← Back to Skills Marketplace
matilda-grifin

ai news weekly agent

by Matilda-Grifin · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ⚠ suspicious
127
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install ai-news-weekly-agent
Description
Generate a weekly AI report with OpenClaw top skills, official announcements, industry news, and capped paper ratio in Markdown format.
README (SKILL.md)

AI News Weekly Agent

Generate a weekly AI report in Markdown, including OpenClaw top skills, official announcements, industry news, and capped paper ratio.

When to use

  • User asks for weekly AI digest/report
  • User wants OpenClaw skills ranking + AI news summary

Command

python3 run_daily_digest.py --use-llm --llm-provider auto --window-hours 168 --max-paper-ratio 0.2 --min-official-items 3

Required environment variables

  • Ark mode:
    • ARK_API_KEY
    • ARK_MODEL
    • ARK_ENDPOINT_ID (recommended, ep-xxx)
  • OpenAI-compatible mode:
    • OPENAI_API_KEY
    • OPENAI_BASE_URL (if ends with /v1, script auto-expands to /chat/completions)
    • OPENAI_MODEL (optional, but recommended)

Notes:

  • In OpenClaw, these variables may be injected by the runtime.
  • If not injected, users must provide them manually in runtime env or local .env.
  • --llm-provider auto prefers Ark when Ark vars exist; otherwise uses OpenAI-compatible mode.
  • Default security policy requires HTTPS endpoint and allowlisted LLM hosts.

Optional environment variables

  • DIGEST_WEBHOOK_URL: webhook for send notifications when using --send

Environment template

Use runtime env injection in OpenClaw, or copy this template to local .env:

ARK_API_KEY=
ARK_MODEL=Doubao-Seed-1.6-lite
ARK_ENDPOINT_ID=
OPENAI_API_KEY=
OPENAI_BASE_URL=
OPENAI_MODEL=
DIGEST_WEBHOOK_URL=

External network access

This skill may access these external endpoints during execution:

  • https://ark.cn-beijing.volces.com (Ark LLM API)
  • OPENAI_BASE_URL target (OpenAI-compatible provider endpoint)
  • https://topclawhubskills.com (OpenClaw leaderboard snapshot)
  • RSS/news URLs listed in sources.json
  • Optional webhook hosts for notification: Feishu/Lark or DingTalk

Security and data handling

  • No API keys are hardcoded in repository files.
  • .env is not tracked and should never be committed.
  • Only report-generation inputs are sent to LLM when --use-llm is enabled.
  • Users should review and trust the configured endpoints before running.
  • SSL verification is enabled by default. Insecure SSL fallback requires explicit --allow-insecure-ssl.
  • Custom LLM endpoint hosts are blocked by default unless --allow-custom-llm-endpoint is provided.
  • Optional extension: set LLM_ALLOWED_HOSTS (comma-separated) to add trusted hosts.
  • Webhook only supports HTTPS and official Feishu/Lark/DingTalk domains.

