AI Prd Builder
Interviews you section by section (Discover, Design, Develop, Deploy) and writes a complete PRD.md for a product that uses AI or agents, then checks it against a living checklist that is kept outside the skill and produces a pass/fail report. Also upgrades an existing PRD. Use this skill whenever the user mentions writing a PRD, a product requirements doc, a spec for an AI or agent product, upgrading a PRD for agents, checking a PRD against the checklist, or turning a one-pager or 6-pager into a PRD.md, even if they do not name the skill. Not for engineering design docs, writing code, or PRDs
Install
npx skills add initmahesh/ai-prd-builder --skill ai-prd-buildergit clone --depth 1 https://github.com/initmahesh/ai-prd-builder.git /tmp/ai-prd-builder
mkdir -p ~/.claude/skills
cp -r /tmp/ai-prd-builder/ai-prd-builder ~/.claude/skills/ai-prd-builderPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AI PRD Builder Version: 1.1 Owner: Mahesh Yadav Updated: 2026-10-22 History: see CHANGELOG.md ## 1. Purpose and scope **Outcome:** one PRD.md for an AI product, written from a section-by-section interview and checked against the living checklist, plus a pass/fail report. The unit of value is one checked PRD. **In scope:** a new PRD from an idea; upgrading an existing PRD; checking a PRD against the checklist; proposing checklist updates after a run. **Anti-patterns (do not):** - Write a fact, number, quote or competitor claim without a source or a "proposed" label. People act on PRDs, so a wrong number spreads. - Invent evidence: interview quotes, customer names, market figures. Leave it as a SET item instead. - Reuse details from another user's product (the contract example in `references/example-prd.md` is a pattern, never content). - Copy the checklist into this skill or work from memory of it. Read the file at `CHECKLIST_PATH` every run, because the user edits it between runs. - Change the checklist file without the user's approval at CP5. - Drop, blank out or fake a required section. Tag missing data visibly instead. - Put secrets, confidential data or personal data in any file or in memory. - Edit this skill's own files or config. Feedback goes to the feedback log, and the owner updates the skill through the skill creator (section 13). ## 2. Triggers and inputs
Details
- Skill name
ai-prd-builder- Repository
- initmahesh/ai-prd-builder
- Path
ai-prd-builder/SKILL.md- Repo updated
- 23 October 2026
FAQ
What does the AI Prd Builder skill do?
Interviews you section by section (Discover, Design, Develop, Deploy) and writes a complete PRD.md for a product that uses AI or agents, then checks it against a living checklist that is kept outside the skill and produces a pass/fail report. Also upgrades an existing PRD. Use this skill whenever the user mentions writing a PRD, a product requirements doc, a spec for an AI or agent product, upgrading a PRD for agents, checking a PRD against the checklist, or turning a one-pager or 6-pager into a PRD.md, even if they do not name the skill. Not for engineering design docs, writing code, or PRDs
How do I install the AI Prd Builder skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add initmahesh/ai-prd-builder --skill ai-prd-builder. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Prd Builder popular?
It lives in initmahesh/ai-prd-builder, which has 10 GitHub stars and 10 forks.
Related skills
Attack Tree Modeling
48sethdford/claude-skills
Build hierarchical attack trees showing how attackers decompose goals into sub-goals and exploits. Use when analyzing attack paths, prioritizing security investments, or assessing attacker effort and cost.
Time Series Anomaly Detection
49UCSB-NLP-Chang/Skill-Usage
Detect anomalies in time series data using Prophet Framework (Meta), which frames the seasonality, trend holiday effect and other needed regressors into its model, to identify unusual surges or slumps in trends. This is a general methodology analyst can use for understanding what changes of their tracking metrics are manifesting anomalies pattern.
C4 Model Diagram
48sethdford/claude-skills
Create C4 context, container, component, and code diagrams. Visualize architecture at different abstraction levels. Use when communicating system structure to diverse audiences.
Speaker Clustering Methods
49UCSB-NLP-Chang/Skill-Usage
Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown, KMeans when count is known, and always normalize embeddings before clustering.
Concurrency Patterns
48sethdford/claude-skills
Actor model, CSP (Communicating Sequential Processes), lock-free patterns, async/await.
Seisbench Model API
49UCSB-NLP-Chang/Skill-Usage
An overview of the core model API of SeisBench, a Python framework for training and applying machine learning algorithms to seismic data. It is useful for annotating waveforms using pretrained SOTA ML models, for tasks like phase picking, earthquake detection, waveform denoising and depth estimation. For any waveform, you can manipulate it into an obspy stream object and it will work seamlessly with seisbench models.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.