marklogic-mcp: Skill for Claude Code

.claude/skills/marklogic-data-modeling/SKILL.md

marklogic-data-modeling is a skill for Claude Code from tternquist/marklogic-mcp. It costs 117 tokens per session (2,021 once invoked), scanned A, original, MIT.

A guide for designing MarkLogic databases that combine documents, linked facts, and vector data. It also covers document naming, collections, and data-integration envelopes.

In plain words
What is it for?
Use it when modelling a new domain in MarkLogic, deciding between nested documents and linked facts, planning document URIs and collections, or preparing query views.
Why use it?
It helps choose the simplest data model that supports the queries you need, instead of adding relationships, similarity search, or analytics without a clear purpose.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is tternquist/marklogic-mcp's own configuration. It tells Claude Code how to work on marklogic-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything marklogic-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tternquist/marklogic-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tternquist/marklogic-mcp/master/.claude/skills/marklogic-data-modeling/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tternquist/marklogic-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for marklogic-data-modeling

README.md
[![agentmods](https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-data-modeling/github.svg)](https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-data-modeling)
Your own site
<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-data-modeling"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-data-modeling/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.

agentmods 80×15 button for marklogic-data-modeling

Your own site · 80×15
<a href="https://agentmods.dev/skills/tternquist/marklogic-mcp/marklogic-data-modeling"><img src="https://agentmods.dev/badge/skills/tternquist/marklogic-mcp/marklogic-data-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00117 $0.02021
Opus 5.5 $0.00047 $0.00808
Sonnet 5.5 $0.00023 $0.00404
Haiku 4.5 $0.00012 $0.00202

Measured 2mo ago against content hash 5d38fcaad122, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

marklogic-data-modeling 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 2mo 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.

.claude/skills/marklogic-data-modeling/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MarkLogic Data Modeling

Three decisions, in order: which models, how documents are shaped and named, and whether an envelope is warranted.

1. Model selection

Choose the least machinery that answers the query goals.

Use When Skip it when
Documents always — the base model never
Triples cross-entity relationships, graph traversal, taxonomy links relationships are simple parent-child → just nest them in the document
Vectors semantic similarity, RAG, recommendations no similarity requirement
TDE / Optic GROUP BY, joins, aggregation no analytical queries

State for each model you keep: why it fits, what it holds, what query capability it unlocks. Being explicit about what you are not using is as valuable as the inclusions.

2. Document design

  • Collection strategy — one collection per entity type; a <source>-raw collection per source system when harmonizing.
  • URI pattern — see §3.
  • Range index candidates — the fields used for filtering, sorting, or ml_values_query. Check what exists with ml_indexes_list.
  • TDE view candidates — the fields needing GROUP BY or JOIN.
  • Never store "". Empty strings pollute range indexes, break range queries, and create misleading TDE rows. Omit the field, or use null.
  • Dates as ISO-8601 strings, to match a dateTime range index scalar type.

3. URI design — six rules

URIs are stable identity. Get them wrong and every later query is awkward.

  1. Prefix with the collection or entity type. The prefix is the directory; ml_document_list scopes to it. /orders/order-{orderId}.json ✓ — /{orderId}.json ✗ (no grouping possible)
  2. Embed every primary key value. Deterministic and collision-free. Avoid UUIDs unless the source has no key. /events/gdelt/{GlobalEventID}.json ✓ — /orders/order.json ✗ (overwrites on every write)
  3. Match the URI prefix to the collection short name. Collection orders → URIs under /orders/.
  4. URL-safe characters only — letters, digits, /, -, _, .. Replace spaces and colons with -; turn slashes in values into path segments.
  5. Right extension — .json / .xml for content, .sjs / .xqy for modules (Modules database), .tdej for JSON TDE templates (Schemas database).
  6. Nest child entities under the parent key. /customers/{customerId}/orders/{orderId}.json lets you list one customer's orders by directory.

Read the full file on GitHub · 173 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 173 lines · 117 tokens per session scan A 5d38fcaad122

Subscribe to this mod's changes

marklogic-data-modeling is a skill published in the GitHub repository tternquist/marklogic-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 2,021 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Related

marklogic-data-modeling compared with skills from other repositories

marklogic-data-modeling next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
marklogic-data-modelingtternquist/marklogic-mcpSkill41mo agoMITA117Claude Code
embeddingsruvnet/rufloSkill81kyesterdayMITA62Claude Code
rag-pineconedavila7/claude-code-templatesSkill33kyesterdayMITA65Claude Code, Codex
data-engineerdavila7/claude-code-templatesSkill33kyesterdayMITA35Claude Code, Codex
similarity-search-patternsforyourhealth111-pixel/Vibe-SkillsSkill3.8k3d agoApache-2.0A30Claude Code, Codex
ingesting-into-data-lakeaws/agent-toolkit-for-awsSkill3.4kyesterdayApache-2.0A228Claude Code
graphjin-envdosco/graphjinSkill3.2k5d agoApache-2.0A61Claude Code, Codex