Borrowing it
Nothing to install: this file belongs to ertra/pm-brain-for-cursor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ertra/pm-brain-for-cursor/main/.cursor/skills/query-datasets/SKILL.mdgit clone --depth 1 https://github.com/ertra/pm-brain-for-cursorWrote 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/ertra/pm-brain-for-cursor/query-datasets)<a href="https://agentmods.dev/skills/ertra/pm-brain-for-cursor/query-datasets"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/query-datasets/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/ertra/pm-brain-for-cursor/query-datasets"><img src="https://agentmods.dev/badge/skills/ertra/pm-brain-for-cursor/query-datasets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00091 | $0.02828 |
| Opus 5.5 | $0.00036 | $0.01131 |
| Sonnet 5.5 | $0.00018 | $0.00566 |
| Haiku 4.5 | $0.00009 | $0.00283 |
Grade A, and why
query-datasets 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 1mo 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
query-datasets
Answer questions about what's in 03-datasets/ using the local indexes at 03-datasets/_indexes/*.db.
The repo ships a small, fictional sample dataset under 03-datasets/ plus
the self-contained tooling under 03-datasets/_tools/. Use this skill for
demos, walkthroughs, and questions of the form "do any support tickets /
calls in the sample mention X?". The skill is read-only.
When this skill applies
- "Do support tickets mention conflicts with the Gmail extension?"
- "Did any prospect on a call ask for an audit log UI?"
- "Is there a ticket about timezone / DST handling?"
- Any factual lookup against
03-datasets/.
When it does NOT apply
- General PM workflow questions not tied to the datasets.
- Requests to modify / add / delete tickets. This skill is read-only.
- Questions spanning multiple corpora at once — ask the user which one instead.
Preconditions
03-datasets/_indexes/<corpus>.dbmust exist and be complete. The file exists ANDSELECT value FROM meta WHERE key='build_complete_at'returns non-empty.- Local Python env must be ready to load the same sentence-transformers model recorded in
meta.modelwhen using hybrid or vector mode. - Python venv at
.venv/with dependencies installed (pip install -r requirements.txt). - If the indexes do not exist yet, build them first:
First run downloadssource .venv/bin/activate python 03-datasets/_tools/build_index.py --corpus support_tickets \ --provider sentence-transformers --model nomic-ai/nomic-embed-text-v1.5 python 03-datasets/_tools/build_index.py --corpus call_transcripts \ --provider sentence-transformers --model nomic-ai/nomic-embed-text-v1.5nomic-ai/nomic-embed-text-v1.5from Hugging Face (~500 MB).
If any of these fail, tell the user what's missing and how to fix it — don't invent results.
Checklist
Do these steps in order. Create TodoWrite items for them when the question is non-trivial.
- Identify the single target corpus from the user's phrasing. Signals:
- "support tickets" / "Zendesk" / "help desk" / "customer support" / "ticket #NNN" →
support_tickets - "calls" / "recordings" / "transcripts" / "what did the prospect say" →
call_transcripts
- "support tickets" / "Zendesk" / "help desk" / "customer support" / "ticket #NNN" →
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.
- 1mo ago First seen · 165 lines · 91 tokens per session scan A 51d1b7f4bcbd
query-datasets is a skill published in the GitHub repository ertra/pm-brain-for-cursor (22 stars, last pushed 5mo ago), licensed MIT. It adds 91 tokens to every session and 2,828 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
pm-ai-reimagination
Map one customer job stage by stage and reimagine it with AI. Captures the current state per stage (action, tools, pain or workaround), classifies each stage as AI does it / AI assists / step disappears / stays human — weighing regulation, data, user trust and feasibility — and describes the reimagined experience plus…
ai-wrapper-product-v2
AI Wrapper Product workflow skill. Use this skill when the user needs Expert in building products that wrap AI APIs (OpenAI, Anthropic, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.