Skip to content

Aboudjem/humanizer-skill / skills/humanizer

humanizer

Verified

Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when editing a Markdown file in place. Triggers on phrases like "humanize this", "make this sound less AI", "make this sound human", "remove AI tells", "does this read like ChatGPT", and "rewrite so it does not sound AI-generated". Pure Markdown, zero dependencies, no network calls.

FileKindSize
README.mdmarkdown4.0 KB
SKILL.mdskill md38.1 KB
evals/evals.jsonconfig3.2 KB
references/always-on-templates.mdmarkdown2.9 KB
references/patterns.mdmarkdown25.3 KB
references/patterns.zh.mdmarkdown14.6 KB

evals/evals.json

View on GitHub
{
  "skill": "humanizer",
  "description": "Trigger and behavior evaluations for the humanizer skill. The description in SKILL.md is the trigger; these cases check that it fires on real humanizing requests and stays quiet on unrelated ones.",
  "how_to_run": "Manual: in a fresh Claude Code session with the skill installed, paste each prompt and record whether the humanizer skill was invoked (should_trigger) and whether the output matches the expectation. Repeat across Claude Haiku, Sonnet, and Opus, since trigger sensitivity varies by model. There is no automated harness in this repo; the optional cli/ tool scores rewrite quality but does not test triggering.",
  "cases": [
    {
      "id": "trigger-humanize-this",
      "prompt": "Humanize this: In today's rapidly evolving landscape, AI is reshaping how we think about creativity, marking a pivotal moment.",
      "should_trigger": true,
      "expect": "Invokes humanizer in rewrite mode. Output is specific, varied human prose with no 'rapidly evolving landscape', 'reshaping', or 'pivotal', and zero em dashes."
    },
    {
      "id": "trigger-sound-less-ai",
      "prompt": "Can you make this sound less AI and more human? 'Our platform leverages cutting-edge technology to deliver a seamless, robust experience.'",
      "should_trigger": true,
      "expect": "Invokes humanizer. Removes 'leverages', 'cutting-edge', 'seamless', 'robust'; replaces with concrete specifics."
    },
    {
      "id": "trigger-detect-score",
      "prompt": "Does this read like ChatGPT wrote it? Give it an AI score. 'It is important to note that this comprehensive guide delves into the intricacies of the subject.'",
      "should_trigger": true,
      "expect": "Invokes humanizer in detect mode with --score. Reports a high 0-100 score and flags P7 (AI vocabulary), P18/P22 (filler/formal), P29 (comprehensive overview)."
    },
    {
      "id": "trigger-remove-ai-tells",
      "prompt": "Remove the AI tells from this paragraph before I publish it on LinkedIn.",
      "should_trigger": true,
      "expect": "Invokes humanizer, ideally --voice professional. Strips emojis, hashtags, and significance inflation; adds concrete detail."
    },
    {
      "id": "trigger-edit-file",
      "prompt": "Run the humanizer on docs/intro.md and fix the AI writing in place.",
      "should_trigger": true,
      "expect": "Invokes humanizer in edit mode on the file, making targeted Edit-tool changes rather than a full rewrite to chat."
    },
    {
      "id": "no-trigger-translate",
      "prompt": "Translate this to French: The cat sat on the mat and watched the rain.",
      "should_trigger": false,
      "expect": "Does NOT invoke humanizer. Performs a translation."
    },
    {
      "id": "no-trigger-write-poem",
      "prompt": "Write me a short poem about the ocean at night.",
      "should_trigger": false,
      "expect": "Does NOT invoke humanizer. Writes an original poem (humanizer rewrites existing AI-flavored text; it is not a general generator)."
    },
    {
      "id": "no-trigger-summarize",
      "prompt": "Summarize this article in three bullet points.",
      "should_trigger": false,
      "expect": "Does NOT invoke humanizer. Produces a summary."
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall