writing-humanizer

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: writing-humanizer
# description: routing-facing summary of when this skill activates and what it covers.
description: "Use when writing or editing human-readable prose such as docs, PRs, issues, release notes, errors, UI copy, commits, tooltips, or support replies, especially when text sounds robotic, padded, monotonous, or overly formal. Covers AI-tell removal, active voice, hedging reduction, readability diagnosis, sentence rhythm, vocabulary variety, tone mapping, paragraph rhythm, bullets-vs-prose choice, and the 5-step humanization workflow. Do NOT use for documentation routing/type selection, code-identifier naming, or in-product UI-text pattern catalogs."
# license: SPDX-compatible license identifier for the skill content.
license: MIT
allowed-tools: Read Grep Edit
# metadata: Skill Metadata Protocol fields encoded under Agent Skills-compatible frontmatter.
metadata:

  # === v8 Classification (subject + public; polyhierarchy via subjects[]) — see ADR-0017 ===
  # subject: primary browse shelf — what the skill teaches. One of twelve closed values:
  # backend-engineering / frontend-engineering / software-architecture / data-engineering / agent-ops / ai-engineering /
  # quality-assurance / design / reasoning-strategy / software-engineering-method / knowledge-organization / product-domain.
  subject: design
  # public: publishability/private-data gate. Boolean.
  # true = publishable/shareable; false = private and excluded from public export.
  # Project anchoring is carried separately by non-empty `project[]` plus `grounding`.
  public: true
  # scope: free-text PRD-style statement of what the skill teaches and what it excludes.
  # (v8 required; not an enum). Mirrors Coverage + Do NOT Use When at frontmatter level.
  scope: "Writing and editing human-readable prose — docs, PRs, issues, release notes, errors, UI copy, commits, tooltips, support replies — especially when text sounds robotic, padded, monotonous, or overly formal: AI-tell removal, active voice, hedging reduction, readability diagnosis, sentence rhythm, vocabulary variety, tone mapping, paragraph rhythm, the bullets-vs-prose choice, and the 5-step humanization workflow. Portable across any written communication; principle-grounded, not repo-bound. Excludes documentation routing/type selection, code-identifier naming, and in-product UI-text pattern catalogs (microcopy)."
  # taxonomy_domain: optional hierarchical sub-path within `subject`. Slash-delimited
  # lowercase kebab-case segments. rename of the original v8 `domain`. Remove when the flat
  # `subject` is sufficient.
  taxonomy_domain: design/content
  # stability: lifecycle marker. One of:
  # experimental (active development) / stable (production-ready) /
  # frozen (no further changes expected) / deprecated.
  # When `deprecated`, schema's allOf REQUIRES `superseded_by: <real-skill-name>`.
  stability: experimental
  # keywords: semantic phrases for fuzzy router activation. v8 cap: max 10.
  # Keep terms a user would actually type when starting a task in this skill's domain.
  keywords: ["AI-tell detection","AI-tell removal","prose humanization","passive-to-active voice","hedging-pattern removal","readability scoring diagnosis","sentence-rhythm pattern","3-beat sentence variety","hook-body-landing paragraph","tone mapping framework"]
  # triggers: explicit-match activation phrases the router fires on literally.
  # Use when label-based routing is intended; usually keywords + examples are enough.
  triggers: ["humanize this text","sounds AI-generated","strip the AI tells","make this read like a human wrote it","this prose is robotic"]
  # examples: 2-5 realistic user prompts the skill SHOULD activate for.
  # Written in the user's voice. Improves retrieval recall beyond keywords alone.
  examples: ["this PR description sounds AI-generated — strip the tells and rewrite it concisely","rewrite this onboarding paragraph in the active voice with shorter average sentence length","audit this rele