AI Feature Definition
Write a complete AI feature specification that defines desired model behaviour, input/output examples, confidence thresholds, fallback logic, and non-functional requirements. Use when defining requirements for an AI-powered feature, writing an AI PRD, or bridging the gap between PM intent and ML team implementation.
Install
/plugin marketplace add tarunccet/pm-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add tarunccet/pm-skills --skill ai-feature-definitiongit clone --depth 1 https://github.com/tarunccet/pm-skills.git /tmp/pm-skills
mkdir -p ~/.claude/skills
cp -r /tmp/pm-skills/pm-ai-product-management/skills/ai-feature-definition ~/.claude/skills/ai-feature-definitionPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
## AI Feature Definition Create a comprehensive AI feature specification that accounts for probabilistic outputs, defines desired behaviour with examples, and establishes evaluation criteria. ### Context You are writing an AI feature specification for **$ARGUMENTS**. ### Instructions ### Phase 0: Context Confirmation Before proceeding, confirm your understanding of the request: 1. **Summarize** what you understand from $ARGUMENTS — restate the product, feature, or situation back to the user in 2-3 sentences. 2. **Identify gaps** — check whether the following are clear (ask if not): - What AI capability is this feature using (e.g., generation, classification, summarization)? - Who is the target user? - What does a successful output look like? - What should happen when the model fails or produces low-confidence output? 3. **Confirm**: _"Here's my understanding: [summary]. I plan to produce a complete AI feature specification covering desired behaviour, input/output examples, confidence thresholds, fallback logic, and non-functional requirements. Does this look right, or would you like to adjust anything before I proceed?"_ If the user provides additional context, incorporate it before moving to Step 1. If the user confirms, proceed. 1. **Understand the feature context**: - What user problem does this AI feature solve? - What are the inputs? (text, image, structured data, user history, documents)
Details
- Skill name
ai-feature-definition- Repository
- tarunccet/pm-skills
- Path
pm-ai-product-management/skills/ai-feature-definition/SKILL.md- License
- MIT
- Repo updated
- 13 November 2026
FAQ
What does the AI Feature Definition skill do?
Write a complete AI feature specification that defines desired model behaviour, input/output examples, confidence thresholds, fallback logic, and non-functional requirements. Use when defining requirements for an AI-powered feature, writing an AI PRD, or bridging the gap between PM intent and ML team implementation.
How do I install the AI Feature Definition skill?
Claude Code plugin: /plugin marketplace add tarunccet/pm-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Feature Definition popular?
It lives in tarunccet/pm-skills, which has 9 GitHub stars and 2 forks.
Related skills
Ab Test Analysis
9tarunccet/pm-skills
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
Adr
9tarunccet/pm-skills
Document architecture and product decisions using the Nygard ADR format — captures context, alternatives considered, and consequences so the team never asks 'why did we do it this way?' again. Use when making architecture decisions, choosing between technical approaches, selecting vendors, or any decision that will be hard to reverse.
AI Build Buy Partner
9tarunccet/pm-skills
Evaluate AI capability sourcing options across build, buy, fine-tune, and partner archetypes using a structured decision matrix. Use when deciding whether to build a custom model, use an LLM API, fine-tune a base model, or partner with an AI vendor.
AI Incident Response
9tarunccet/pm-skills
Handle AI model failures, quality regressions, bias incidents, and safety issues with a structured response runbook. Use when an AI feature produces harmful outputs, when model quality degrades in production, or when preparing an incident response plan for an AI system.
AI Data Strategy
9tarunccet/pm-skills
Define a data strategy for AI products covering training data requirements, data quality, labeling strategy, feedback loops, and continuous retraining. Use when assessing data readiness for an AI feature, designing a data flywheel, or planning an ML data pipeline.
AI Model Evaluation
9tarunccet/pm-skills
Evaluate and compare LLMs, ML APIs, and fine-tuned models for product fit across quality, latency, cost, compliance, and vendor risk dimensions. Use when selecting an AI model or vendor, comparing foundation model options, or making build-vs-API decisions for a product use case.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.