kentoshimizu/sw-agent-skills/ml-problem-framing
Claude Code and agent skill by kentoshimizu/sw-agent-skills
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
ML problem framing workflow for objective definition, target variable design, and success criteria. Use when translating business problems into ML tasks and objective/label/metric definitions are still ambiguous; do not use for generic API-layer or infrastructure-only changes.
Install
npx vskill@latest install kentoshimizu/sw-agent-skills/ml-problem-framingSKILL.md
Ml Problem Framing
Overview
Use this skill to define an ML problem that supports a real product decision with measurable outcomes.
Scope Boundaries
- Use this skill when the task matches the trigger condition described in
description. - Do not use this skill when the primary task falls outside this skill's domain.
Shared References
- Objective and labeling rules:
references/objective-and-labeling-rules.md
Templates And Assets
- Problem framing template:
assets/problem-framing-template.md
Inputs To Gather
- Business decision to support and value target.
- Candidate prediction target and labeling source.
- Risk constraints (fairness, latency, compliance).
- Baseline process and non-ML alternatives.
Deliverables
- Framed ML objective with explicit non-goals.
- Label definition and prediction unit.
- Success metrics and decision thresholds.
- Risks and assumptions log.
Workflow
- Define decision context with
assets/problem-framing-template.md. - Validate objective/label choices using
references/objective-and-labeling-rules.md. - Align metric choices to business and user outcomes.
- Document assumptions, constraints, and alternatives.
- Publish go/no-go framing decision.
Quality Standard
- Objective is measurable and decision-relevant.
- Label definition is leakage-safe and reproducible.
- Metrics and thresholds are operationally actionable.
Failure Conditions
- Stop when objective does not map to a concrete decision.
- Stop when label quality/timing cannot be validated.
- Escalate when framing risks exceed policy tolerance.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/ml-problem-framing/SKILL.md
Popularity
- Repository stars
- 5
- 7-day trend score
- 9
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 8 Apr 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kentoshimizu/sw-agent-skills/ml-problem-framing)