Client lookup and history — searches all output files for a client and displays a comprehensive summary

MITAuto-check passedSales & Support

Install Agency Client

skills CLI
$ npx skills add zubair-trabzada/ai-agency-claude --skill agency-client -a claude-code

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

GitHub CLI
$ gh skill install zubair-trabzada/ai-agency-claude agency-client --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/zubair-trabzada/ai-agency-claude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agency-client .claude/skills/agency-client && 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
agency-client
GitHub stars
151
Token cost
~3.2k tokens
SKILL.md length
1,086 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Client lookup and history — searches all output files for a client and displays a comprehensive summary

  • Works in 7 steps: Normalize the Client Name for Search → Search for All Client Files → Extract Data from Each File → …
  • Tasks that involve Proposals and quotes
  • SKILL.md covers Trigger, Step 1 — Normalize the Client…, Step 2 — Search for All Client… and Step 3 — Extract Data from…, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agency Client is an agent skill from zubair-trabzada/ai-agency-claude. Client lookup and history — searches all output files for a client and displays a comprehensive summary

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering Proposals and quotes. The repository describes itself as: AI Agency Command Center for Claude Code — orchestrates 5 AI teams (Marketing, Sales, Legal, Reputation, GEO/SEO) into a unified zero-employee agency. 9 skills, 5 parallel… The licence is MIT.

When your agent uses it

  • Tasks that involve Proposals and quotes

Example prompts

  • “/agency-client”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Normalize the Client Name for Search
  2. Search for All Client Files
  3. Extract Data from Each File
  4. Determine Pipeline Stage
  5. Calculate Revenue Opportunity
  6. Display the Client Summary
  7. Recommended Next Steps Logic

What it can do on your machine

Read from SKILL.md and the folder at commit 172a6c2. 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.

    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

Agency Client loads about 3.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 1,086 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

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 zubair-trabzada/ai-agency-claude at commit 172a6c2, republished under its MIT licence (© zubair-trabzada). 1,086 words, ~3,214 tokens.

Download SKILL.mdSave it as .claude/skills/agency-client/SKILL.md (or your agent's skills folder).
name
agency-client
description
Client lookup and history — searches all output files for a client and displays a comprehensive summary

Client Lookup & History

You are the Client Lookup agent for the AI Agency Command Center. When the user runs /agency client <name>, you search the current working directory for ALL files related to that client and produce a comprehensive history timeline with scores, findings, pipeline stage, and revenue opportunity.

Trigger

This skill activates when the user runs:

/agency client <name>

Where <name> is a business name, client name, or partial match string. Examples:

  • /agency client "Joe's Plumbing"
  • /agency client joesplumbing
  • /agency client Joe

Take the client name provided by the user and prepare multiple search variants:

  1. Exact name as provided (e.g., Joe's Plumbing)
  2. Stripped name — remove apostrophes, hyphens, special characters (e.g., Joes Plumbing)
  3. Condensed name — remove spaces and lowercase (e.g., joesplumbing)
  4. Individual words — split into separate search tokens (e.g., Joe, Plumbing)
  5. PascalCase variant — for filename matching (e.g., JoesPlumbing)
  6. Hyphenated variant — for filename matching (e.g., Joes-Plumbing)

These variants enable fuzzy matching across different file naming conventions used by the 5 tool suites.

Step 2 — Search for All Client Files

Search the current working directory for ALL files that match any variant of the client name. Use Glob and Grep to find files across these categories:

Agency Command Center outputs:

  • AGENCY-ONBOARD-*.md — Full agency onboard reports
  • AGENCY-PROPOSAL-*.md — Service proposals
  • AGENCY-REPORT*.pdf — Unified PDF reports
  • AGENCY-PIPELINE.md — Check if this client appears in the pipeline

Marketing Suite outputs:

  • MARKETING-AUDIT*.md — Marketing audit reports
  • MARKETING-REPORT*.md — Marketing reports
  • MARKETING-REPORT*.pdf — Marketing PDF reports
  • MARKETING-PROPOSAL*.md — Marketing proposals
  • MARKETING-SEO*.md — SEO audit reports
  • MARKETING-FUNNEL*.md — Funnel analysis reports
  • MARKETING-COMPETITORS*.md — Competitive analysis

Sales Team outputs:

  • PROSPECT-ANALYSIS*.md — Full prospect analysis
  • SALES-REPORT*.md — Sales reports
  • SALES-REPORT*.pdf — Sales PDF reports
  • SALES-PROPOSAL*.md — Sales proposals
  • SALES-RESEARCH*.md — Company research
  • SALES-CONTACTS*.md — Decision maker intelligence
  • SALES-ICP*.md — Ideal customer profile
  • SALES-OUTREACH*.md — Outreach sequences

Reputation Manager outputs:

  • REPUTATION-AUDIT-*.md — Full reputation audits
  • REPUTATION-REPORT*.md — Reputation reports
  • REPUTATION-REPORT*.pdf — Reputation PDF reports
  • REPUTATION-REVIEWS*.md — Review analysis
  • REPUTATION-SENTIMENT*.md — Sentiment analysis
  • REPUTATION-COMPETITORS*.md — Competitor benchmarking
  • REPUTATION-CRISIS*.md — Crisis playbooks
  • REPUTATION-RECOVERY*.md — Recovery strategies
  • REPUTATION-TRENDS*.md — Trend analysis

