CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-writer

The Spec Writer specialist for Headout's PM OS. Use this skill to write a full, production-ready PRD for any feature, experiment, or product change at Headout. This is not a template filler — it is a deliberate, scenario-forcing, hypothesis-anchored spec writer that produces documents detailed enough for an engineering agent (Cursor / Plato) to implement from and rigorous enough to pass Atish's L1 review gate. Trigger this skill whenever a PM needs to write a spec, PRD, or requirements doc. Also trigger when a PM says "I want to document this feature", "can you write up the requirements for X", "help me write a PRD", or when a Problem Frame + any additional inputs (data insights, prototype) are ready to be turned into a formal spec. The Spec Writer prefers a Problem Frame as input. If none exists, the skill will run a compressed problem-framing pass before writing — it never writes a spec without first establishing why we're doing this, what the objective is, and how success will be measured. The output follows Headout's standard PRD template (Problem Alignment → Solution → Execution Plan → Open Questions → Working Log → Change Log).

Invalid
This skill can't be scored yet
Validation errors are blocking scoring. Review and fix them to unlock Quality, Impact and Security scores. See what needs fixing →
SKILL.md
Quality
Evals
Security

Security

1 medium severity finding. This skill can be installed but you should review these findings before use.

Medium

W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection)

What this means

Detected hidden or invisible Unicode characters (Format/Cf or Control/Cc categories) in the component’s content. These characters are invisible when rendered but are still processed by AI models, and attackers use them to smuggle instructions past human review — for example, zero-width spaces, bidirectional overrides, invisible formatters, or Unicode Tag characters (U+E0000–U+E007F) that encode an entire hidden message. Severity escalates to high when three or more distinct hidden character types are present, or when a hidden tag-encoded message is successfully decoded, as these strongly indicate intentional obfuscation.

Why it was flagged

Hidden Unicode characters detected (1 type(s) found)

Report incorrect finding
Repository
headout/pm-os-marketplace
Audited
Security analysis
Snyk

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.