CtrlK
BlogDocsLog inGet started
Tessl Logo

to-prd

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

73

1.50x
Quality

58%

Does it follow best practices?

Impact

98%

1.50x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/to-prd/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

50%

Notification Preferences Feature PRD

PRD template structure and section content

Criteria
Without context
With context

Problem Statement section

62%

100%

Solution section

12%

100%

User Stories section present

50%

100%

User story format

100%

100%

Extensive user stories

62%

100%

Implementation Decisions section

37%

100%

No file paths in Implementation Decisions

50%

100%

Testing Decisions section

50%

100%

Good test definition

0%

100%

Modules to test listed

66%

100%

Out of Scope section

62%

100%

Further Notes section

0%

100%

No file creation instructions leaked

100%

100%

95%

7%

Search and Filtering System PRD

Module planning with deep modules and no user interviewing

Criteria
Without context
With context

Module plan file created

100%

100%

Deep module language used

100%

100%

Modules described with interfaces

100%

100%

No user questions

100%

100%

PRD Testing Decisions present

100%

100%

External behavior test definition

33%

100%

Modules to test listed in PRD

100%

100%

Implementation Decisions in PRD

100%

100%

No file paths in Implementation Decisions

50%

37%

User Stories section present

100%

100%

Out of Scope section present

100%

100%

100%

43%

Card Comments Feature PRD

Domain vocabulary, ADR compliance, needs-triage label

Criteria
Without context
With context

Domain terms in PRD

100%

100%

ADR-001 respected

100%

100%

ADR-002 respected

100%

100%

No user questions

100%

100%

needs-triage label named

0%

100%

Problem Statement section

0%

100%

User Stories section

100%

100%

Implementation Decisions section

0%

100%

Testing Decisions section

0%

100%

Out of Scope section

100%

100%

Further Notes section

0%

100%

Repository
coder/agent-tty
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.