GitHub organization
Agent skills by probabl-ai
- skills
- 23
- repository
- 1
Repositories by probabl-ai
Skills by probabl-ai, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Add a Python dependency through the project env manager, or ask the user to install it when env.managed is false. | probabl-ai/ | 135 | — | ~1.8k | Automated safety check: Pass | BSD-3-Clause | today |
| 2 | Declare the pipeline from data source to predictor as a skrub DataOps graph. | probabl-ai/ | 135 | — | ~4k | Automated safety check: Pass | BSD-3-Clause | today |
| 3 | Evaluate one learner with skore.evaluate. An agent skill from probabl-ai/skills. | probabl-ai/ | 135 | — | ~4.2k | Automated safety check: Pass | BSD-3-Clause | today |
| 4 | Detect an existing ML workspace or scaffold a fresh one via python -m skoreskills scaffold --package <pkg. | probabl-ai/ | 135 | — | ~1.5k | Automated safety check: Pass | BSD-3-Clause | today |
| 5 | Read-only audit of one persisted skore report: audit/NN<stem.py (jupytext percent), 1:1 with experiments/ and journal/. | probabl-ai/ | 135 | — | ~9.5k | Automated safety check: Pass | BSD-3-Clause | today |
| 6 | Owns data understanding before any model is designed. An agent skill from probabl-ai/skills. | probabl-ai/ | 135 | — | ~5.7k | Automated safety check: Pass | BSD-3-Clause | today |
| 7 | Convert a jupytext percent %% Python file into an executed .ipynb with cell outputs. | probabl-ai/ | 135 | — | ~1k | Automated safety check: Pass | BSD-3-Clause | today |
| 8 | Set up git for an ML workspace after scaffolding. An agent skill from probabl-ai/skills. | probabl-ai/ | 135 | — | ~1.4k | Automated safety check: Notes | BSD-3-Clause | today |
| 9 | Copy skore reports between local, Hub, and MLflow with skore sync, and optionally switch the recorded upload destination. | probabl-ai/ | 135 | — | ~1.6k | Automated safety check: Pass | BSD-3-Clause | today |
| 10 | Lock the problem, the deployment setting, the comparison metric, the baseline, and the fold count in the journal before any model code. | probabl-ai/ | 135 | — | ~2.1k | Automated safety check: Pass | BSD-3-Clause | today |
| 11 | Pick how to write a figure before custom plot code. An agent skill from probabl-ai/skills. | probabl-ai/ | 135 | — | ~785 | Automated safety check: Pass | BSD-3-Clause | today |
| 12 | Literature and web research for an ML methodology concern (EDA extra measurements, leakage, transforms, feature engineering, learner family), or an EDA extra-analysis survey from JOURNAL plus… | probabl-ai/ | 135 | — | ~1.1k | Automated safety check: Pass | BSD-3-Clause | today |
| 13 | Owns one experiment's smoke test: a small pytest that fits on part of real data/ and predicts on a disjoint slice with no pre-history buffer. | probabl-ai/ | 135 | — | ~6k | Automated safety check: Pass | BSD-3-Clause | today |
| 14 | Resolve a genuine choice between Python libraries for one job, then ask add-python-package to add the chosen dependency. | probabl-ai/ | 135 | — | ~501 | Automated safety check: Pass | BSD-3-Clause | today |
| 15 | Coordinate on-demand export: executed notebooks and/or an offline MkDocs documentation site. | probabl-ai/ | 135 | — | ~505 | Automated safety check: Pass | BSD-3-Clause | today |
| 16 | Package JOURNAL, exploratory data analysis markdown, and design notes into an offline MkDocs site opened via report.html at the workspace root. | probabl-ai/ | 135 | — | ~1.2k | Automated safety check: Pass | BSD-3-Clause | today |
| 17 | Canonical backlog loop step. An agent skill from probabl-ai/skills. | probabl-ai/ | 135 | — | ~3.3k | Automated safety check: Pass | BSD-3-Clause | today |
| 18 | Show the project choices already stored in status and let the user change one by re-entering the skill that owns it. | probabl-ai/ | 135 | — | ~777 | Automated safety check: Pass | BSD-3-Clause | today |
| 19 | Post-evaluate review. An agent skill from probabl-ai/skills. | probabl-ai/ | 135 | — | ~1.1k | Automated safety check: Pass | BSD-3-Clause | today |
| 20 | Search scientific and technical sources for a query and, after the user picks and confirms one direction, write one idea file and its Ideas row. | probabl-ai/ | 135 | — | ~872 | Automated safety check: Pass | BSD-3-Clause | today |
| 21 | Shape an idea the user already has, or answer a project question, and write one idea file and its Ideas row after they confirm. | probabl-ai/ | 135 | — | ~980 | Automated safety check: Pass | BSD-3-Clause | today |
| 22 | Session owner: list installed entry skills and ask which to run. | probabl-ai/ | 135 | — | ~2.2k | Automated safety check: Pass | BSD-3-Clause | today |
| 23 | Persist the current loop stage with the real git CLI when the end-turn hook says invoke. | probabl-ai/ | 135 | — | ~683 | Automated safety check: Notes | BSD-3-Clause | today |
Questions, answered from the data.
What is the best skill by probabl-ai?
Add Python Package from probabl-ai/skills ranks first of the 23 skills by probabl-ai listed here, with the highest score: its repository has 135 GitHub stars, its SKILL.md loads about 1.8k tokens and it passes the automated safety check with no findings. Next come Build ML Pipeline and Evaluate ML Pipeline.
Are probabl-ai's skills official?
None yet. All 23 skills by probabl-ai listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.