Borrowing it
Nothing to install: this file belongs to haakonbull/autosprint. 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/haakonbull/autosprint/master/.claude/skills/grill-me-data-science/SKILL.mdgit clone --depth 1 https://github.com/haakonbull/autosprintWrote 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/haakonbull/autosprint/grill-me-data-science)<a href="https://agentmods.dev/skills/haakonbull/autosprint/grill-me-data-science"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/grill-me-data-science/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/haakonbull/autosprint/grill-me-data-science"><img src="https://agentmods.dev/badge/skills/haakonbull/autosprint/grill-me-data-science.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 | $0.00076 | $0.01720 |
| Opus 5 | $0.00038 | $0.00860 |
| Sonnet 5 | $0.00015 | $0.00344 |
| Haiku 4.5 | $0.00008 | $0.00172 |
Grade A, and why
grill-me-data-science 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 11d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second-pass grilling that complements grill-destination. Run this after the general destination interview is complete (or after confirming autosprint/destination.md already has the usual sections filled in). The goal is to add data-science-specific content to the same autosprint/destination.md under the existing ## Desired behavior and ## Success criteria sections, and — if the user agrees — a new ## Experiment log reference to autosprint/data_science_results.md.
Data-science projects have a property normal code projects don't: you don't know in advance what "done" looks like. The correct model, the correct features, the correct preprocessing — all of those are discovered, not specified. destination.md must therefore describe the process as well as the outcome.
Before starting
- Read
autosprint/destination.md. If it's missing or has only the seed content, stop and tell the user: "Rungrill-destinationfirst — this skill layers on top of that one." - Read
autosprint/adr.mdif it exists — some staged-workflow decisions may already be recorded there (e.g. "use MLflow for experiment tracking"). Don't re-ask those. - Quote the current
## Purposeand## Desired behaviorsections back to the user and confirm this is a data-science project before starting. A project that just happens to use numpy is not a data-science project — the skill is for projects where model/method/feature selection is part of the loop.
Interview style
- Hard on metrics. A metric the planning phase can't compute has no ability to drive decisions. If the user says "better accuracy", push for "AUC on holdout set ≥ 0.85".
- Hard on staged criteria. "Enough exploration" is meaningless if it's not tied to a number of experiments, a time budget, or a plateau criterion.
- Soft on stage boundaries being fuzzy. It's legitimate to say "the planning phase decides when to move from exploration to selection" — the loop can make that call each replan.
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.
- 11d ago First seen · 103 lines · 76 tokens per session scan A 0bb10e7680f1
grill-me-data-science is a skill published in the GitHub repository haakonbull/autosprint (5 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,720 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…