Is the X Filter skill free?

Yes. The skill itself is free from kangarooking/x-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the X Filter SkillProof Score?

7.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 4/10, docs & honesty 4/5.

How do I install X Filter?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use X Filter with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

X Filter

Scores X/Twitter topic candidates on a weighted 10-point rubric and tiers them

by kangarooking · kangarooking/x-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · d06dadf

Located x-filter/SKILL.md (frontmatter parses; name+description present). Spot-checked the two cross-skill files it references, x-create/references/user-profile.md and x-create/scripts/x_state.py, both HTTP 200. No security smells (no curl|sh, no base64, no exfiltration). I ran the same task two ways: baseline (no skill) gave a 3-line prose ranking of 3 topics; skill-following output produced per-criterion numeric scores, a weighted 0-10 total, explicit Tier A/C threshold at 7, and a FILTER_JSON block (both saved to scratchpad/baseline.md and skill.md). Same relative ranking either way, so the skill's added value is auditable structure and pipeline-chaining rather than a different decision — hence output 7, not higher. README's "智能推荐算法 borrowed from X For You" oversells what is a simple weighted rubric, costing a docs point.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 4/10
Docs & honesty 4/5

What X Filter does

Applies a weighted 10-point scoring rubric (trending 4, controversy 2, value 3, relevance 1) to candidate X/Twitter topics, categorizing each into Tier A (>=7, creation pool), B, or C and emitting a structured report plus a machine-readable FILTER_JSON block. Triggers when the user wants to evaluate collected materials, filter or score topics, or says "filter topics", "score materials", or "选题筛选". Optionally uses rejected-topic similarity and diversity decay when the companion x-create skill's state files are present.

How to install X Filter

git clone --depth 1 https://github.com/kangarooking/x-skills.git /tmp/x-filter-src
mkdir -p ~/.claude/skills
cp -R /tmp/x-filter-src/x-filter ~/.claude/skills/x-filter
# Standalone: core scoring works alone (falls back to default domains/weights).
# For full features (user-profile weights, rejected-topic SimilarityFilter, state),
# also install the companion skill it references:
#   cp -R /tmp/x-filter-src/x-create ~/.claude/skills/x-create
# The similarity/state Python calls are OPTIONAL; skill degrades gracefully if absent.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger X Filter

/x-filter Scores X/Twitter topic candidates on a weighted 10-point rubric and tiers them

It also activates on plain-language prompts like these:

Score these collected topics for X posts
Filter my materials by relevance and virality
Rank these ideas using the 10-point system

Frequently asked questions

Is the X Filter skill free?: Yes. The skill itself is free from kangarooking/x-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does X Filter work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Works with setup. Located x-filter/SKILL.md (frontmatter parses; name+description present). Spot-checked the two cross-skill files it references, x-create/references/user-profile.md and x-create/scripts/x_state.py, both HTTP 200. No security smells (no curl|sh, no base64, no exfiltration). I ran the same task two ways: baseline (no skill) gave a 3-line prose ranking of 3 topics; skill-following output produced per-criterion numeric scores, a weighted 0-10 total, explicit Tier A/C threshold at 7, and a FILTER_JSON block (both saved to scratchpad/baseline.md and skill.md). Same relative ranking either way, so the skill's added value is auditable structure and pipeline-chaining rather than a different decision — hence output 7, not higher. README's "智能推荐算法 borrowed from X For You" oversells what is a simple weighted rubric, costing a docs point.
What is the X Filter SkillProof Score?: 7.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 4/10, docs & honesty 4/5.
How do I install X Filter?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use X Filter with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.