Skills human-writer
πŸ“¦

human-writer

v1.2.0 Content revision r2 Safe βš™οΈ External commands

Polish Drafts While Preserving Your Voice

Automated drafts can sound repetitive or overly polished and may lose the writer's original voice. This skill applies minimal editorial fixes while preserving meaning.

Supports: Claude Codex Code(CC)
πŸ’Ž 90 Featured

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "human-writer" from https://skillstore.io/skills/glenskii-human-writer.md and its manifest at https://skillstore.io/api/skills/glenskii-human-writer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "human-writer". The app serves as a robust platform that streamlines daily reporting.

Expected outcome:

The app is a platform that simplifies daily reporting.

Using "human-writer". Audit this paragraph without editing: Distribution matters. This is the part most people skip.

Expected outcome:

Faux-insight setup: "This is the part most people skip." Suggested fix: remove the setup and keep the concrete claim.

Using "human-writer". Please polish this direct email: I need the revised figures by Thursday. Let me know if you would like more detail.

Expected outcome:

I need the revised figures by Thursday.

Security Audit

Safe
v3 β€’ 8/9/2026 Open versioned report

All 15 static findings are false positives caused by editorial prose, Markdown code spans, or a clear Unicode literal. The bundled script performs local text checks without dynamic commands, network access, or obfuscated behavior.

10
Files scanned
393
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History β†’
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/glenskii-human-writer/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/glenskii-human-writer/security.svg)](https://skillstore.io/skills/glenskii-human-writer?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/glenskii-human-writer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/glenskii-human-writer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/glenskii-human-writer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA Β· BibTeX Β· CFF)

APA citation

glenskii. (2026). human-writer security audit report (audit version 3) [Author version 1.2.0]. Skillstore. https://skillstore.io/skills/glenskii-human-writer/audits/3

BibTeX citation

@techreport{glenskii-glenskii-human-writer-2026, author = {glenskii}, title = {human-writer security audit report (audit version 3)}, institution = {Skillstore}, year = {2026}, number = {3}, url = {https://skillstore.io/skills/glenskii-human-writer/audits/3}, note = {Author version 1.2.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "human-writer security audit report (audit version 3)" version: "1.2.0" type: report authors: - name: "glenskii" date-released: "2026-08-09" url: "https://skillstore.io/skills/glenskii-human-writer/audits/3" identifiers: - type: other value: "skillstore:glenskii-human-writer:audit:3" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
95
Architecture
100
Maintainability
87
Content
65
Community
91
Spec Compliance

What You Can Build

Refine a professional email

Remove robotic phrasing and formatting artifacts while keeping the sender's directness, facts, and requested action unchanged.

Review technical documentation

Apply the full checklist while protecting precise claims, terminology, headings, and the document's established register.

Audit a social draft

Identify visible writing patterns without rewriting the post or making unsupported claims about authorship.

Try These Prompts

Quick draft cleanup
Edit this draft with the lightest possible touch. Remove clear machine-written patterns, preserve my meaning and formatting, and return only the corrected text.
Detect patterns without editing
Audit this draft without rewriting it. Quote each detected pattern, name the checklist category, and suggest a brief fix without scoring authorship.
Preserve a defined voice
Edit this draft using the supplied voice profile. Preserve its tone, rhythm, terminology, facts, and deliberate rough edges. Flag any uncertain change.
Prepare public documentation
Apply the full documentation and public-copy checks to this file. Preserve technical meaning, run the bundled editorial checker, and summarize substantial change categories.

Best Practices

  • Provide the complete draft and identify its destination, such as email, documentation, or social media.
  • Supply a short voice profile when punctuation, terminology, or brand language must remain consistent.
  • Review flagged factual and stylistic choices because the skill intentionally leaves uncertain changes unresolved.

Avoid

  • Do not ask the skill to create a new article, argument, example, or factual claim.
  • Do not use detection results as proof that a model authored third-party text.
  • Do not request aggressive rewriting when preserving the writer's meaning and voice is required.

Frequently Asked Questions

Can this skill write a new draft from an outline?
No. It only edits existing text and does not add new claims, examples, or arguments.
Does it change factual claims?
It flags an apparent factual error and asks before changing it. It does not perform a research or verification pass.
Can it identify whether a model wrote the text?
No. Detect mode names visible patterns but does not assign authorship, probability, or confidence scores.
Will it preserve my formatting?
Yes, unless the formatting itself matches a listed problem, such as stray Markdown in a plain-text destination.
How does it handle a brand voice?
Provide a voice profile with tone, punctuation, approved terminology, and editing boundaries. The skill uses those rules during review.
Does the bundled script send text anywhere?
No. The script reads the selected local text file, checks two prohibited patterns, and prints matching lines locally.

Developer Details

Author

glenskii

License

MIT

Author version

v1.2.0

Skillstore revision

r2

Ref

f4838806900353c20a6899b1cbb5f5bc3a23357a

Maintenance freshness

8/9/2026

Usage

7 downloads Β· 0 views

File structure

More from glenskii

View all
View all