agentleFS
Sign inStart free
Red-empty-potatoRed-empty-potato/ai-agent-skills/skills/ai-tools-radar/SKILL.md

ai-tools-radar

Skill0 starsChanged 3 months agoMITView on GitHub

Discover newly released AI tools, evaluate them against criteria (cost, privacy, integrations), and add them to a tracking list. 发现新 AI 工具并评估入库。

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify with the official source before adding — a repo with no releases or a dead site is a red flag.

    line 51
  2. Distinctive:

    Keep entries short; this is a radar, not a review site.

    line 52
  3. Distinctive:

    Update the same tracker file over time — a growing dated history is the real value.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AI Tools Radar | AI 工具雷达

Scan for newly released AI tools, evaluate each against a small set of practical criteria, and maintain a running "radar" list the user can browse.

扫描新发布的 AI 工具，用一套实用标准逐项评估，并维护一份可持续浏览的「雷达」清单。

When to use | 适用场景

  • The user asks: 「最近有什么新的 AI 工具」「what new AI tools came out this month」
  • Keeping a personal tracker of interesting tools to try later
  • Evaluating whether a new tool is worth switching to / adopting

Workflow | 工作流程

  1. Scan — web search for newly released / trending AI tools (this month preferred). Include categories: AI coding, AI agents, LLM ops, media/generation, productivity, open source.
  2. Shortlist — keep tools that are actually new (or newly notable) and not vaporware.
  3. Evaluate each on these criteria (bilingual output):
    • 它做什么 What it does — one line
    • 成本 Cost — free / freemium / paid; rough price if public
    • 隐私 Privacy — local / cloud; data handling if stated
    • 集成 Integrations — API, GitHub, Slack, etc.
    • 值得试 Worth trying? — yes / maybe / no + one-line why
  4. Verify claims — prefer the tool's official site/repo; flag marketing claims you can't confirm.
  5. Update the tracker — append to a radar.md (or the user's chosen file) with a dated section, so the list grows over time. Keep past entries; add a ## <week date> heading.

Output format | 输出格式

# 🛰️ AI Tools Radar — <month week> | 本周工具雷达

## 🆕 New this week | 本周新增
| Tool | 一句话 What | Cost | Privacy | Integrations | Worth trying |
|---|---|---|---|---|---|
| ... | ... | ... | ... | ... | ✅ / 🟡 / ❌ |

### Notes | 备注
- **<Tool>** — why it stands out / why to skip.

Tips | 提示

  • New ≠ useful: many "new AI tools" are thin wrappers around an API. Say so when it looks like one.
  • Verify with the official source before adding — a repo with no releases or a dead site is a red flag.
  • Keep entries short; this is a radar, not a review site.
  • Update the same tracker file over time — a growing dated history is the real value.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free