How do I install the X Safety Filtering skill?

Run npx skillmds@latest add elemontcapital/x-safety-filtering in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is X Safety Filtering safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with X Safety Filtering?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is X Safety Filtering free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published X Safety Filtering?

ElemontCapital (@elemontcapital) published this skill. Their other Agent Skills are listed on their SkillMD profile.

X Safety Filtering by elemontcapital

Name: X Safety Filtering
Author: ElemontCapital

X Safety Filtering

Use this skill when analyzing why content is not appearing, checking for "shadowban" conditions, or understanding the safety compliance layer. This skill covers the `VisibilityLib` logic that runs *after* candidate sourcing but *before* final ranking to ensure platform health.

File contents

X Safety & Filtering

Expert knowledge of X's VisibilityLib, covering safety labels, shadowban logic, NSFW filtering, and content health suppression mechanisms.

Context

The filtering stage is the "Gatekeeper" of the timeline. Even if a tweet has a high ML score from the Heavy Ranker, VisibilityLib can drop it entirely or apply a "Do Not Amplify" label that restricts it to the author's profile. This layer enforces legal compliance, user blocks, mutes, and platform safety rules (e.g., NSFW or Toxicity).

What it does

Decodes "Shadowbans": Explains the specific internal labels (like SearchBlacklist) that cause users to perceive they are shadowbanned.
Enforces User Preferences: Handles the logic for Mutes, Blocks, and "Show less often" signals.
Manages Content Health: Identifies toxic content or misinformation using models like pToxicity and pAbuse and applies downstream penalties.
NSFW Handling: Segments content into "Adult" or "Graphic" categories using pNSFWMedia and ensures it respects the viewer's sensitivity settings.

Guidelines

SafetyLevel Context: Rules are evaluated based on the SafetyLevel (e.g., Timeline vs. Profile). A tweet might be visible on a Profile but blocked in the Home Timeline.
The "Do Not Amplify" (DNA) Label: Disqualifies tweets from the "For You" (Out-of-Network) timeline and Search results without removing them from the profile.
Visibility vs. Ranking: 1. Pre-Scoring: Hard filters (Drop) remove blocked or legally prohibited content.
1. Post-Scoring: Soft filters (Labels) apply safety checks (e.g., author diversity) after the Heavy Ranker has assigned scores.
Toxicity Thresholds: If a user enters a "Reply Guy" mode with consistently high pToxicity scores, their account enters a state that limits the reach of all their future replies.
Linear Decay: Negative reputation signals follow a linear decay model; an account can "heal" its reputation over time by stopping negative behavior.

Example Trigger Prompts

"/safety-check shadowban or SearchBlacklist status"
"/safety-check toxicity decay for @user"
"/safety-check flagged content vs safe content ratio"
"/safety-check audit applied filters on a thread"
"what are the visibility rules affecting recent posts"
"show suppressed accounts in a community"

---name: x-safety-filteringdescription: Use this skill when analyzing why content is not appearing, checking for "shadowban" conditions, or understanding the safety compliance layer. This skill covers the `VisibilityLib` logic that runs *after* candidate sourcing but *before* final ranking to ensure platform health.license: MIT---# X Safety & FilteringExpert knowledge of X's VisibilityLib, covering safety labels, shadowban logic, NSFW filtering, and content health suppression mechanisms.## ContextThe filtering stage is the "Gatekeeper" of the timeline. Even if a tweet has a high ML score from the Heavy Ranker, `VisibilityLib` can drop it entirely or apply a "Do Not Amplify" label that restricts it to the author's profile. This layer enforces legal compliance, user blocks, mutes, and platform safety rules (e.g., NSFW or Toxicity).## What it does* **Decodes "Shadowbans":** Explains the specific internal labels (like `SearchBlacklist`) that cause users to perceive they are shadowbanned.* **Enforces User Preferences:** Handles the logic for Mutes, Blocks, and "Show less often" signals.* **Manages Content Health:** Identifies toxic content or misinformation using models like `pToxicity` and `pAbuse` and applies downstream penalties.* **NSFW Handling:** Segments content into "Adult" or "Graphic" categories using `pNSFWMedia` and ensures it respects the viewer's sensitivity settings.## Guidelines* **SafetyLevel Context:** Rules are evaluated based on the `SafetyLevel` (e.g., Timeline vs. Profile). A tweet might be visible on a Profile but blocked in the Home Timeline.* **The "Do Not Amplify" (DNA) Label:** Disqualifies tweets from the "For You" (Out-of-Network) timeline and Search results without removing them from the profile.* **Visibility vs. Ranking:** 1. **Pre-Scoring:** Hard filters (Drop) remove blocked or legally prohibited content. 2. **Post-Scoring:** Soft filters (Labels) apply safety checks (e.g., author diversity) after the Heavy Ranker has assigned scores.* **Toxicity Thresholds:** If a user enters a "Reply Guy" mode with consistently high `pToxicity` scores, their account enters a state that limits the reach of all their future replies.* **Linear Decay:** Negative reputation signals follow a linear decay model; an account can "heal" its reputation over time by stopping negative behavior.## Example Trigger Prompts* "/safety-check shadowban or SearchBlacklist status"* "/safety-check toxicity decay for @user"* "/safety-check flagged content vs safe content ratio"* "/safety-check audit applied filters on a thread"* "what are the visibility rules affecting recent posts"* "show suppressed accounts in a community"

Frequently asked questions