BB mongodb
Designs MongoDB schemas, indexes, and aggregation pipelines, and debugs slow queries, connection errors, and replica set failures. Use when modeling documents, deciding embed vs reference, reading an explain plan, or fixing a COLLSCAN, and when a query times out, a pipeline aborts at the memory limit, a cursor dies mid-loop, the pool exhausts and server selection times out, writes fail with duplicate key or "not writable primary", a secondary lags, the oplog window closes, a shard key hotspots, or WiredTiger cache stalls the cluster. Covers mongosh and Compass, Atlas, Mongoose and driver connection strings, transactions and retry loops, change streams, time-series collections, Atlas Search and vector search, sharding, backups, restores, and upgrades. Not for SQL or relational modeling — normalization instincts actively mislead here.
Designs MongoDB schemas, indexes, and aggregation pipelines, and debugs slow queries, connection errors, and replica set failures.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitybackups.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Keep a copy that a compromised production credential cannot delete. Ransomware against exposed MongoDB deployments is not hypothetical, and the deletion of backups is part of the playbook.
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5226 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5226 tokens
- 100Steps. 65 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 844: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 65 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.