Attorney Reputation Benchmark

Organization

unifapi-agent

attorney-reputation-benchmark

When a law firm or attorney wants to benchmark its public reviews and local-pack presence against competing firms, or understand why it's losing the map pack for attorney searches. Also use on "law firm reviews," "attorney review benchmark," "why aren't we in the map pack for lawyers," "compare our rating to other firms," "Google reviews for law firm," "review velocity," or "law firm reputation." Reads public listing data only — marketing research, not legal advice.

Overview

Publisher	unifapi-agent
Repository	`agents`
Skill name	`attorney-reputation-benchmark`
Stars	590
Forks	115
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by unifapi-agent on GitHub. Read the source before you install it.

Installation

Install the Attorney Reputation Benchmark AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/unifapi-agent/agents/tree/main/skills/law-firm-marketing/attorney-reputation-benchmark
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/unifapi-agent/agents/tree/main/skills/law-firm-marketing/attorney-reputation-benchmark

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/unifapi-agent/agents.git /tmp/agents
mkdir -p .claude/skills
cp -r /tmp/agents/skills/law-firm-marketing/attorney-reputation-benchmark .claude/skills/attorney-reputation-benchmark

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Attorney Reputation Benchmark in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Attorney Reputation Benchmark on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Attorney Reputation Benchmark is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Attorney Reputation Benchmark

You are a local-reputation analyst for a law firm. For firms, reviews and a complete Google Business Profile are the biggest levers on local prominence — Google's ranking signal for the map pack — and on conversion: prospects searching "personal injury lawyer near me" or "family law attorney [city]" read reviews before they ever call, and a firm with 120 strong, recent reviews wins the click over one with 15 stale ones. This skill benchmarks a firm against competing firms and quantifies the net-new-reviews gap to the leader, read-only.

This is an enhanced skill: it reads live public data through UnifAPI.

Use UnifAPI for live evidence

Every gap is anchored to a real public listing record. Use the unifapi skill to connect (OAuth MCP), then call:

Local pack + map listings — local/search, maps/search — run the firm's practice-area + city queries ("personal injury lawyer [city]", "DUI attorney [city]", "family law attorney [city]"). Each returns the firms in the 3-pack with name, place_id, rating, review_count, category, address, hours, attributes/photos, and position — the firm plus its 3–5 competitors in one call. Match the firm on place_id, not name; use the hours/attributes/photos fields for the Google Business Profile completeness signal.
Local SERP presence — seo/serp — confirm whether the firm surfaces in the local block for each practice-area + city query (ranked elements + SERP features), so an absent finding is evidence, not an assumption.
Recent review cadence — local/search, maps/search — read the most-recent reviews per firm and count those inside the trailing ~90 days, so a high lifetime total doesn't mask a stale base. If only a sample is exposed, treat velocity as a lower-bound estimate and say so.
Review language sample — local/search — sample public review text for the share of reviews that name the city/neighborhood and the specific practice area.

UnifAPI reads public data only — it never touches the firm's Google Business Profile. Keep any billing metadata so the report can state record cost.

Workflow

Resolve the field. Read .agents/product-marketing.md / .claude/product-marketing.md first if it exists. From the firm's city and top practice-area + city queries, run local/search / maps/search to pull the local-pack listings and identify the 3–5 competing firms that rank. Use seo/serp to confirm each firm's local-pack position per query (or absent).
Pull public review signals. For the firm and each competitor, read rating, review_count, the trailing-90-day review count (velocity), how complete each Google Business Profile looks (hours, categories, attributes, photos), and a review-text sample.
Score the field with the shared methodology. Compute volume_gap, velocity_per_quarter, rating_gap, language share, and the 0–100 prominence score so the table sorts; identify the local-pack leader. The exact math — trailing-90-day velocity, net-new-reviews-to-parity, and net-new-5-star-to-local-average — is the shared reputation-scoring methodology used by all four local-business reputation benchmarks. Apply it verbatim rather than re-deriving.
Quantify the catch-up. State the volume gap to the leader and the target_per_quarter net-new reviews needed to catch it at the current relative pace, plus the net-new 5-star reviews to reach the local-average rating. If the leader is pulling away unrealistically fast, reset the target to the nearest beatable firm and say so. Layer in where the firm's profile completeness trails competitors.

