Anime Meme Collector

Daily collection and management of anime/ACG memes and trending phrases from Chinese internet. Automatically fetches from Bilibili and other platforms to bui...

Security Scan

The skill does what it says: a local script that scrapes public Chinese ACG sources and maintains a local meme database; its code and instructions are internally consistent with no unexplained credential or install requests.

Purpose & Capability

Name/description match the actual components: a collection script, local reference files, and instructions to run or cron it. There are no unrelated resource requests (no cloud creds, no unrelated binaries).

Instruction Scope

SKILL.md only instructs running the included Python script and referencing local files when answering; it does request outbound web fetches from Bilibili and Zhihu which is consistent with its purpose. Note: the instructions propose adding a cron job (either system cron or OpenClaw cron) — that is expected for scheduled collection but the user should confirm before enabling automated scheduling.

Install Mechanism

No install spec (instruction-only with one bundled script). Nothing is downloaded or installed during runtime beyond the script running with standard Python libraries.

Credentials

The skill requires no environment variables, credentials, or config paths. All network access uses public endpoints and the script stores results under the skill's references directory — credential requests would be disproportionate and none are present.

Persistence & Privilege

always is false and the skill does not request elevated or system-wide config changes beyond advising a cron job. Autonomous model invocation is allowed (platform default) but not combined with other concerning privileges.

Assessment

This skill is coherent and local: it fetches public data and updates a local JSON of memes. Before installing or enabling scheduled runs, review the included script and consider: (1) the script disables SSL certificate verification (in create_ssl_context) which weakens TLS checks — consider enabling verification; (2) the code performs outbound requests to public APIs (Bilibili, Zhihu) so your host's IP will contact those services and may be rate-limited or subject to terms of service — run it responsibly; (3) the script appears to have some brittle regex/logic (harmless but may miss/extract wrong text) — test manually by running the script once; (4) only enable the cron job if you want automatic network access on a schedule. If you want extra safety, run the script in an isolated environment or container and inspect logs/outputs before granting persistent scheduling.

Automated daily collection of anime/ACG memes from Chinese internet platforms.

Overview

Maintains an up-to-date database of:

• Bilibili trending video memes
• Bilibili hot search keywords
• Galgame terminology (Yuzusoft, Key, Type-Moon, etc.)
• Streamer/gaming culture (电棍, 山泥若, 炫狗, etc.)
• 346+ curated memes

Quick Start

Manual Collection

python scripts/collect_memes.py

Automated Daily Updates

Set up cron job for midnight (Asia/Shanghai):

0 0 * * * cd /path/to/skill && python scripts/collect_memes.py

Or use OpenClaw cron:

{
  "action": "add",
  "job": {
    "name": "daily-anime-meme-collect",
    "schedule": { "kind": "cron", "expr": "0 0 * * *", "tz": "Asia/Shanghai" },
    "payload": {
      "kind": "systemEvent",
      "command": "python scripts/collect_memes.py"
    }
  }
}

Using the Database

When responding with anime/meme context:

1. Check references/anime_memes_db.json for recent trends
2. Reference references/anime_memes_manual.md for classics
3. Incorporate memes naturally into responses

Data Sources

• Bilibili API: Trending videos and hot search
• Manual curation: Classic and timeless memes
• Galgame terms: Yuzusoft, Key, Type-Moon, etc.
• Streamer culture: 电棍, 山泥若, 炫狗, etc.

Reference Files

• anime_memes_db.json - Auto-generated database (300+ entries)
• anime_memes_manual.md - Curated classic memes

Notes

• Script respects rate limits with timeouts
• Failed requests are logged but don't stop collection
• Database limited to 300 entries to prevent bloat
• Each entry includes source tracking