More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Tool Fit: A Yes or No Before You Install

    1

    Send an agent a link to a new tool and you get a summary of its README instead of a decision. Your agent reads the repo, checks it against your machine and existing setup, and opens with yes, no, or one condition.

    Free

    Security scanned
    Tool Fit: A Yes or No Before You Install

    Tool Fit: A Yes or No Before You Install

    Example session with this skill installed

    • Read your context and instructions
    • Compiled the tool fit

    The agent reads the README, MIT license, and last release from 3 weeks ago, and confirms the tool supports macOS on Apple silicon. It searches your skills and MCP servers and finds an installed skill that already does the same job for one of its two features. It greps the source and finds it posts usage data to its own analytics endpoint by default. It answers: "Only if you need the second feature; you already have the first." Then one sentence on what it is with an example, the overlap by name, license and maturity notes, the telemetry finding with the setting to turn it off, and the install command.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    About this skill

    A new repo or product link arrives with "can I use this?" and the usual answer restates the README: what it is, its features, how to install it. You still have to work out whether it fits your machine, duplicates something you already run, has a license you can use at work, or sends data somewhere.

    This skill makes the agent answer the question. It reads the README, the license, the latest release or commit date, and the install requirements, and checks the requirements against your machine. It searches your existing setup for the same job: skill descriptions under ~/.claude/skills, hooks in ~/.claude/settings.json, your scripts folder if you keep one, and your MCP servers. If the tool runs code locally or calls the network, it looks at what it sends and where, and greps the source for endpoints when the repo is small enough. The answer opens with yes, no, or "only if" one condition, then covers what it is with one concrete example, the overlap by name, license, maturity, privacy, and the install command only when the verdict is yes.

    The proof

    There is no measurement for this skill, and the listing claims none. Its check is the answer shape: the verdict is on the first line, the answer names at most one condition or one cheap test, never a list, and the overlap line either names what it duplicates or states "no overlap" with what was searched. The skill also never installs, signs up for, or runs the tool until you say so.

    What you get

    One SKILL.md with the four-step procedure and the fixed answer shape.

    How to use

    1. Add the skill folder to your agent's skills directory (for Claude Code, ~/.claude/skills/tool-fit/).
    2. Paste a GitHub or product link and ask "can I use this?" or "is this worth adding?"
    3. Read the verdict line, then the overlap and checks, and run the install command yourself if it says yes.

    Source and license

    Free to use and MIT licensed. The full source, install steps, and issue tracker are on GitHub at https://github.com/robertmnyborg/everyday-agent-skills.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.

    The overlap check assumes a Claude Code setup with skills under ~/.claude/skills; on other agents it relies on what you tell it. Privacy checks depend on readable source, so closed-source or very large tools get a shallower review. It does not install or test-run the tool. License advice is a reading of the license text, not legal advice.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Software
    Claude Code

    Permissions

    Allowed Hosts

    the tool's repo or product site

    File Scopes

    ~/.claude/skills/*/SKILL.md
    (read)
    ~/.claude/settings.json

    Read-only. It does not install, sign up, or run the tool.

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    Agents summarize what a tool does. They rarely compare it with what you already have installed or check where it sends data, and they tend to end with a list of "it depends". This skill requires a verdict on the first line and an overlap check against your setup.

    The verdict and checks work with any agent that reads SKILL.md and can browse. The overlap search looks in Claude Code locations (~/.claude/skills and settings.json); on other agents it compares against what you describe.

    No. It gives the install command only when the verdict is yes, and runs nothing until you say so.

    It reads the source for network endpoints when the repo is small enough to read. Closed-source or very large tools get a shallower check, and the answer says what it could and could not see.

    On GitHub at https://github.com/robertmnyborg/everyday-agent-skills, under the MIT license. Every file in this package is there, plus the README and install steps.

    New in Productivity

    Free