Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

Muvon

@muvon source repo

115 published skills · page 2 of 2

  1. ▌
    Content Locale Humanize Ar · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Arabic (ar) target text — auto-loads alongside content-locale-humanize when the target language is Arabic.
    0
    installs
  2. ▌
    Content Locale Humanize De · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in German (de) target text — auto-loads alongside content-locale-humanize when the target language is German.
    0
    installs
  3. ▌
    Content Locale Humanize Es · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Spanish (es) target text — auto-loads alongside content-locale-humanize when the target language is Spanish.
    0
    installs
  4. ▌
    Content Locale Humanize Fr · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in French (fr) target text — auto-loads alongside content-locale-humanize when the target language is French.
    0
    installs
  5. ▌
    Content Locale Humanize Hi · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Hindi (hi) target text — auto-loads alongside content-locale-humanize when the target language is Hindi.
    0
    installs
  6. ▌
    Content Locale Humanize It · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Italian (it) target text — auto-loads alongside content-locale-humanize when the target language is Italian.
    0
    installs
  7. ▌
    Content Locale Humanize Ja · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Japanese (ja) target text — auto-loads alongside content-locale-humanize when the target language is Japanese.
    0
    installs
  8. ▌
    Content Locale Humanize Ko · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Korean (ko) target text — auto-loads alongside content-locale-humanize when the target language is Korean.
    0
    installs
  9. ▌
    Content Locale Humanize Pt · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Portuguese (pt) target text — auto-loads alongside content-locale-humanize when the target language is Portuguese.
    0
    installs
  10. ▌
    Content Locale Humanize Th · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Thai (th) target text — auto-loads alongside content-locale-humanize when the target language is Thai.
    0
    installs
  11. ▌
    Content Locale Humanize Zh · muvon
    Per-language calibration anchors for detecting AI-slop and translationese in Chinese (zh) target text — auto-loads alongside content-locale-humanize when the target language is Chinese.
    0
    installs
  12. ▌
    Device Computer Automation · muvon
    Operate the local computer's native UI — macOS, Linux, or Windows — via the desktop-automation MCP server. Covers OS accessibility / screen-recording permissions, pixel-anchor targeting (no semantic UI tree), region-capture discipline under the MCP response cap, window focus and multi-monitor handling, keyboard / mouse / clipboard sequencing, and the safety boundary around destructive desktop actions and screen-lock / biometric bypass. Activate when the user wants to drive a native desktop app or the OS shell at the GUI layer. Pairs with the device:operator agent which carries the shared snapshot → verify → record discipline; this skill carries the desktop-specific tooling and rules and pulls the device-computer capability automatically.
    0
    installs
  13. ▌
    AI Prompt Injection Defense · muvon
    Operational playbook for defending LLM applications against prompt injection (direct + indirect), and red-teaming them in 2026. Covers OWASP Top 10 for LLM Applications v2025 (LLM01–LLM10), OWASP Top 10 for Agentic Applications 2026 (ASI01–ASI10), foundational research (Greshake et al. on indirect injection, Anthropic Many-Shot Jailbreaking, Constitutional AI), documented real-world exploits (Slack AI Aug 2024, EchoLeak CVE-2025-32711, GitHub Copilot RCE CVE-2025-53773, Bing/Sydney), defense layers (XML tag separation per Anthropic docs, structured outputs, content filters via Llama Guard 3 / OpenAI Moderation / Anthropic classifiers, NeMo Guardrails), and red-team tooling (garak, PyRIT, Promptfoo red-team mode). Use when auditing an LLM app for injection, designing defense-in-depth, mapping OWASP risks, or building a red-team suite. Output: red-team findings + defense recommendations with reproducible payloads.
    0
    installs
  14. ▌
    Browser Backlink Submission · muvon
    Operational playbook for EXECUTING backlink submissions via a headless browser — driving directory/listing/Web2.0 forms with Playwright, mapping a single site profile to per-target fields, handling signup + email verification + captchas, throttling to avoid spam flags, and producing an auditable submission log. Activate ONLY when the user has a qualified prospect list and wants the browser to actually submit. Prospect discovery, qualification, and anchor/description copy are upstream concerns — this skill is execution-only.
    0
    installs
  15. ▌
    Browser Social Account Maintenance · muvon
    Operational playbook for RECURRING social-account hygiene executed via a headless browser — profile/bio sync across networks, cross-posting a pre-written piece to N platforms, scheduled-post audits, follower/connection cleanup, notification triage, archive/delete of old posts, DM-inbox housekeeping. Activate ONLY when the user wants the browser to actually drive social account ops as maintenance work. Authoring new post copy is NOT this skill — text must be supplied as input or fetched from a content specialist via tap.
    0
    installs