTS.md的 dbt 入口。docs/ADR/0007-dbt-staging-cleaning-boundary.md。docs/ADR/0008-raw-source-profiling-before-dbt-staging.md。docs/RFC/archive/0013-raw-source-profiling-before-dbt-staging.md。docs/plans/archive/0025-raw-source-profiling-before-dbt-staging-implementation-plan.md。
Workflow
- 确认目标 staging model 和直接 raw inputs。
- 读取
pipeline/elt/models/sources.yml。 - 读取对应
pipeline/contracts/datasets/<dataset>.yml。 - 如存在,读取
docs/references/data_dict/<dataset>.md。
- 读取
- 按 dbt discovering-data 方法完成 raw profiling。
- inventory。
- sample raw data。
- row count、日期/分区范围。
- grain 和候选自然键。
- null、空字符串、占位值。
- 枚举值和 top values。
- 证券代码/日期/高价值字符串格式。
- 数值范围、负数、零值、极端值和单位判断。
- 写入
docs/references/raw_profile/<dataset>.md。 - 在 report 前半部分提炼“数据分析发现”,不要只留下 SQL 输出。
- 数据量、覆盖范围、分区范围。
- grain、候选键、重复情况;如存在新旧候选键,必须对比说明。
- 关键字段 null / 空字符串 / 占位值,并解释哪些是预期缺失。
- 证券代码、日期、报告期、状态字段等高价值字段的格式和异常样本。
- 枚举分布、长尾文本、低频异常值;必要时补充字段间相关性。
- 时间字段范围和业务合理性检查,例如日期先后关系。
- 数值字段负数、零值、极端值和单位判断。
- 只把已执行查询支持的事实写成结论;推断必须标明为判断。
- 从 report 中提取 staging 设计:
- rename。
- cast。
- normalize。
- null handling。
- data tests。
- YAML
config.meta.source_columns和 normalization metadata。 - deferred to intermediate/mart。
- 只有完成 raw profile 后,再写 staging SQL/YAML。
- 运行验证。
Report Shape
raw profile report 应采用“结论优先,证据后置”的结构。SQL 附录用于追溯, 但 reviewer 应能先通过“数据分析发现”和“Staging 设计决策”判断模型怎么写。
推荐章节:
范围与执行信息:命令、日期、状态、contract、source、ClickHouse raw 表。数据分析发现:用分组 bullet 写高信号事实。- 数据量与覆盖:总行数、distinct 主体数、分区 / 日期范围。
- 粒度与候选键:候选键去重结果、旧键对比、重复样本归因。
- 缺失与占位:关键字段 NULL、空字符串、
1970-01-01、供应商占位。 - 格式与参照完整性:证券代码格式、报告期标签、是否能命中直接依赖 raw input。
- 分布与相关性:枚举 top values、少量值、长尾文本、字段间强相关。
- 时间合理性:min/max、日期顺序异常、批次时间范围。
- 数值合理性:负数、零值、极端值、单位假设。
字段画像:保留逐字段表,用于快速查 NULL、占位、distinct 和备注。数据质量问题:只列实际发现的问题;通用风险不要写成问题。Staging 设计决策:明确每个清洗动作是否进入 staging、测试和 metadata。延后到 Intermediate/Mart:跨源归并、业务优先级、主数据修正、复杂文本归一化。待确认问题。关键 SQL 证据摘要:只放支撑结论的高信号结果。验收清单:保持## 9. 验收清单标题,兼容 readiness lint。Profiling SQL 与结果:保留高信号、可复核的查询和输出。
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 · 139 lines · 62 tokens per session scan A 44ec7fa69069
fleur-dbt-model-readiness is a skill published in the GitHub repository WackyGem/Fleur (114 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,811 once invoked, about $0.0003 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
pinecone
Managed vector DB for production RAG and search.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…
nornicdb-qdrant-migration
Migrate from Qdrant to NornicDB end-to-end through NornicDB's Qdrant-compatible gRPC surface. Covers connection setup, collection→database mapping, point→node mapping, the vector-config and named-vector replication, point upsert in batches, count verification, and what (deliberately) does not transfer (snapshots, HNSW…