Writer Perspective Distiller

PassAudited by ClawScan on May 6, 2026.

Overview

This is an instruction-only writing-analysis skill with clear human checkpoints, but users should review any generated skill before installing it and avoid putting private correspondence or sensitive biography into persistent prompts.

This skill appears safe to use as an instruction-only analysis workflow. Before installing any generated SKILL.md, review it for unwanted instructions, plagiarism risk, and sensitive personal or organizational details. Do not include private correspondence or confidential material unless you are comfortable having it distilled into a reusable local writing prompt.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If the generated SKILL.md contains bad or overbroad instructions, installing it could influence future writing sessions.

Why it was flagged

The skill is designed to generate another callable skill for installation, which can affect future agent behavior. This is disclosed and user-directed, not hidden.

Skill content
Drop it back into `~/.claude/skills/<author-slug>-perspective/SKILL.md` and call it during writing.
Recommendation

Read the generated SKILL.md before installing it, keep it local when appropriate, and remove or edit any instructions that are too broad or not aligned with your intended use.

What this means

Private correspondence, personal biography, or confidential brand voice material could be summarized into a persistent prompt if the user includes it.

Why it was flagged

The workflow asks for potentially sensitive author materials and turns the analysis into a reusable skill, creating persistent context that may be reused later.

Skill content
provide: ... Non-fiction / essays / interviews / correspondence ... Biographical context ... finally output a SKILL.md ready to load.
Recommendation

Use only materials you are allowed to process, omit private details that are not needed, and keep generated skills marked local/private when they contain sensitive context.