Not in the top 1,000 by GitHub stars
kangarooking/x-skills
自动收集素材,确认选题,并创作x推文,最后并发布到草稿箱的Claude Skills
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
x-collect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
95f4c6e4221f → 95f4c6e4221f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 95f4c6e4221f
No earlier version was observed for comparison.
x-create/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
95f4c6e4221f → 95f4c6e4221f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 95f4c6e4221f
No earlier version was observed for comparison.
x-filter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
95f4c6e4221f → 95f4c6e4221f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 95f4c6e4221f
No earlier version was observed for comparison.
x-publish/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
95f4c6e4221f → 95f4c6e4221f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 95f4c6e4221f
No earlier version was observed for comparison.
Heat
4.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
x-collect
When your agent uses it
Collect and research materials for X (Twitter) content creation using multi-round web search strategy. Use when user wants to gather trending topics, research subjects for X posts, or mentions "collect materials", "research topic", "find content for X", "x-collect". Performs 4-round deep research mimicking human research workflow.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,376 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Optional State (ContextStore)
- Workflow
- Execution Steps
- Example
- Integration
- Tips
Files
SKILL.mdcore5,314 bytesSKILL.mdcore5,314 bytesSKILL.mdcore5,314 bytes
Read SKILL.md
# X Collect
Collect trending topics and research materials for X content creation using a systematic 4-round web search strategy.
## Prerequisites
- WebSearch tool available
- Internet connection
## Optional State (ContextStore)
If available, leverage user preference state to improve search quality:
- State dir: `~/.claude/skills/x-create/state/`View the complete source on GitHubx-create
When your agent uses it
Create viral X (Twitter) posts including short tweets, threads, and replies. Use when user wants to write X content, create posts, or mentions "create tweet", "write thread", "x-create", "写推文", "创作推文". Supports 5 post styles with customizable templates, plus a mandatory humanize pass to reduce AI-sounding phrasing. First-time users go through onboarding to set up profile.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,625 tokensWhen the skill is activated
Reference documents
4,312 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First-Time Setup
- Post Types
- Creation Workflow
- Output Format
- Template Priority
- Resources
- Example
- Integration
Scripts executed separately
scripts/hooks.pyscripts/schemas.pyscripts/similarity.pyscripts/x_state.py
Files
SKILL.mdcore9,704 bytesSKILL.mdcore9,704 bytesSKILL.mdcore9,704 bytesSKILL.mdcore9,704 bytesassets/templates/README.mddoc1,766 bytesreferences/post-patterns.mddoc10,673 bytesreferences/user-profile.mddoc1,783 bytesscripts/hooks.pyruns2,785 bytesscripts/schemas.pyruns1,015 bytesscripts/similarity.pyruns2,630 bytesscripts/x_state.pyruns13,358 bytes
Read SKILL.md
# X Create
Create viral X posts (short tweets, threads, replies) based on user's persona and post patterns.
## First-Time Setup
**Check user profile before creating content:**
1. Read `references/user-profile.md`
2. If `initialized: false` or file doesn't exist → Run onboarding
3. If `initialized: true` → Proceed to content creation
### Onboarding Questions
View the complete source on GitHubx-filter
When your agent uses it
Score and filter topics for X content creation using weighted criteria. Use when user wants to evaluate collected materials, filter topics by score, or mentions "filter topics", "score materials", "x-filter", "选题筛选". Applies 10-point scoring system with customizable weights.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,144 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scoring System (满分10分)
- Prerequisites
- Optional State (Feedback Loop)
- Workflow
- Execution Steps
- Example
- Customization
- Integration
Files
SKILL.mdcore7,278 bytesSKILL.mdcore7,278 bytesSKILL.mdcore7,278 bytesSKILL.mdcore7,278 bytes
Read SKILL.md
# X Filter
Score and filter collected materials for X content creation. Topics scoring ≥7 points enter the creation pool.
