Agent skill

Practice Area Rank Audit

by unifapi-agent in unifapi-agent/agents

When a law firm or attorney wants to know where it ranks for each practice-area + city query and what's holding it back.

MITAuto-check passedMarketing & SEO

Install Practice Area Rank Audit

skills CLI
$ npx skills add unifapi-agent/agents --skill practice-area-rank-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install unifapi-agent/agents practice-area-rank-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/law-firm-marketing/practice-area-rank-audit .claude/skills/practice-area-rank-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
practice-area-rank-audit
GitHub stars
589
Token cost
~2.5k tokens
SKILL.md length
1,075 words
Files
3 (incl. references)
Skills in repo
47
Repo updated
First seen
Licence
MIT

At a glance

When a law firm or attorney wants to know where it ranks for each practice-area + city query and what's holding it back.

  • Works in 5 steps: Build the matchup grid. Cross the firm's… → Pull live rank per cell. Via… → Benchmark the firms above. For each cell… → …
  • Tasks that involve SEO audit
  • SKILL.md covers Use UnifAPI for live evidence, Workflow, Scoring rubric and Output: rank grid + content…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Practice Area Rank Audit is an agent skill from unifapi-agent/agents. When a law firm or attorney wants to know where it ranks for each practice-area + city query and what's holding it back. Also use on "personal injury lawyer [city] ranking," "family law attorney SEO," "where do we rank for practice areas," "law firm local pack," "why aren't we ranking for [practice area]," "attorney content gaps," or "law firm SEO audit." Reads public SERP and map data only — marketing research, not legal advice.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/practice-area-method.md`).

It sits in Marketing & SEO, covering SEO audit. The repository describes itself as: Open-source marketing agents for Claude, ChatGPT, Codex, OpenClaw & Hermes. One plugin: SEO audits, GEO / AI-visibility, local SEO, KOL pricing, social listening & competitive… The licence is MIT.

When your agent uses it

  • Tasks that involve SEO audit

Example prompts

  • “s holding it back. Also use on”
  • “family law attorney SEO,”
  • “where do we rank for practice areas,”
  • “/practice-area-rank-audit”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Build the matchup grid. Cross the firm's real revenue practice areas (personal injury, family law, criminal defense, estate planning, …)…
  2. Pull live rank per cell. Via local/search + maps/search (looping the location param) record the firm's local-pack position (1–3, extended…
  3. Benchmark the firms above. For each cell capture the firms ranking above the target in the pack and organically, with their review_count…
  4. Score content depth per ranking page. For a higher-ranking firm, pull seo/competitors/relevant-pages to find its practice-area pillar and…
  5. Score and rank the cells, then write the prioritized gap list: practice areas where rank is weak and content is thin, where new depth…

What it can do on your machine

Read from SKILL.md and the folder at commit fb53247. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Practice Area Rank Audit loads about 2.5k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 1,075 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~115
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from unifapi-agent/agents at commit fb53247, republished under its MIT licence (© unifapi-agent). 1,075 words, ~2,468 tokens.

Download SKILL.mdSave it as .claude/skills/practice-area-rank-audit/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
practice-area-rank-audit
description
When a law firm or attorney wants to know where it ranks for each practice-area + city query and what's holding it back. Also use on "personal injury lawyer [city] ranking," "family law attorney SEO," "where do we rank for practice areas," "law firm local pack," "why aren't we ranking for [practice area]," "attorney content gaps," or "law firm SEO audit." Reads public SERP and map data only — marketing research, not legal advice.
license
MIT
metadata.author
UnifAPI
metadata.version
1.0.0

Practice Area Rank Audit

You are a legal-marketing search analyst. Law firms compete query by query: "personal injury lawyer [city]", "family law attorney [city]", "DUI lawyer [city]". Each practice area is its own race, and "near me" legal searches — high hire-intent, mostly mobile — are won by firms that rank in both the local pack and organic results and back each practice area with a deep page. This skill audits the firm's rank for every practice-area × city query, benchmarks it against the firms outranking it, and flags where thin content is the reason it's losing.

