Is the X Collect 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 Collect SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install X Collect?

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 Collect 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 Collect

Multi-round web-search research that compiles scored, clustered source material for X posts

by kangarooking · kangarooking/x-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 802674a

Fetched x-collect/SKILL.md and README raw from HEAD; frontmatter parses with name+description, and the only referenced script (x-create/scripts/x_state.py) returns HTTP 200 and is used only in an explicitly optional step. I ran the actual workflow on topic "MCP": a baseline single WebSearch produced one undifferentiated prose blurb with no scoring, while the skill-directed 4-round strategy (official/technical/comparison/security) produced a structured report of 4 source items with QualityScore, TopicCluster and HookCandidates plus a MATERIALS_JSON block — and surfaced the function-calling comparison and security angles (CVE-2025-49596, 80% cloud adoption) the baseline entirely missed. No security smells found; docs claims match observed behavior aside from suite-wide "viral tweet" hype.

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 8/10
Docs & honesty 4/5

What X Collect does

Researches a topic for X (Twitter) content by running a 4-round web-search strategy (official sources, technical analysis, comparisons, gap-filling) and synthesizes the findings into a structured markdown report plus a machine-readable MATERIALS_JSON block for handoff to filtering. Triggers when the user asks to collect materials, research a subject for X posts, find content for X, or invokes /x-collect. Core workflow needs only the WebSearch tool; state/event steps are optional.

How to install X Collect

git clone --depth 1 https://github.com/kangarooking/x-skills.git /tmp/x-collect-src
mkdir -p ~/.claude/skills
cp -R /tmp/x-collect-src/x-collect ~/.claude/skills/x-collect
# Core workflow needs ONLY the built-in WebSearch tool — no extra deps.
# Optional step 9 (event logging) calls: python ~/.claude/skills/x-create/scripts/x_state.py
#   -> install the sibling x-create skill (cp -R /tmp/x-collect-src/x-create ~/.claude/skills/x-create) if you want it; skill runs fine without it.
# Optional ContextStore state at ~/.claude/skills/x-create/state/{liked,rejected}_topics.json is used only if present.

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

Commands — how to trigger X Collect

/x-collect Multi-round web-search research that compiles scored, clustered source material for X posts

It also activates on plain-language prompts like these:

Collect materials on this trending topic for X
Research subjects for my next X post
Gather trending topics in the AI space

Frequently asked questions

Is the X Collect 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 Collect work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched x-collect/SKILL.md and README raw from HEAD; frontmatter parses with name+description, and the only referenced script (x-create/scripts/x_state.py) returns HTTP 200 and is used only in an explicitly optional step. I ran the actual workflow on topic "MCP": a baseline single WebSearch produced one undifferentiated prose blurb with no scoring, while the skill-directed 4-round strategy (official/technical/comparison/security) produced a structured report of 4 source items with QualityScore, TopicCluster and HookCandidates plus a MATERIALS_JSON block — and surfaced the function-calling comparison and security angles (CVE-2025-49596, 80% cloud adoption) the baseline entirely missed. No security smells found; docs claims match observed behavior aside from suite-wide "viral tweet" hype.
What is the X Collect SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install X Collect?: 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 Collect 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.