## Scoring System (满分10分)
| Criteria | Weight | Description |
|----------|--------|-------------|
| **热度/趋势** | 4分 | Current popularity and trend momentum |
| **争议性** | 2分 | Discussion potential and debate value |
| **高价值** | 3分 | Information density and actionable insights |
| **账号定位相关** | 1分 | Alignment with account positioning |
**Threshold**: ≥7分 enters creation poolView the complete source on GitHubx-publish
When your agent uses it
Publish tweets and threads to X (Twitter) draft using browser automation. Use when user wants to publish content to X, save to drafts, or mentions "publish to X", "post tweet", "x-publish", "发布推文". Supports short tweets and threads. NEVER auto-publish, always saves to draft.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
1,539 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Critical Rules
- Content Types
- Scripts
- Workflow
- Efficiency Guidelines
- Element References
- Example Flows
- Error Handling
- Integration
Scripts executed separately
scripts/copy_to_clipboard.py
Files
SKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesSKILL.mdcore5,871 bytesscripts/copy_to_clipboard.pyruns4,735 bytes
Read SKILL.md
# X Publish
Publish tweets and threads to X draft using Playwright browser automation.
## Prerequisites
- Playwright MCP for browser automation
- User logged into X (Twitter)
- Python 3.9+ with dependencies:
- macOS: `pip install Pillow pyobjc-framework-Cocoa`
- Windows: `pip install Pillow pywin32`
## Critical Rules
View the complete source on GitHubSkills included
- x-collect
- x-create
- x-filter
- x-publish
Repository facts
- License
- Apache-2.0
- Created
- Jan 20, 2026
- Last pushed
- Feb 21, 2026
- Forks
- 56
- Open issues
- 2
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 17 notes
x-collect/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-collect/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-create/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-create/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-create/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-filter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-filter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-filter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedx-publish/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 17 network referencesin 1 file: x-publish/SKILL.md:59
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 5 files: x-create/scripts/hooks.py:1 x-create/scripts/schemas.py:1 x-create/scripts/similarity.py:1 and 2 more
- No access to secrets
- No requests to vote in Hot
Show all 22 signals by file
x-create/scripts/hooks.py
- Executable scriptline 1
Executable file
x-create/scripts/schemas.py
- Executable scriptline 1
Executable file
x-create/scripts/similarity.py
- Executable scriptline 1
Executable file
x-create/scripts/x_state.py
- Executable scriptline 1
Executable file
x-publish/SKILL.md
- Network accessline 59
browser_navigate: https://x.com/compose/post - Network accessline 77
Report: "Draft saved. Please review at https://x.com/compose/drafts" - Network accessline 94
browser_navigate: https://x.com/compose/post - Network accessline 121
Report: "Thread draft saved ({n} tweets). Review at https://x.com/compose/drafts" - Network accessline 167
# 2. Navigate and paste browser_navigate: https://x.com/compose/post - Network accessline 168
browser_navigate: https://x.com/compose/post - Network accessline 177
# 4. Report "Draft saved! Review at: https://x.com/compose/drafts" - Network accessline 178
"Draft saved! Review at: https://x.com/compose/drafts" - Network accessline 206
# Navigate browser_navigate: https://x.com/compose/post - Network accessline 207
browser_navigate: https://x.com/compose/post - Network accessline 228
# Report "Thread draft saved (3 tweets). Review at: https://x.com/compose/drafts" - Network accessline 229
"Thread draft saved (3 tweets). Review at: https://x.com/compose/drafts" - Network accessline 258
- 类型: {short/thread} - 条数: {n} - 草稿链接: https://x.com/compose/drafts - Network accessline 260
- 草稿链接: https://x.com/compose/drafts - Network accessline 273
"post_type": "short|thread", "count": 1, "draft_url": "https://x.com/compose/drafts" - Network accessline 274
"count": 1, "draft_url": "https://x.com/compose/drafts" } - Network accessline 275
"draft_url": "https://x.com/compose/drafts"
x-publish/scripts/copy_to_clipboard.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 22 facts
- Executable script in prose of a file that runsx-create/scripts/hooks.py:1Low confidence
- Executable script in prose of a file that runsx-create/scripts/schemas.py:1Low confidence
- Executable script in prose of a file that runsx-create/scripts/similarity.py:1Low confidence
- Executable script in prose of a file that runsx-create/scripts/x_state.py:1Low confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:59High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:77High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:94High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:121High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:167High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:168High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:177High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:178High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:206High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:207High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:228High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:229High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:258High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:260High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:273High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:274High confidence
- Network access in code of the SKILL.mdx-publish/SKILL.md:275High confidence
- Executable script in code of a file that runsx-publish/scripts/copy_to_clipboard.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md x-collect/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md x-collect/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md x-collect/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md x-collect/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md x-collect/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md x-collect/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.