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

Use UnifAPI for live evidence

A legal rank is personalized and proximity-weighted — you can't reason it from memory, you pull the actual pack and SERP for the actual query at the actual search point. Use the unifapi skill to connect (OAuth MCP), then call:

  • Local-pack positions — local/search, maps/search — for each practice-area + city query, the firms in the 3-pack and their position. Each listing carries name, place_id, rating, review_count, category, address — the prominence numbers behind each gap. Loop the location param across the firm's office(s) and the city centroid to build the grid. Tie the target to its place_id, not its name — firm names collide.
  • Organic SERP — seo/serp — the organic positions for the same query, the firm's ranking URL, the competing firms' ranking pages, and which SERP features (local pack, People-Also-Ask, ads) sit above the fold. A firm can hold the blue links yet be absent from the pack — keep the two distinct.
  • AI-answer status — geo/serp — whether the firm is cited (is_target) when someone asks an AI assistant for a "[practice area] lawyer in [city]", which sources the answer names, and which prompts have no clear local winner yet.
  • Who outranks + their winning page — seo/competitors/relevant-pages (a higher-ranking firm's top organic pages — exposes the practice-area pillar doing the relevance work) and seo/competitors/domain-rank-overview (that firm's domain rank + organic traffic, so a content-depth gap is sized, not just asserted).

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

Workflow

  1. Build the matchup grid. Cross the firm's real revenue practice areas (personal injury, family law, criminal defense, estate planning, …) with its city/cities, splitting broad areas into the sub-niches competitors page out separately (personal injury → car accident, slip-and-fall, wrongful death). For each cell add the variants prospects type: bare "[practice area] lawyer [city]", "near me", "best [practice area] lawyer [city]". 5–15 core cells is a workable audit; more becomes noise. (Read .agents/product-marketing.md / .claude/product-marketing.md first if it exists.)
  2. Pull live rank per cell. Via local/search + maps/search (looping the location param) record the firm's local-pack position (1–3, extended 4–10, or absent); via seo/serp its organic position and ranking URL; via geo/serp its AI-answer status. Stamp every position with search point, language, and timestamp.
  3. Benchmark the firms above. For each cell capture the firms ranking above the target in the pack and organically, with their review_count and rating from the listing, so each gap has named competitors and a prominence number.
  4. Score content depth per ranking page. For a higher-ranking firm, pull seo/competitors/relevant-pages to find its practice-area pillar and supporting subpages, and seo/competitors/domain-rank-overview to size its authority; compare the firm's page against it on length and supporting-subpage coverage (rubric below).
  5. Score and rank the cells, then write the prioritized gap list: practice areas where rank is weak and content is thin, where new depth should move the needle most.

See references/practice-area-method.md for the full grid-scoring, content-depth rubric, and gap-attribution checklist.

Show full SKILL.md (475 more words)Show less

Scoring rubric

Two scores combine into one priority. Rank score captures where the firm sits; content-depth score captures whether its page earns the rank.

Rank state (per cell)Rank score
In local pack 1 + organic top 35
In local pack 2–3 OR organic top 34
Extended pack 4–10 OR organic 4–102
Absent from pack but ranks organically (page 2+)1
Absent entirely0
Content depth of the firm's ranking pageDepth score
Deep page (~1,500–2,500 words) + 3–5 supporting subpages5
Solid page (~1,500+ words), few/no subpages3
Thin page (<800 words) or only a service-list stub1
No dedicated practice-area page at all0

Assign each practice area a priority weight (1–3): 3 = core revenue practice, 1 = peripheral. Opportunity = (5 − rank_score) × weight, and the gap is content-attributable when depth_score ≤ 2 and a higher-ranking competitor's seo/competitors/relevant-pages page scores higher. Sort by opportunity descending; surface content-attributable gaps first because they are the most actionable lever a firm controls (Google rewards demonstrated topical depth on competitive legal niches).

Output: rank grid + content depth + gaps

markdown
# Practice Area Rank Audit — <firm> — <date>

Search params: location(s) <…> · language <…>

## Rank grid (one row per practice-area × city)

| #   | Practice area × city     | Local pack | Organic | AI cited? | Outranked by (reviews)          | Firm page words / subpages | Depth score | Opportunity | Likely cause                  |
| --- | ------------------------ | ---------- | ------- | --------- | ------------------------------- | -------------------------- | ----------- | ----------- | ----------------------------- |
| 1   | Personal injury · Austin | absent     | 14      | no        | Smith PI (612), Jones Law (430) | 420 / 0                    | 1           | 12          | thin content + low prominence |

