Datasets
Arize-ai/phoenix
Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments.
Pick which precise covariance estimator to use for a given dataset.
MITAuto-check passed
Install Choose Covariance Estimator
$ npx skills add microprediction/precise --skill choose-covariance-estimator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microprediction/precise choose-covariance-estimator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/microprediction/precise.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/choose-covariance-estimator .claude/skills/choose-covariance-estimator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "choose-covariance-estimator" agent skill from https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimator into .claude/skills/choose-covariance-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "choose-covariance-estimator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add microprediction/precise --skill choose-covariance-estimator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microprediction/precise choose-covariance-estimator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microprediction/precise.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/choose-covariance-estimator .agents/skills/choose-covariance-estimator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "choose-covariance-estimator" agent skill from https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimator into .agents/skills/choose-covariance-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "choose-covariance-estimator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microprediction/precise --skill choose-covariance-estimator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microprediction/precise choose-covariance-estimator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microprediction/precise.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/choose-covariance-estimator .cursor/skills/choose-covariance-estimator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "choose-covariance-estimator" agent skill from https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimator into .cursor/skills/choose-covariance-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "choose-covariance-estimator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/microprediction/precise.git --path .claude/skills/choose-covariance-estimator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add microprediction/precise --skill choose-covariance-estimator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microprediction/precise choose-covariance-estimator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microprediction/precise.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/choose-covariance-estimator .gemini/skills/choose-covariance-estimator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "choose-covariance-estimator" agent skill from https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimator into .gemini/skills/choose-covariance-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "choose-covariance-estimator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install microprediction/precise choose-covariance-estimatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add microprediction/precise --skill choose-covariance-estimator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microprediction/precise.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/choose-covariance-estimator .github/skills/choose-covariance-estimator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "choose-covariance-estimator" agent skill from https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimator into .github/skills/choose-covariance-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "choose-covariance-estimator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microprediction/precise --skill choose-covariance-estimator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microprediction/precise choose-covariance-estimator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microprediction/precise.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/choose-covariance-estimator .opencode/skills/choose-covariance-estimator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "choose-covariance-estimator" agent skill from https://github.com/microprediction/precise/tree/main/.claude/skills/choose-covariance-estimator into .opencode/skills/choose-covariance-estimator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "choose-covariance-estimator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
choose-covariance-estimator- GitHub stars
- 337
- Token cost
- ~482 tokens
- SKILL.md length
- 163 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Pick which precise covariance estimator to use for a given dataset.
- A given dataset
- SKILL.md covers What it keys on and Guardrail (important)
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- You have data X and are unsure which estimator fits its dimension
What it does
Choose Covariance Estimator is an agent skill from microprediction/precise. Pick which precise covariance estimator to use for a given dataset. Use when you have data X and are unsure which estimator fits its dimension, conditioning, or tail behavior. Wraps precise.suggest() and covariancefeatures().
Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Online Covariance and Correlation Estimation. The licence is MIT.
When your agent uses it
- A given dataset
- You have data X and are unsure which estimator fits its dimension
Example prompts
- “/choose-covariance-estimator”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 2a193c0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Choose Covariance Estimator loads about 482 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 163 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from microprediction/precise at commit 2a193c0, republished under its MIT licence (© microprediction). 163 words, ~482 tokens.
Download SKILL.mdSave it as
.claude/skills/choose-covariance-estimator/SKILL.md (or your agent's skills folder).- name
- choose-covariance-estimator
- description
- Pick which precise covariance estimator to use for a given dataset. Use when you have data X and are unsure which estimator fits its dimension, conditioning, or tail behavior. Wraps precise.suggest() and covariance_features().
Choose a covariance estimator for your data
No estimator wins everywhere, so precise recommends one from observable, truth-free features.
from precise import suggest, covariance_features
suggest(X, top=3) # -> list of estimator CLASSES, best first
covariance_features(X) # -> dict of the features behind the choiceX is 2-D (rows = observations, columns = variables). Then:
Est = suggest(X, top=1)[0]
est = Est()
est.fit(X) # or stream rows with partial_fit
cov = est.covariance_What it keys on
covariance_features(X) returns p, n, p_over_n, effective_rank, sphericity,
condition_number, mean_abs_offdiag_corr, avg_excess_kurtosis — all computed from the sample, none
requiring the unknown truth. Internally suggest uses a frozen, numpy-only decision tree; broadly it
routes high p/n or ill-conditioned data to shrinkage/factor estimators and heavy-tailed data to robust
ones.
Guardrail (important)
suggest is a heuristic trained on synthetic regimes. In leave-one-generative-family-out tests it does
not reliably beat the single best fixed estimator on a wholly novel data-generating family — it
generalizes across samples within familiar regimes, not to arbitrarily new structure. So:
- Treat its output as a strong shortlist, not an oracle.
