Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add QinghongLin/data2story-skill --skill ideationgit clone --depth 1 https://github.com/QinghongLin/data2story-skillWrote 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/qinghonglin/data2story-skill/ideation)<a href="https://agentmods.dev/skills/qinghonglin/data2story-skill/ideation"><img src="https://agentmods.dev/badge/skills/qinghonglin/data2story-skill/ideation/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/qinghonglin/data2story-skill/ideation"><img src="https://agentmods.dev/badge/skills/qinghonglin/data2story-skill/ideation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.01901 |
| Opus 5 | $0.00053 | $0.00950 |
| Sonnet 5 | $0.00021 | $0.00380 |
| Haiku 4.5 | $0.00011 | $0.00190 |
Grade A, and why
ideation 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 9d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideation — from a vague idea to a data-backed topic + a real dataset
The /data2story-pro orchestrator routes here in IDEA MODE: the reader handed over a hunch, a
question, or a half-formed angle instead of a dataset. Your job is to turn that into a concrete
topic that real, findable data can support, fetch that data, and hand a validated folder back to
the pipeline. You do this WITH the reader, not for them — two real checkpoints, no railroading.
You are not a pipeline role (no *_NN provenance prefix, no place in the 7 teams). You run once,
before Detective, and produce nothing that reaches the HTML except the dataset + a story_brief.
Inputs
$1= the reader's raw idea text (may be empty → open by inviting it).$2=DATA2STORY_ROOT(resolved by the orchestrator; wheredata/<slug>/will live).
Return contract (how the orchestrator continues)
- Success: emit a final line
DATA_DIR=<absolute path to the validated dataset folder>. Thestory_brief.jsonsits at<DATA_DIR>/meta/story_brief.json. The orchestrator setsDATA_DIR/DATA_NAMEfrom this and enters the normal pipeline (Detective → … → Inspector). - Abort: emit
IDEATION_ABORTED: <one-line reason>(reader stopped, or no real dataset supports the idea after the bounded loop). The orchestrator halts honestly and runs NO pipeline. Never fabricate data to manufacture a success.
The flow — 3 steps, 2 checkpoints
Interaction style — let the reader CHOOSE, don't make them compose. Drive the convergence
and BOTH checkpoints with AskUserQuestion: frame the angles / scope / data-forks as options the
reader clicks, not paragraphs they must write — picking is far lower-friction and each question
doubles as a micro-checkpoint. ALWAYS keep the Other / free-text escape open: the menu is your
framing, and the reader's own off-menu angle is often the best one, so never let it cage the
brainstorm. (This is NOT the cold opening questionnaire sparring-partner warns against — it is
choice-driven convergence after you have framed the space: lead the very first turn with
substance + an open invite, then switch to options.)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 121 lines · 107 tokens per session scan A e9458dce5679
ideation is a skill published in the GitHub repository QinghongLin/data2story-skill (155 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,901 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
alterlab-pyhealth
Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…
alterlab-pufferlib
Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom…
alterlab-shap
Model interpretability and explainability with SHAP (SHapley Additive exPlanations) — feature importance and plots (waterfall, beeswarm, bar, scatter, force, heatmap). Use when explaining ML model predictions, computing feature importance, debugging models, analyzing bias or fairness, comparing models, or implementing…
alterlab-timesfm
Zero-shot univariate time-series forecasting with Google's TimesFM foundation model, producing point forecasts and prediction intervals from CSV/DataFrame/array inputs, with a preflight system checker for RAM/GPU. Use to forecast any univariate series (sales, sensors, energy, vitals, weather) without training a custom…
alterlab-deepchem
Runs molecular machine learning with DeepChem — diverse featurizers, pre-built MoleculeNet benchmark datasets, and pre-trained models (ChemBERTa, GROVER) for property prediction (ADMET, toxicity, solubility) via traditional ML or graph neural networks. Use when running end-to-end molecular ML experiments that need…