## Prioritized gaps

- Cells sorted by opportunity, content-attributable gaps flagged first.
- Each gap with its concrete fix surface: "PI page is 420 words with no sub-topic pages; the firm outranking you (`seo/competitors/relevant-pages`) runs a 2,100-word pillar with 4 sub-pages."
- Every position and page metric cited to the live SERP/map record, stamped with search point + date.
- Record cost consumed (or best estimate if billing metadata is unavailable).
Worked example (abbreviated)

A 3-attorney injury + family firm in Austin. Grid = (personal injury, car accident, family law, divorce) × Austin, with "near me" + "best" variants. "Car accident lawyer Austin" → firm absent from pack (local/search), organic #14 (seo/serp); the two firms above run 1,900- and 2,400-word pillars with car-accident sub-pages (rear-end, drunk-driving, pedestrian) per seo/competitors/relevant-pages and carry 600+ reviews. Firm's car-accident page: 380 words, no subpages → depth 1, rank 0, weight 3 → opportunity 15, content-attributable, ranked #1. "Estate planning Austin" scored rank 4 / depth 3, weight 1 → opportunity 1, deprioritized. The brief leads with the car-accident pillar + sub-pages, not estate planning.

Guardrails

  • Marketing research only — not legal advice. This skill audits visibility and content depth; it makes no legal claims and never drafts attorney-advertising copy that implies, predicts, or guarantees a case outcome.
  • The firm remains responsible for state-bar and attorney-advertising compliance on anything it publishes — disclaimers, "specialist"/"expert" usage rules, testimonial and case-result rules, jurisdictional notices. Word-count and subpage targets are SEO guidance, not a license to publish unreviewed claims.
  • Read-only ("eyes, not hands"). It reports rankings and gaps; it never edits a Google Business Profile, website, or listing, and never posts. The firm's own team makes any changes.
  • Confirmed vs inferred. Report the city/query/search point each position was measured at; label positions read off the pack as confirmed and depth attribution as inferred. Rankings are personalized and dated — treat each as a snapshot, present ranges not false precision. Word count and subpage count are public-page estimates; verify before acting.
  • attorney-reputation-benchmark (Law Firm Marketing): the reviews / local-pack prominence side for this firm — pair a prominence gap here with its review math.
  • local-pack-audit (Local SEO): the general-purpose multi-location local-pack audit and proximity/prominence/relevance attribution checklist this rank loop is built on.
  • unifapi: the shared data skill — connect MCP and discover the operations above.

© unifapi-agent, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/law-firm-marketing/practice-area-rank-audit of unifapi-agent/agents.

  • SKILL.md
  • README.md
  • references/practice-area-method.md

Open the folder on GitHubat commit fb53247

Compare with similar skills

Practice Area Rank Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Practice Area Rank Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Practice Area Rank Audit this skillunifapi-agent/agents589—~2.5kAutomated safety check: PassMIT
Local Legal SEO Auditsickn33/agentic-awesome-skills47k2 repos~3.2kAutomated safety check: PassMIT
Hreflang and International SEOAgriciDaniel/claude-seo19k5 repos~3.4kAutomated safety check: PassMIT
Google SEO APIsAgriciDaniel/claude-seo19k1 repos~4.2kAutomated safety check: PassMIT
Evaluate Skillevery-app/open-seo23k—~1.8kAutomated safety check: NotesMIT
FLOW SEO FrameworkAgriciDaniel/claude-seo19k2 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Local Legal SEO Audit

    sickn33/agentic-awesome-skills

    Audit and improve local SEO for law firms, attorneys, forensic experts and legal/professional services sites with local presence, focusing on GBP, directories, E-E-A-T and practice/location pages.

    47k GitHub starsUsed in 2 repos~3.2k tokens
    Marketing & SEOAuto-check passed
  • Hreflang and International SEO

    AgriciDaniel/claude-seo

    Audits, validates and generates hreflang tags for multi-language and multi-region sites in HTML, HTTP headers or XML sitemaps, flagging common code and return-tag mistakes.

    19k GitHub starsUsed in 5 repos~3.4k tokens
    Marketing & SEOAuto-check passed
  • Google SEO APIs

    AgriciDaniel/claude-seo

    Pulls real Google data for SEO work: Search Console, PageSpeed Insights, CrUX field data, the Indexing API and GA4 organic traffic, through /seo google commands.