- If the decision matters, verify the shortlist out-of-sample on your own data with the score-covariance-estimate skill, rather than trusting the recommendation blind.
- A well-conditioned shrinkage estimator (
LedoitWolfCovariance/OASCovariance) is a safe default when in doubt.
© microprediction, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/choose-covariance-estimator of microprediction/precise.
Open the folder on GitHubat commit 2a193c0
Compare with similar skills
Choose Covariance Estimator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Choose Covariance Estimator this skillmicroprediction/precise | 337 | — | ~482 | Automated safety check: Pass | MIT | |
| DatasetsArize-ai/phoenix | 12k | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Flutter Cherry Pickflutter/flutter | 180k | — | ~1.8k | Automated safety check: Pass | BSD-3-Clause | |
| Task Effort EstimatorDonchitos/Claude-Code-Game-Studios | 26k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Progressive Estimationsickn33/agentic-awesome-skills | 47k | 2 repos | ~863 | Automated safety check: Pass | MIT | |
| Dataset Curationwshobson/agents | 40k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Flutter Cherry Pick
flutter/flutter
How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel.
Task Effort Estimator
Donchitos/Claude-Code-Game-Studios
Estimates the effort for a game development task from code complexity, scope, risk and past sprint data, returning a range with a confidence level.
Progressive Estimation
sickn33/agentic-awesome-skills
Estimate AI-assisted and hybrid human+agent development work with research-backed PERT statistics and calibration feedback loops
Dataset Curation
wshobson/agents
Prepare, format, and validate datasets for supervised fine-tuning and preference training.
- Official
Arize Dataset
github/awesome-copilot
Creates, manages, and queries Arize datasets and examples. An agent skill from github/awesome-copilot.
More from microprediction/precise
Estimate Online Covariance
microprediction/precise
Estimate a covariance / correlation / precision matrix incrementally with precise.
Keyed Dynamic Universe
microprediction/precise
Maintain an online covariance over named series whose set changes over time (e.g.
Precise
microprediction/precise
Online (incremental) covariance, correlation, and precision estimation in Python — the streaming complement to sklearn.covariance.
Score Covariance Estimate
microprediction/precise
Score and compare covariance estimates with precise's assessor panel.
Assess Covariance Method
microprediction/precise
Rigorously and honestly assess a NEW or proposed covariance / correlation / precision estimator, or a new covariance scoring rule, using precise.
Questions about Choose Covariance Estimator
What does Choose Covariance Estimator do?
Pick which precise covariance estimator to use for a given dataset. Choose Covariance Estimator is an agent skill from microprediction/precise. Pick which precise covariance estimator to use for a given dataset.
When should I use Choose Covariance Estimator?
Choose Covariance Estimator fits situations like: A given dataset; you have data X and are unsure which estimator fits its dimension.
How do I install Choose Covariance Estimator in Claude Code?
Run `npx skills add microprediction/precise --skill choose-covariance-estimator -a claude-code`. Or copy the skill folder (.claude/skills/choose-covariance-estimator in microprediction/precise) into .claude/skills/choose-covariance-estimator in your project. Claude Code loads it when a task matches its description.
How do I install Choose Covariance Estimator in Codex?
Run `npx skills add microprediction/precise --skill choose-covariance-estimator -a codex`. Or copy the skill folder (.claude/skills/choose-covariance-estimator in microprediction/precise) into .agents/skills/choose-covariance-estimator in your project. Codex loads it when a task matches its description.
Can I use Choose Covariance Estimator in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microprediction/precise --skill choose-covariance-estimator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/choose-covariance-estimator, .gemini/skills/choose-covariance-estimator, .github/skills/choose-covariance-estimator and .opencode/skills/choose-covariance-estimator in your project.
What does Choose Covariance Estimator need to run?
SKILL.md names no scripts, command-line tools or credentials: Choose Covariance Estimator is instructions for the agent only. Our summary lists: Python 3.
Does Choose Covariance Estimator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Choose Covariance Estimator safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Choose Covariance Estimator use?
Choose Covariance Estimator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Choose Covariance Estimator use?
About 482 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Choose Covariance Estimator?
Skills that share tags, products or a category with Choose Covariance Estimator: Datasets (Arize-ai/phoenix, 12k stars), Flutter Cherry Pick (flutter/flutter, 180k stars), Task Effort Estimator (Donchitos/Claude-Code-Game-Studios, 26k stars) and Progressive Estimation (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Choose Covariance Estimator?
microprediction (a GitHub user) maintains it in microprediction/precise, which has 337 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 6, 2026.
Source: microprediction/precise on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.