Publishing note

  • For ClawHub publish, confirm the MIT-0 license checkbox in the web UI.
Usage Guidance
This skill looks like a legitimate weekly AI digest generator, but check these before installing or running: 1) The registry says no env vars, but the script needs LLM credentials (ARK_* or OPENAI_*). Don’t paste keys into the repo; set them only in a trusted runtime or local .env you control. 2) Inspect sources.json for any feeds you don't trust and consider removing unknown RSS URLs. 3) If you enable LLM usage, confirm OPENAI_BASE_URL or Ark endpoint is a provider you trust and set LLM_ALLOWED_HOSTS to restrict endpoints. 4) If you enable notifications, only set DIGEST_WEBHOOK_URL to an endpoint you control and trust (the script limits webhook suffixes, but verify the full host). 5) If you want to avoid sending fetched content to an external LLM, run without --use-llm or run locally offline. 6) Ask the publisher to correct the registry metadata (declare required env vars) before using in a shared/runtime environment. Running the script in an isolated environment and reviewing run_daily_digest.py yourself is recommended.
Capability Analysis
Type: OpenClaw Skill Name: ai-news-weekly-agent Version: 1.0.2 The skill bundle is a legitimate AI news aggregation tool that fetches RSS feeds, scrapes the OpenClaw leaderboard, and generates summarized reports using LLMs. The code in 'run_daily_digest.py' includes several proactive security features, such as HTTPS enforcement, an allowlist for LLM endpoints (e.g., Ark, OpenAI), and domain restrictions for webhooks (limited to Feishu, Lark, and DingTalk). No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; the script's capabilities are well-aligned with its stated purpose of generating weekly AI digests.
Capability Assessment
ℹ Purpose & Capability
Name/description match the code and SKILL.md: the script aggregates RSS feeds, scrapes an OpenClaw leaderboard, and optionally calls an LLM to generate text. However registry metadata lists no required environment variables while SKILL.md and the script clearly expect LLM credentials (ARK_* or OPENAI_*), and an optional webhook URL. That mismatch between declared requirements and runtime instructions is unexpected and should be resolved.
ℹ Instruction Scope
SKILL.md gives a concrete command to run the included Python script. The runtime instructions stay within the stated purpose (fetch RSS, scrape topclawhubskills.com, optionally call LLM, optionally post to a webhook). They explicitly mention enforced HTTPS, allowed LLM hosts, and webhook domain suffix checks. Be aware the script will fetch external URLs from sources.json and will send generated/prompts to whichever LLM endpoint you configure, so review endpoints and sources beforehand.
✓ Install Mechanism
No install spec is provided (instruction-only skill plus bundled Python file). There are no downloads or archive extractions in the manifest. The included code runs as a local script and uses standard library networking — no package registry installs or remote code pulls during install.
⚠ Credentials
The environment variables the SKILL.md requires (ARK_API_KEY, ARK_MODEL, ARK_ENDPOINT_ID or OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL, and optional DIGEST_WEBHOOK_URL) are appropriate for an LLM-backed report generator. The concern is the registry metadata claims 'Required env vars: none' which understates the actual runtime secrets the script may use. This inconsistency could cause users to unknowingly provide credentials. Also note that providing a webhook (DIGEST_WEBHOOK_URL) will transmit generated output to an external endpoint — the script restricts webhook hosts to certain suffixes but you should still verify the destination.
✓ Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configs, and has no install step that persists binaries into system paths. It writes generated reports to a local daily_docs/ directory but otherwise has normal, limited persistence behavior for a reporting script.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ai-news-weekly-agent
  3. After installation, invoke the skill by name or use /ai-news-weekly-agent
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Security policy improvements and stricter endpoint controls: - Clarified: Default security policy requires HTTPS endpoints and allowlisted LLM hosts. - Added: SSL verification now enabled by default; insecure connection fallback requires explicit flag. - Added: Custom LLM endpoints are blocked unless explicitly allowed with `--allow-custom-llm-endpoint`. - Added: `LLM_ALLOWED_HOSTS` environment variable to extend trusted LLM hosts. - Noted: Webhook notifications are now restricted to HTTPS and official Feishu/Lark/DingTalk domains.
v1.0.1
Initial release with environment configuration and documentation enhancements. - Added support for both Ark and OpenAI-compatible LLM providers via environment variables. - Updated the startup command to include `--llm-provider auto` for automatic provider selection. - Added documentation outlining required and optional environment variables in SKILL.md. - Included security, data handling, and external access details in the documentation. - Provided `.env.example` and updated `.gitignore` for environment variable management.
v1.0.0
AI News Weekly Agent 1.0.0 – Initial Release - Generates a weekly AI report in Markdown format. - Includes OpenClaw top skills, official announcements, industry news, and research paper ratio cap. - Designed for user requests about weekly AI digests or OpenClaw skills rankings with news. - Provides a simple command line interface for report generation.
Metadata
Slug ai-news-weekly-agent
Version 1.0.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is ai news weekly agent?

Generate a weekly AI report with OpenClaw top skills, official announcements, industry news, and capped paper ratio in Markdown format. It is an AI Agent Skill for Claude Code / OpenClaw, with 127 downloads so far.

How do I install ai news weekly agent?

Run "/install ai-news-weekly-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is ai news weekly agent free?

Yes, ai news weekly agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does ai news weekly agent support?

ai news weekly agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created ai news weekly agent?

It is built and maintained by Matilda-Grifin (@matilda-grifin); the current version is v1.0.2.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments