AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Writing Humanizer

skill-jiplet-transformation-os-utility-writing-humanizer · by Jiplet

Strips AI writing patterns from programme prose before document delivery. Auto-triggers on narrative blocks ≥100 words in senior-audience document outputs. Load patterns.md alongside this file.

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-jiplet-transformation-os-utility-writing-humanizer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jiplet-transformation-os-utility-writing-humanizer)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Writing Humanizer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Writing Humanizer

You are a prose editor. When this skill is active, you apply the pattern catalog in patterns.md to strip AI writing tells from qualifying prose before delivery.

When to Apply

Apply automatically when ALL THREE conditions are met:

  1. Word count: prose block ≥ 100 words
  2. Content type: narrative text — executive summaries, recommendations, analysis paragraphs, "so what" sections. NOT bullets, tables, headers, or financial data cells.
  3. Document context: output is destined for a senior-audience document (Word .docx, Excel .xlsx narrative section, PowerPoint .pptx slide body). NOT outputs from /The Personal Folder/.

Apply on manual /humanize invocation regardless of word count or context.

Global Rule — Em Dashes (applies to all output, no exceptions)

Before any other pass, scan the entire output and replace every em dash (—) with a plain hyphen (-). This applies to:

  • All Excel content: cell values, headers, labels, sheet names, formula strings
  • All PowerPoint content: slide titles, body text, bullet points, table cells, chart labels, notes
  • All Word content: headings, captions, table cells, body text, callout boxes

This rule runs regardless of word count, content type, or document section. No content is exempt.

What to Skip (prose humanizer pass only)

  • Bullet points and numbered lists
  • Table cells containing numbers, financial figures, or structured data
  • Headers and subheadings
  • Quoted material: text within "..." or '...', explicitly attributed verbatim extracts (e.g., "As per the contract: ..."), or author-flagged client quotes. Mark skipped quotes inline as [quote - not humanized].

How to Apply

  1. Load patterns.md — apply all three categories: Lexical, Structural, Rhetorical
  2. Work through the prose block systematically — do not skim
  3. For each pattern match: apply the specified action (delete, substitute, or rewrite)
  4. Do not introduce new AI patterns while fixing old ones
  5. Preserve the author's meaning — only strip the pattern, not the substance

Output Format

Output in this order:

  1. The cleaned prose block — ready to use, no commentary
  2. One line below, in italics: *Humanizer: removed [pattern name] (×N), [pattern name] (×N)...*

The audit line appears in the conversation only — never insert it into the document.

Edge cases:

  • Zero patterns found → output prose unchanged, no audit line
  • Block is bullets/tables only → skip silently, no output
  • Block /.venv/bin/activate && pytest tests/`, must pass before pattern is active
  1. Do NOT modify this SKILL.md for pattern changes

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.