Skip to content

aiopshwang/data-analysis-ml-agent-skills / skills/using-data-analysis

using-data-analysis

Unverified

Route data analysis and machine learning work to the right skill in this suite. Use when starting any analysis, modeling, validation, or reproducibility task and the matching specialized skill is not yet clear; not needed when one specific skill already clearly applies.

Using Data Analysis Skills

Pick the narrowest skill that covers the current task. When the work spans multiple lifecycle stages, start from the orchestrator and let it call the others.

SituationSkill
An end-to-end project or an ambiguous modeling requestrunning-decision-grade-data-science
Data meaning, joins, labels, or ground truth may be untrustworthyauditing-data-and-ground-truth
Designing splits, feature eligibility, baselines, or comparisonsdesigning-leakage-safe-experiments
A metric dropped, results disagree, or training-serving mismatchdiagnosing-ml-failures
Reviewing whether results support a claim or launch decisionvalidating-models-and-claims
Packaging finished work for independent reproductionshipping-reproducible-results

Each skill states its own non-goals in its description; respect them. The orchestrator running-decision-grade-data-science already routes to the other five at the right lifecycle stage, so do not stack it with them manually for the same step.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 464kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 464kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 318kUpdated Claude CodeCodexUnverifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 318kUpdated Claude CodeCodexUnverifiedInstall