GStars
    blader

    blader/humanizer

    #28 this week

    Agent skill that removes signs of AI-generated writing from text

    llm
    agent-skills
    ai-humanizer
    ai-writing
    chatgpt
    claude
    Python
    MIT
    65.3K stars
    5.2K forks
    278 GitHub watchers
    Updated Nov 6, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #5 among LLM repositories ranked this week, and #5 over the last 30 days; #28 of 182 repositories with measured growth this week (top 15%).

    This week's +2,931 stars is in line with its 30-day pace of about +2,508 per week.

    4 releases in the last 90 days, the latest 38 days ago, with 23 contributors on GitHub.

    Peaked at #28 in the weekly ranking the week of Nov 1, its best in the past year.

    Use Cases & Benefits

    • Removes signs of AI-generated writing from text to make it sound more natural and human.
    • Enables no-fabrication rewrites that preserve original facts while eliminating AI writing artifacts.
    • Use for refining AI-generated content to match a specific human writing style via voice calibration.
    • Use for cleaning up documentation or marketing copy to remove promotional or formulaic AI language.
    • Use for integrating into agent harnesses or Claude Code plugins to automate humanizing text workflows.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    A portable agent skill that removes signs of AI-generated writing from text, making it sound more natural and human. It is plain Markdown, so it can run in any harness that supports skill-style instructions.

    Install globally with the cross-agent skills CLI so Humanizer is available in every project:

    To install globally into every supported agent harness:

    To target one configured harness, pass its agent name:

    Omit --global for a project-local install that can be committed and shared with collaborators. Start a new agent session or reload skills after installation.

    Excerpt from the blader/humanizer README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Aug 9: +139Aug 10: +213Aug 11: +306Aug 12: +261Aug 13: +228Aug 14: +185Aug 15: +133Aug 16: +142Aug 17: +69Aug 18: +340Aug 19: +218Aug 20: +250Aug 27: +281Aug 28: +264Aug 29: +168Aug 30: +221Aug 31: +254Sep 1: +329Sep 2: +578Sep 3: +1,136Sep 4: +1,208Sep 5: +837Sep 6: +722Sep 7: +846Sep 8: +434Sep 9: +564Sep 10: +488Sep 11: +464Sep 12: +404Sep 13: +335Sep 14: +469Sep 15: +423Sep 16: +611Sep 17: +422Sep 18: +364Sep 19: +310Sep 20: +387Sep 21: +421Sep 22: +171Oct 31: +368Nov 3: +536Nov 4: +396Nov 5: +430Nov 6: +451

    +30,954 stars over 90 days across 50 snapshot days; best day +1,208 on Sep 4.

    Forks

    5.2K+2.1K

    Open issues

    16-8

    Compared with peers in LLM

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    View category →
    blader/humanizer compared with LLM repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    thedotmack/claude-mem113.6K+8.8K35today
    NVIDIA/auto-ontology7.5K+5.6K37—
    HKUDS/DeepTutor55.5K+5.5K655 days ago
    affaan-m/ECC297.9K+5.2K6335 days ago
    DietrichGebert/ponytail185.3K+5.1K607 days ago
    blader/humanizer65.3K+2.9K3738 days ago
    Category median113.6K+5.5K60—
    Compare humanizer with claude-mem, auto-ontology, DeepTutor →

    Discover Repositories

    Search across tracked repositories by name or description