don-cheli-sdd: Skill for Claude Code

.agent/skills/doncheli-prd/SKILL.md

doncheli-prd is a skill for Claude Code from doncheli/don-cheli-sdd. It costs 81 tokens per session (1,155 once invoked), scanned A, original, Apache-2.0.

A product requirements document generator that combines design files, briefs, user research, existing code, and conversation details. A PRD is a document describing what a product or feature should do and how its success and risks will be assessed.

In plain words
What is it for?
Use it to turn Figma screens into user stories and acceptance criteria, assess technical, product, UX, business, legal, security, and operational risks, and create a launch plan with priorities.
Why use it?
It brings scattered product and technical information into one plan. It also highlights missing interface states, edge cases, constraints, and risks before development starts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

This is doncheli/don-cheli-sdd's own configuration. It tells Claude Code how to work on don-cheli-sdd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything don-cheli-sdd configures →

Part of the don-cheli-sdd plugin — 28 skills, 115 commands, 1 agent shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to doncheli/don-cheli-sdd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/doncheli/don-cheli-sdd/main/.agent/skills/doncheli-prd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/doncheli/don-cheli-sdd

Made for: Claude Code.

Or install don-cheli-sdd, the plugin that ships this one along with the rest of its 28 skills, 115 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for doncheli-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-prd/github.svg)](https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-prd)
Your own site
<a href="https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-prd"><img src="https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-prd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for doncheli-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/doncheli/don-cheli-sdd/doncheli-prd"><img src="https://agentmods.dev/badge/skills/doncheli/don-cheli-sdd/doncheli-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01155
Opus 5 $0.00041 $0.00577
Sonnet 5 $0.00016 $0.00231
Haiku 4.5 $0.00008 $0.00115

Measured 10d ago against content hash 271778034e35, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

doncheli-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agent/skills/doncheli-prd/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Don Cheli: PRD Generator

Instructions

  1. Discover sources — Identify all available inputs:

    • Figma links: analyze screens, flows, components, missing states
    • Brief documents: extract objectives, audience, problems
    • User research: identify personas, JTBD, pain points
    • Existing code: detect technical constraints
    • Conversation context: extract requirements mentioned by the user
  2. Analyze Figma (if provided):

    • Count screens/frames and map navigation flow
    • Extract texts, labels, form fields, interactions
    • Detect missing UI states: loading, empty, error, success, offline
    • Identify gaps: flows not designed, edge cases missing
    • Convert each screen → user stories → acceptance criteria
  3. Risk analysis — For each feature, evaluate 7 risk categories:

    • Technical (complexity, integrations, tech debt)
    • Product (market fit, adoption, competition)
    • UX (usability, accessibility, learning curve)
    • Business (revenue, cost, time-to-market)
    • Legal (GDPR, compliance, ToS)
    • Security (OWASP, sensitive data, auth)
    • Operational (support, scalability, monitoring)
    • Assign probability (Low/Medium/High) and impact (Low/Medium/High/Critical)
    • Propose mitigation for each risk
  4. Prioritize features using MoSCoW + RICE:

    • MoSCoW: Must / Should / Could / Won't
    • RICE: (Reach × Impact × Confidence) / Effort
    • Rank features by RICE score
  5. Generate PRD with 13 sections:

    1. Executive Summary
    2. Problem (context, pain points, evidence)
    3. Objectives & Success Metrics (KPIs, North Star)
    4. Target Audience (personas, JTBD, user journey)
    5. Proposed Solution (overview, main flow, features by priority)
    6. Detailed Requirements (functional with Gherkin, non-functional, integrations, data model)
    7. Design & UX (Figma analysis, UI states, responsive, accessibility)
    8. Risk Analysis (matrix, mitigations, dependencies)
    9. Scope (in scope, out of scope, future iterations)
    10. Timeline & Milestones
    11. Competitive Analysis
    12. Launch Plan (rollout, monitoring, rollback)
    13. Appendices (glossary, references, change history)

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 118 lines · 81 tokens per session scan A 271778034e35

Subscribe to this mod's changes

doncheli-prd is a skill published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,155 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.