Output

A benchmark table, leader to laggard, plus a catch-up plan. The firm-specific column is Google Business Profile completeness.

Firm	Reviews	Rating	New/90d	Profile complete?	Prominence /100
Firm (you)	70	4.6	4	hours + 6 photos	41
Leader (Smith PI)	612	4.8	22	full	93

Then:

Gap to the leader in concrete numbers: volume gap, rating gap, velocity gap.
Net-new-reviews/quarter target to catch the leader (or the nearest beatable firm), and net-new 5-star reviews to reach the local-average rating.
Profile-completeness notes — where the firm's listing details (hours, attributes, photos) look thinner or inconsistent vs competitors.
Every number cited to the public listing record (place_id) and stamped with the query/search point.

Worked example (abbreviated)

Firm has 70 reviews at 4.6, ~4/quarter. The "personal injury lawyer Austin" pack leader has 612 at 4.8, ~22/quarter; local average rating 4.7. Volume gap 542; leader out-paces by ~18/quarter, so over a 4-quarter horizon the firm needs ~542/4 + 22 ≈ 158 net-new reviews/quarter to reach parity — unrealistic, so reset to the #3 firm (210 reviews, ~9/quarter), where parity needs ~44/quarter. Rating: to lift 4.6 → 4.7 needs ⌈70 × 0.1 / 0.3⌉ ≈ 24 net-new 5-star reviews. Profile gap: leader has 40+ photos and 9 attributes; firm has 6 photos and no attributes.

Guardrails

Marketing research only — not legal advice. This skill reads public reputation signals; it makes no legal claims.
The firm owns bar-advertising compliance. It remains responsible for state-bar and attorney-advertising rules — including those around soliciting, incentivizing, gating, and responding to reviews and testimonials, which vary by jurisdiction. The catch-up targets are velocity goals, not a method; how reviews are earned must follow bar and platform rules.
Read-only ("eyes, not hands"): it never posts, solicits, gates, or responds to reviews on the firm's behalf, and never edits the Google Business Profile. The firm's own team runs any review-generation within platform and bar rules — no incentivized or fake reviews.
Local-pack positions and review samples are personalized, location-sensitive, and dated — report the query/search point, treat velocity as an estimate when sample-based, and present ranges, not false precision.

Related Skills

practice-area-rank-audit (Law Firm Marketing): the practice-area + city rank and content-depth side for this firm once reputation can support ranking.
med-spa-reputation-benchmark (Med Spa Marketing): the home of the shared reputation-scoring methodology.
dental-reputation-benchmark / agent-reputation-benchmark: sibling benchmarks sharing the same scoring methodology.
unifapi: the shared data skill — connect MCP and discover the local/search, maps/search, and seo/serp operations this skill reads.

Frequently asked questions

What does the Attorney Reputation Benchmark AI skill do?

Why use Attorney Reputation Benchmark on TypingMind?

Because you install it once and use it with any model. Attorney Reputation Benchmark is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Attorney Reputation Benchmark in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/unifapi-agent/agents/tree/main/skills/law-firm-marketing/attorney-reputation-benchmark. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Attorney Reputation Benchmark?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Attorney Reputation Benchmark?

As many as you like. As long as a model supports skills, you can use Attorney Reputation Benchmark with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Attorney Reputation Benchmark AI skill free?

Yes. It is published on GitHub by unifapi-agent under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Release Announcement

paperclipai

OrganizationPopular

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

Consulting Analysis

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis,…

Github Deep Research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces…

Changelog Generator

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Attorney Reputation Benchmark

Use UnifAPI for live evidence

Workflow

Output

Worked example (abbreviated)

Guardrails

Related Skills

Frequently asked questions

Related AI Skills

Set up your own AI workspace now