ericrisco/rsc-harness / skills/mongodb
mongodb
VerifiedUse when modeling MongoDB documents (embed versus reference, the 16MB cap, bucket and subset patterns), choosing or fixing indexes (compound order by the ESR rule, partial, TTL, multikey, reading explain), writing aggregation pipelines that stay index-eligible, running multi-document transactions with retry, or operating and securing a deployment (replica set, read/write concern, Atlas tiers, Vector Search, Queryable Encryption). MongoDB 8.2, driver-agnostic. NOT relational schema, SQL or EXPLAIN ANALYZE (that is `postgresdb`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.9 KB |
| evals/README.md | markdown | 1.6 KB |
| evals/cases.yaml | config | 3.7 KB |
| references/aggregation.md | markdown | 4.8 KB |
| references/data-modeling.md | markdown | 5.4 KB |
| references/transactions-and-ops.md | markdown | 5.9 KB |
| scripts/verify.shexecutable | script | 6.5 KB |
evals/README.md
View on GitHub# Eval harness — `mongodb`
These cases check two things: **triggering** (does the skill fire on real MongoDB problems and stay
quiet on near-misses?) and **capability** (does loading it measurably improve the answer?). Cases
live in `cases.yaml` and are **LLM-graded against the rubric — no live MongoDB is needed**; run them
through the repo's agent eval harness, not a shell script.
## Triggering
For each prompt, start a fresh agent session with only the `mongodb` skill discoverable (its
`SKILL.md` description in scope, no siblings loaded), paste the prompt verbatim, and run 3–5 trials
(the trigger decision is stochastic):
- `should_trigger`: PASS if the skill fires in the majority of trials. Several prompts deliberately
avoid the words "index" / "MongoDB" (the COLLSCAN complaint, the Spanish modeling request) to test
intent recognition over keyword matching.
- `should_not_trigger`: PASS if the skill does **not** fire. Each names a `route_to` sibling
(`postgresdb`, `nodejs`, `security-audit`, `redis`, `vector-db`); a wrong-but-not-`mongodb` route
still passes this skill's gate.
Pass bar: ≥ 90% trigger accuracy across all trigger cases.
## Capability
Run the `capability` scenario twice — once WITHOUT the skill (clean agent) and once WITH it — and
grade each transcript against the `must_include` checklist, one point per bullet that is correctly
and specifically covered (not merely name-dropped). Pass bar: WITH the skill covers ≥ 80% of bullets
and clearly beats WITHOUT (target ≥ +30 points). Record trial counts and per-bullet verdicts so a
reviewer can audit; don't report a bare pass/fail.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |