SKILLEMALL.ai
RU Sign in

BC thought-leader-tracker

Daily automated collection of podcasts, interviews, and videos from thought leaders across YouTube, Apple Podcasts, and Spotify. Generates Markdown reports with content summaries, key points, and common theme analysis. Use when tracking thought leader content, creating daily digests, analyzing industry trends, or monitoring specific experts' new releases.

ClawHub Agent Skills author: rickytsao-swordedge v1.0.0 MIT-0 9 files · 1 script body ≈ 521 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerYouTubeMedia and videoInfrastructuretype 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
B
83/100
safety, quality, tests
Safety 60%
79
Quality 40%
90
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

    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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Obfuscation obf-hex-escape-chain daily-logs/daily-report-2026-03-26-7d.md:174
      Escaped/char-code string obfuscation
      - **Link:** https://podcasts.apple.com/us/podcast/%E8%8F%B2%E5%88%A9%E5%85%8B%E6%96%AF%E8%A5%BF%E7%8F%AD%E7%89%99%E8%AF%AD/id14…529?uo=4
    • medium Obfuscation obf-hex-escape-chain daily-logs/daily-report-2026-03-26-7d.md:195
      Escaped/char-code string obfuscation
      - **Link:** https://podcasts.apple.com/us/podcast/%E9%98%BF%E9%9D%9E%E5%88%A9%E5%8A%A0-%E9%9D%9E%E6%B4%B2%E5%8F%8A%E6%96%B0%E5%85%B4%E5%B8%82%E5%9C%BA%E5%95%86%E4%B8%9A%E7%A7%91%E6%8A%80%E5%91%A8%E6%8
    • medium Obfuscation obf-hex-escape-chain daily-logs/daily-report-2026-03-27-7d.md:174
      Escaped/char-code string obfuscation
      - **Link:** https://podcasts.apple.com/us/podcast/%E8%8F%B2%E5%88%A9%E5%85%8B%E6%96%AF%E8%A5%BF%E7%8F%AD%E7%89%99%E8%AF%AD/id14…529?uo=4
    • medium Obfuscation obf-hex-escape-chain daily-logs/daily-report-2026-03-27-7d.md:195
      Escaped/char-code string obfuscation
      - **Link:** https://podcasts.apple.com/us/podcast/%E9%98%BF%E9%9D%9E%E5%88%A9%E5%8A%A0-%E9%9D%9E%E6%B4%B2%E5%8F%8A%E6%96%B0%E5%85%B4%E5%B8%82%E5%9C%BA%E5%95%86%E4%B8%9A%E7%A7%91%E6%8A%80%E5%91%A8%E6%8
    • low Exfiltration exfil-secret-in-url scripts/collector.js:26
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      // const url = `https://www.googleapis.com/youtube/v3/search?q=…)}&type=video&order=date&maxResults=10&key=${apiKey}`;
      placeholder

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 54/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (thought-leader-tracker) differs from the folder (thought-leader-tracker-skill)
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 14 steps
    • 100Execution cost. Instruction body is 521 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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 357: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 14 items
    • +3Output format is stated explicitly
    • +4Has examples (4 code blocks)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: clean
    This skill runs a disclosed local tracker that queries public podcast search data and writes local Markdown reports, but its generated reports may be low quality or misattributed.
    LLM: benign (high) · VirusTotal: · 29 May 2026