    19k GitHub starsUsed in 1 repo~4.2k tokens
    Marketing & SEOAuto-check passed
  • Evaluate Skill

    every-app/open-seo

    Test a candidate OpenSEO skill end to end by running fresh, isolated Codex sessions against the local backend and scoring the reports they save.

    23k GitHub stars~1.8k tokensUpdated yesterday
    Marketing & SEOAuto-check: notes
  • FLOW SEO Framework

    AgriciDaniel/claude-seo

    Brings the FLOW framework's stage-specific SEO prompts into the agent, from keyword discovery through backlinks, on-page work and conversion to local SEO, loaded on demand.

    19k GitHub starsUsed in 2 repos~1.4k tokens
    Marketing & SEOAuto-check passed
  • GEO-First SEO Audit Tool

    zubair-trabzada/geo-seo-claude

    Audits a website for AI search visibility across ChatGPT, Claude, Perplexity and Google AI Overviews while checking traditional SEO, schema and E-E-A-T content quality.

    11k GitHub stars~2.8k tokensUpdated today
    Marketing & SEOAuto-check: notes

More from unifapi-agent/agents

All 47 skills in this repo
  • LLM Mention Tracking

    unifapi-agent/agents

    When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of prompts, and how that share of voice compares to named competitors over…

    589 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Buying Signal Monitor

    unifapi-agent/agents

    When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that…

    589 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Customer Research

    unifapi-agent/agents

    When the user wants to research customers from public communities, or synthesize customer language, pains, and objections.

    589 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Keyword Research

    unifapi-agent/agents

    When the user wants to research keywords, find keyword opportunities, run a keyword gap analysis, build topic clusters, or compare what competitors rank for.

    589 GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Schema

    unifapi-agent/agents

    When the user wants to add, fix, or optimize schema markup and structured data on their site.

    589 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • SEO Audit

    unifapi-agent/agents

    When the user wants to audit, review, or diagnose SEO issues on their site.

    589 GitHub stars~3.4k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Practice Area Rank Audit

What does Practice Area Rank Audit do?

When a law firm or attorney wants to know where it ranks for each practice-area + city query and what's holding it back. Practice Area Rank Audit is an agent skill from unifapi-agent/agents. When a law firm or attorney wants to know where it ranks for each practice-area + city query and what's holding it back.

When should I use Practice Area Rank Audit?

Practice Area Rank Audit fits situations like: tasks that involve SEO audit.

How do I install Practice Area Rank Audit in Claude Code?

Run `npx skills add unifapi-agent/agents --skill practice-area-rank-audit -a claude-code`. Or copy the skill folder (skills/law-firm-marketing/practice-area-rank-audit in unifapi-agent/agents) into .claude/skills/practice-area-rank-audit in your project. Claude Code loads it when a task matches its description.

How do I install Practice Area Rank Audit in Codex?

Run `npx skills add unifapi-agent/agents --skill practice-area-rank-audit -a codex`. Or copy the skill folder (skills/law-firm-marketing/practice-area-rank-audit in unifapi-agent/agents) into .agents/skills/practice-area-rank-audit in your project. Codex loads it when a task matches its description.

Can I use Practice Area Rank Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add unifapi-agent/agents --skill practice-area-rank-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/practice-area-rank-audit, .gemini/skills/practice-area-rank-audit, .github/skills/practice-area-rank-audit and .opencode/skills/practice-area-rank-audit in your project.

What does Practice Area Rank Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Practice Area Rank Audit is instructions for the agent only.

Does Practice Area Rank Audit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Practice Area Rank Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Practice Area Rank Audit use?

Practice Area Rank Audit is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Practice Area Rank Audit use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Practice Area Rank Audit?

Skills that share tags, products or a category with Practice Area Rank Audit: Local Legal SEO Audit (sickn33/agentic-awesome-skills, 47k stars), Hreflang and International SEO (AgriciDaniel/claude-seo, 19k stars), Google SEO APIs (AgriciDaniel/claude-seo, 19k stars) and Evaluate Skill (every-app/open-seo, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Practice Area Rank Audit?

unifapi-agent (a GitHub organization) maintains it in unifapi-agent/agents, which has 589 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on September 5, 2026.

Source: unifapi-agent/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.