CtrlK
BlogDocsLog inGet started
Tessl Logo

prd

Use when a PM has a rough idea or a written PRD that needs to be structured into the standard format with P0/P1/P2-tagged user stories. Auto-discovers the source doc in the project folder. Use --approved to skip the challenge step.

84

1.85x
Quality

76%

Does it follow best practices?

Impact

100%

1.85x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Evaluation results

100%

57%

Checkout Redesign PRD

Priority tagging and stable US-XX IDs from rough PM notes

Criteria
Without context
With context

Must/required → P0

50%

100%

Should/important → P1

50%

100%

Nice to have → P2

20%

100%

Hedged → [NEEDS TAG]

0%

100%

Stable US-XX IDs

50%

100%

Story format

10%

100%

Correct output path

100%

100%

YAML frontmatter fields

50%

100%

Sections 5-6 as comments

0%

100%

No invented requirements

100%

100%

100%

35%

Personalized Recommendations PRD

AI/ML PRD with Open Questions placeholder and no EA/GA split

Criteria
Without context
With context

AI/ML Open Questions placeholder

33%

100%

Affected Surfaces as comment

0%

100%

Dependencies & Constraints as comment

0%

100%

No EA/GA split

100%

100%

Must/required → P0

100%

100%

Should/important → P1

100%

100%

Nice-to-have → P2

100%

100%

Stable US-XX IDs

100%

100%

Correct output path

100%

100%

YAML frontmatter

0%

100%

100%

44%

Push Notifications PRD

Source doc auto-discovery, output path derivation, and complete story structure

Criteria
Without context
With context

Source doc discovery

100%

100%

Correct output path

100%

100%

YAML frontmatter — all fields

0%

100%

status: draft in frontmatter

0%

100%

US-XX ID format

0%

100%

Must/required → P0

100%

100%

Should/important → P1

100%

100%

Hedged → [NEEDS TAG]

0%

100%

Affected Surfaces placeholder

0%

100%

No invented requirements

100%

100%

No EA/GA split

100%

100%

Repository
PagerDuty/ai-forward-planning
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.