Clients

Use to build and maintain a personal client system, one organized place per client for contacts, project history, documents (contracts, invoices, proposals), communication logs, preferences, and a leads pipeline. Trigger when the user mentions tracking a client, "pull up context on X before my call", logging a meeting, remembering a client's preferences/payment terms, or managing leads. Great companion to the agency skill for solo freelancers.From its SKILL.md

Install

npx -y skills add mehtab78/skills --skill clients

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, 647 tokens by cl100k_base, as published. Nobody here has run it

Personal client system

Give the user a durable, per-client memory so nothing lives only in their head or scattered inboxes. Keep it in ~/clients/ and grow it as you go.

How to behave

User names a client → offer to create or update that client's profile.
User is heading into a call/decision → surface the relevant history unprompted.
User shares a document → help file it under the right client.
First use → create the ~/clients/ workspace.

Layout

~/clients/
├── active/
│   └── acme-corp/
│       ├── profile.md
│       ├── projects/
│       ├── documents/          # contracts, invoices, proposals, assets
│       ├── communications/
│       └── notes.md
├── past/
├── leads/
└── templates/

Within a client folder, keep documents sorted (contracts/, invoices/, proposals/, assets/, and a received/ for their materials), one folder per project, and a running communications log. If the contracts skill is also installed, that's the canonical home for executed contracts and their metadata (~/contracts/{name}/) — keep a link in this client's contracts/ folder instead of a second copy of the file.

What a profile holds

Company basics, all contacts with roles, and, most valuable, the operating details you keep forgetting: preferred channel, meeting habits, who signs off on what, payment terms, timezone, and any recurring quirks. A short profile might capture that the primary contact prefers Slack, that anything over $5k needs CEO approval, and that they pay Net 30.

Track per project

Scope, budget, timeline, status, milestones (as a checklist), the team/ stakeholders, where deliverables live, and notes on any scope changes and whether they were approved.

Log communications

After meaningful calls or threads, jot the date, what was decided, and the next step. A month later, "we approved the motion-graphics add-on on the 10th" is the difference between looking sharp and looking lost.

Keep a leads pipeline

In leads/, sort prospects hot / warm / cold with the next action and a date, so follow-ups don't slip.

What to surface, and when

Proactively raise things like: "last contact with Acme was two weeks ago," "Sarah prefers Slack," "their contract renews next month," or "open invoice: $5,000, sent 15 days ago." Before a meeting, pull current project status, the last communication, open items, and their preferences.

Grow it gradually

Start by making a folder for each active client, add key contacts and preferences, move documents into the structure, and log communications after meetings. The failure modes to avoid: documents scattered outside the client folder, important calls never logged, open invoices forgotten, and missed renewal dates.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most log analysis skills give in 647 tokens

Counted across 325 of the 341 authors here whose files we hold, read 2026-09-06

Use structured JSON loggingin 32 of 325, across 30 files
Link every alert to a runbookin 15 of 325, across 13 files
Alert on symptoms, not causesin 11 of 325, across 10 files
Include correlation IDs in every log linein 10 of 325
Propagate trace context across service boundariesin 9 of 325, across 8 files
Include request IDs for correlationin 8 of 325, across 6 files
Include trace_id in every structured log entryin 8 of 325, across 7 files
Include request and user context in every log entryin 8 of 325
Correlate logs and traces with shared trace IDin 7 of 325, across 6 files
Record exceptions and set span status on errorsin 7 of 325
Confirm connection is ACTIVE before running workflowsin 6 of 325, across 3 files
Call RUBE_SEARCH_TOOLS first for current schemasin 6 of 325, across 3 files

Said here and by no other author read

create the clients workspace on first use
offer to create or update the named client's profile
surface relevant client history before calls or decisions
before meetings, pull status, last communication, open items, and preferences
file shared documents under the right client
keep documents sorted by type within client folders

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.