SKILLEMALL.ai
GitHub ↗ RU Sign in

CF x-reader\n\nUniversal content reader — fetch, transcribe, and digest content from any platform.\n\n## Trigger\n\nWhen us

x reader

modbender/skill-library-mcp Agent Skills author: modbender MIT 22 files body ≈ 743 tokens Open the sourcegithub.com↗ analyzed 2 d ago

x reader

As a process F 26/100 · Will not run — weak spots: steps, result and completion, when it triggers

ProcedurePlaywrightTelegramGitHubYouTubeMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
71/100
safety, quality, tests
Safety 60%
99
Quality 40%
28
Run on models
none yet
Process rating
F
26/100
Will not run
Steps w 15
0
Result and completion w 14
0
When it triggers w 12
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Exfiltration read-dotenv README.md:182
    Reads a .env file
    cp .env.example .env

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error name-long name is longer than 64 chars
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 26/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (x-reader\n\nUniversal content reader — fetch, transcribe, and digest content from any platform.\n\n## Trigger\n\nWhen user sends content (URL, text, or transcript) with analysis intent:\n- 「analyze [URL]》\n- "Analyze this article"\n- "What are the key takeaways?"\n- Auto-triggered after video/podcast transcription (from video skill)\n\n## Pipeline\n\n### Step 1: Get Content\n\nChoose tool based on input type:\n\n| Input | Tool |\n|-------|------|\n| Tweet URL | or Jina Reader |\n| Web URL | or Jina Reader |\n| Local file | Read file directly |\n| Transcript from video skill | Use directly |\n\n### Step 2: Multi-Dimensional Analysis\n\nScan content across these dimensions. Only output dimensions with actual content — skip empty ones.\n\n\n\n### Step 3: Personalized Relevance (Customizable)\n\nMap insights to YOUR context. Edit the dimensions below to match your own projects, interests, and systems.\n\n\n\n> **Customization**: Edit the dimensions in Step 2 and Step 3 to match your own\n> domain. A trader might add "Market Impact" and "Risk Assessment". A developer\n> might add "Architecture Patterns" and "Tech Debt". Make it yours.\n\n## Output Modes\n\n| Mode | Trigger | Output |\n|------|---------|--------|\n| **Full** (default) | | All dimensions |\n| **Sparse** | | Only hit dimensions, skip empty |\n| **Brief** | | Action items only |\n\n## Best Practices\n\n1. **Scan all dimensions, but don't force-fill** — skip empty dimensions cleanly\n2. **Actions must be specific** — not "learn about X" but "read X docs chapter Y"\n3. **Distinguish fact from opinion** — mark the author's claims vs verified facts\n4. **Source everything** — tag where each insight comes from in the original content\n5. **ROI awareness** — not every action is worth doing, assess effort vs impact\n\n## Supported Platforms\n\n| Platform | Text Fetch | Video/Audio Transcript |\n|----------|-----------|----------------------|\n| YouTube | ✅ Jina | ✅ yt-dlp subtitles → Groq Whisper fallback |\n| Bilibili (B屏) | ✅ API | ✅ via Claude Code skill |\n| X / Twitter | ✅ Jina → Playwright | — |\n| WeChat (微信公众号) | ✅ Jina → Playwright | — |\n| Xiaohongshu (小红书) | ✅ Jina → Playwright* | — |\n| Telegram | ✅ Telethon | — |\n| RSS | ✅ feedparser | — |\n| 小宇舟 (Xiaoyuzhou) | — | ✅ via Claude Code skill |\n| Apple Podcasts | — | ✅ via Claude Code skill |\n| Any web page | ✅ Jina fallback | — |\n\n> \*XHS requires a one-time login: (saves session for Playwright fallback)\n>\n> YouTube Whisper transcription requires — get a free key from [Groq](https://console.groq.com/keys)\n\n## Dependencies\n\n- Python package (provides core content fetching)\n- Optional: for Whisper transcription\n- Optional: + for Telegram support\n- Optional: Playwright for browser-based scraping\n\n## Source & Issues\n\n- **Source:** https://github.com/runesleo/x-reader\n- **Issues:** https://github.com/runesleo/x-reader/issues\n- **Author:** [@runes_leo](https://x.com/runes_leo)) differs from the folder (x-reader)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 100Execution cost. Instruction body is 743 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 8: 120–800 characters recommended
  • +4Structure: 1 headings, hard to scan
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -212 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions

Quality base 70; lint remarks subtract, signals add up to 100. Result: 28.