CtrlK
BlogDocsLog inGet started
Tessl Logo

l1-reviewer

The L1 Reviewer is the quality gate for all product specs at Headout before they reach Atish. Use this skill to review any PRD, spec, or requirements document for completeness, logical soundness, scenario coverage, metric clarity, and design coherence. Structured critique, not a polish pass. Rejects incomplete specs with specific, actionable failure reasons. A passing spec is ready for Atish. A failing spec returns to the PM with exactly what needs fixing. Trigger for: "review this PRD", "is this spec good enough", "L1 check", "review before I send to Atish", or whenever the Spec Writer finishes a draft. Checks both the LOGIC layer (scenario coverage, metric rigor, AC quality) and the DESIGN layer (design coherence, prototype alignment).

91

1.26x
Quality

88%

Does it follow best practices?

Impact

99%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

4%

Reviewing a PRD for Search Ranking Improvements

Metrics and AC quality review

Criteria
Without context
With context

FAIL verdict

100%

100%

Blocking vs non-blocking separated

100%

100%

Unquantified metrics flagged

100%

100%

Measurement method missing

100%

100%

Guardrail metrics absent

100%

100%

AC format flagged

100%

100%

AC observable behavior

100%

100%

Anti-scope missing

100%

100%

Scope platform missing

100%

100%

Specific failure notes

100%

100%

Open questions lacking owners

66%

100%

Resubmit checklist present

66%

100%

Strengths acknowledged

100%

100%

100%

39%

Reviewing a Mobile Checkout Redesign PRD

Scope integrity and scenario coverage

Criteria
Without context
With context

FAIL verdict

100%

100%

Anti-scope insufficient

83%

100%

Platform disambiguation missing

60%

100%

Logged-out user state missing

100%

100%

Empty state not defined

33%

100%

Boundary condition absent

12%

100%

Non-GIVEN/WHEN/THEN ACs flagged

77%

100%

Hidden assumption in scope

37%

100%

Open questions lack owners

0%

100%

Blocking vs non-blocking separated

28%

100%

Resubmit checklist present

100%

100%

Strengths acknowledged

16%

100%

Specific failure notes

100%

100%

Measurement window noted

100%

100%

99%

21%

Reviewing a Wishlist Feature PRD

Design review layer completeness

Criteria
Without context
With context

Design layer reviewed

100%

100%

Component library reference flagged

0%

100%

UI states insufficient for designer

91%

100%

Interaction patterns absent

80%

100%

Edge case design descriptions missing

90%

90%

Mobile-first considerations checked

50%

100%

Logic layer strengths recognized

75%

100%

FAIL or PASS verdict present

100%

100%

Blocking vs non-blocking separated

100%

100%

Failure notes specific to design

100%

100%

Resubmit checklist present on FAIL

100%

100%

Repository
headout/pm-os-marketplace
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.