mongodb

Guide for implementing MongoDB - a document database platform with CRUD operations, aggregation pipelines, indexing, replication, sharding, search capabilities, and comprehensive security. Use when working with MongoDB databases, designing schemas, writing queries, optimizing performance, configuring deployments (Atlas/self-managed/Kubernetes), implementing security, or integrating with applications through 15+ official drivers. (project)

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./claude/skills/mongodb/SKILL.md

Quality

Content

53%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with extensive executable examples, but it fails as a skill overview: it is a monolithic 1400-line reference dump that buries basic content Claude already knows and uses zero progressive disclosure (no reference files, no navigation). Destructive/batch operations also lack explicit validation checkpoints.

Suggestions

Split the body into one-level-deep reference files (e.g. references/aggregation.md, references/indexing.md, references/security.md, references/drivers.md) and keep SKILL.md as a concise overview with clearly signaled links to them, rather than a 1400-line monolith.

Trim content Claude already knows — basic find/insert/update CRUD, the 100+ operator lists, and trivial driver CRUD in four languages — and remove the marketing claim about '24,618 documentation links across 172 sections' to respect the token budget.

Add explicit validation checkpoints around destructive and batch operations (e.g. run explain() / a count query before deleteMany, verify bulkWrite results against expected counts, validate shard-key choice before shardCollection) so workflows include feedback loops.

Dimension	Reasoning	Score
Conciseness	At ~1420 lines the body is noticeably verbose, inlining large amounts of basic material Claude already knows (elementary find/insert/update CRUD, 100+ operator lists, trivial driver CRUD in four languages) plus marketing fluff ("synthesizes 24,618 documentation links across 172 major MongoDB sections"). It does not assume Claude's intelligence or respect the token budget.	2 / 5
Actionability	The body is packed with copy-paste-ready, executable code across CRUD, aggregation, indexing, replication, sharding, security, deployment, and drivers, covering the common cases concretely rather than in the abstract.	5 / 5
Workflow Clarity	The content is organized as a topic catalog rather than a sequenced workflow, and destructive/batch operations (deleteMany, bulkWrite, dropIndex, shardCollection) are shown without explicit validate-then-proceed checkpoints; scattered verification tools (explain(), $indexStats, profiling) and the transaction try/commit/abort pattern exist but do not lift it above the destructive/batch cap of 3.	3 / 5
Progressive Disclosure	No bundle files exist and the entire reference is inlined into a single 1400+ line SKILL.md with no links to separate files; content that clearly belongs in dedicated references (aggregation, indexing, security, drivers) is all inlined, fitting the anchor where content that should be in separate files is inlined.	2 / 5
	Total	12 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it explicitly states both what the skill covers and when to use it, with concrete MongoDB-specific capabilities and trigger phrases, all in third-person voice. Minor room to add a few more natural synonyms (NoSQL, mongosh, named drivers) for maximum trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ("CRUD operations, aggregation pipelines, indexing, replication, sharding, search capabilities, and comprehensive security") plus concrete trigger actions ("designing schemas, writing queries, optimizing performance, configuring deployments"), giving comprehensive coverage of MongoDB's surface area.	5 / 5
Completeness	Explicitly answers both what ("Guide for implementing MongoDB - a document database platform with...") and when ("Use when working with MongoDB databases, designing schemas, writing queries...") with concrete trigger phrases, matching the anchor-5 example structure almost exactly.	5 / 5
Trigger Term Quality	Good natural-term coverage including "MongoDB databases", "Atlas/self-managed/Kubernetes", "aggregation pipelines", "sharding", and "official drivers"; a few common user variations (e.g. "NoSQL", "BSON", "mongosh", named drivers like PyMongo) are absent, keeping it just below the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly named product ("MongoDB") with MongoDB-specific triggers (Atlas, sharding, aggregation pipelines), giving it a clear niche with minimal risk of triggering for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1425 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: einverne/dotfiles
Path: claude/skills/mongodb/SKILL.md
Commit: 7d18cf4

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.