agentleFS
sammollaeisammollaei/law-firm-skills/skills/setup/SKILL.md

setup

Skill1 starsChanged 32 days agoMITView on GitHub

Help a lawyer, law firm owner, or practice manager get started with Law Firm Skills. Choose a first workflow, show a fictional result, and explain supplied-data and already-connected-tool modes. Use when installing this collection or asking how to start; not for unrelated software setup.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-atomic-chat-tool, add-dashboard and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    add-atomic-chat-tool

    Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

    Also in 8 projects that use this

  • MicrosoftSkill

    add-dashboard

    Add a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.

    Also in 8 projects that use this

  • +10 more from microsoft

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 5

    Distinctive

    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:

    Use information already supplied.

    line 18
  2. Distinctive:

    Do not ask for client names, credentials, financial records, or account access to demonstrate the collection.

    line 22
  3. Distinctive:

    Use meeting-prep before a call and verify to check a completed result.

    line 29
  4. Distinctive:

    If private workspace context is useful, propose a short record of role, goal, source coverage, timezone, and approval rules.

    line 60
  5. Distinctive:

    Do not install tools, connect accounts, create automations, send messages, or modify business records during setup.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 169 edited versions of this file we could read. “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

Get started with Law Firm Skills

Help the user get one useful result with minimal setup. This collection contains 18 practice-management workflows plus this onboarding skill. Installation grants no access to accounts, permission to act, or ongoing background work.

First conversation

Use information already supplied. Ask only for missing information that changes the first workflow: their role, the outcome they want, whether they will supply notes or use tools already authorized in this workspace, and applicable approval boundaries. Bundle these in one short question rather than a long questionnaire. Do not ask for client names, credentials, financial records, or account access to demonstrate the collection. If they want to try it immediately, use the fictional example below without blocking on configuration.

Choose decide or playbook for the first result. Use morning once source coverage is understood. Other entry points: meeting for notes to actions; follow-up for existing commitments; build for an idea requiring a specification and approval. Use meeting-prep before a call and verify to check a completed result. Explain that independent review needs a separate authorized provider and an approved evidence packet; missing access is reported, not silently substituted. Name the intended skill and load it using the host's skill selector when available. If it is not installed or available, say so and provide the explicit request the user can paste. Do not claim an unavailable skill was invoked.

Fictional first result

Example: A two-lawyer firm can improve appointment reminders or replace intake software this month. Missed appointments are the measured problem; the existing software already supports reminders. No cost, volume, or conversion data was provided. The user wants advice only.

Show a compact decision: test the existing reminder feature first; it addresses the observed issue with fewer implementation assumptions. Ask the responsible operator to confirm permission and baseline attendance before any pilot. Do not invent savings, a deadline, or a completed configuration. Reconsider if evidence shows the current software cannot deliver reliable reminders or the main cause lies elsewhere. Label this as fictional, not a client result.

Explain use and access

  • Supplied-data mode: use permitted notes, exports, or a fictional example.
  • Connected mode: use only tools actually available and authorized by the user. This collection bundles no inbox, CRM, calendar, task, or video connector.
  • Claude Code standalone: /morning. Claude plugin: /law-firm-skills:morning.
  • Codex: select the skill or use $morning. ChatGPT: select the installed plugin with the @ selector; a public directory listing is required for that route.
  • A pasted workflow prompt is a fallback, not native installation.

If private workspace context is useful, propose a short record of role, goal, source coverage, timezone, and approval rules. Save only in a user-approved private location with permission, never inside the public plugin or repository. Do not install tools, connect accounts, create automations, send messages, or modify business records during setup. End with one suggested first request.

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.