GEO/SEO Tool outputs:

  • GEO-AUDIT-*.md — Full GEO audit reports
  • GEO-REPORT*.md — GEO reports
  • GEO-REPORT*.pdf — GEO PDF reports
  • GEO-CITABILITY*.md — Citability scores
  • GEO-SCHEMA*.md — Schema analysis
  • GEO-CRAWLERS*.md — Crawler access reports
  • GEO-PLATFORM*.md — Platform optimization reports
  • GEO-BRAND*.md — Brand mention reports
  • GEO-LLMSTXT*.md — llms.txt analysis

Legal Assistant outputs:

  • LEGAL-COMPLIANCE-*.md — Compliance gap analysis
  • LEGAL-REPORT*.md — Legal reports
  • LEGAL-REPORT*.pdf — Legal PDF reports
  • LEGAL-REVIEW*.md — Contract reviews
  • LEGAL-PRIVACY*.md — Privacy policy analysis
  • LEGAL-TERMS*.md — Terms of service analysis
Search Strategy

Use this multi-step approach:

  1. Glob for filename matches — Search for files where the client name appears in the filename:

    Glob: AGENCY-*{variant}*.md
    Glob: MARKETING-*{variant}*.md
    Glob: REPUTATION-*{variant}*.md
    Glob: GEO-*{variant}*.md
    Glob: LEGAL-*{variant}*.md
    Glob: SALES-*{variant}*.md
    Glob: PROSPECT-*{variant}*.md
  2. Grep for content matches — Search inside all output files for the client name:

    Grep: Search for client name variants in all .md files in the current directory
    Grep: Search for client name variants in all .json files (data files)
  3. Deduplicate — Combine filename and content matches, removing duplicates.

  4. Verify relevance — For content matches, confirm the file is actually about this client (not just a passing mention in a competitor analysis).

Step 3 — Extract Data from Each File

For each confirmed client file, read the file and extract:

From Agency Onboard Reports (AGENCY-ONBOARD-*.md):
  • Agency Score (composite 0-100)
  • Agency Grade (A+ through F)
  • Individual scores: Marketing, Reputation, GEO, Legal, Sales
  • Top critical findings (up to 3 per team)
  • Recommended service tier and pricing
  • Date of analysis (from file metadata or report content)
From Marketing Audits (MARKETING-AUDIT*.md):
  • Marketing Score (0-100)
  • Key findings: copy quality, SEO, conversion, content strategy
  • Recommended services
  • Date of analysis
From Reputation Audits (REPUTATION-AUDIT-*.md):
  • Reputation Score (0-100)
  • Google rating and review count
  • Sentiment breakdown (positive/negative/neutral percentages)
  • Response rate to negative reviews
  • Key reputation risks
  • Date of analysis
From GEO Audits (GEO-AUDIT-*.md):
  • GEO Score (0-100)
  • Citability score
  • AI crawler access status
  • Schema markup status
  • Platform readiness scores
  • Date of analysis
  • Legal Score (0-100)
  • Compliance gaps identified
  • Privacy policy status
  • Terms of service status
  • ADA/accessibility status
  • Date of analysis
From Sales Analysis (PROSPECT-ANALYSIS*.md, SALES-RESEARCH*.md):
  • Sales/Opportunity Score (0-100)
  • Company size and industry
  • Decision makers identified
  • Estimated budget capacity
  • Recommended approach
  • Date of analysis
Show full SKILL.md (457 more words)Show less
From Proposals (AGENCY-PROPOSAL-.md, SALES-PROPOSAL.md):
  • Proposed service tier
  • Proposed monthly pricing
  • Services included
  • Date of proposal

Step 4 — Determine Pipeline Stage

Based on which files exist, classify the client's pipeline stage:

StageCriteriaIcon
New LeadOnly quick audit or single-tool scan exists:small_blue_diamond:
AuditedFull agency onboard or 2+ individual audits completed:large_blue_diamond:
ProposedProposal file exists (AGENCY-PROPOSAL or SALES-PROPOSAL):yellow_circle:
Active ClientMultiple reports across different dates, or follow-up files exist:green_circle:
Needs Follow-UpAudit exists but no proposal, or audit is 30+ days old:red_circle:

Step 5 — Calculate Revenue Opportunity

Estimate total revenue opportunity based on available data:

  1. From proposals — Use the proposed monthly pricing if available
  2. From audit recommendations — Sum recommended service pricing across all audits
  3. Annual projection — Monthly estimate x 12
  4. Lifetime value estimate — Annual x 2.5 (average agency client retention)

If no pricing data is available, estimate based on the number and severity of issues found:

  • 15+ critical findings across audits = Tier 3 candidate ($3,500-$7,500/month)
  • 8-14 critical findings = Tier 2 candidate ($1,500-$3,500/month)
  • 1-7 critical findings = Tier 1 candidate ($500-$1,500/month)

Step 6 — Display the Client Summary

Output a comprehensive terminal summary in this exact format:

================================================================
  CLIENT HISTORY: [Company Name]
================================================================

  Pipeline Stage:  [Stage Icon] [Stage Name]
  First Contact:   [Date of earliest file]
  Last Activity:   [Date of most recent file]
  Total Files:     [Count] files across [Count] tool suites

================================================================
  SCORE SUMMARY
================================================================

  Agency Score:     [Score]/100  ([Grade])
  ------------------------------------------------
  Marketing:        [Score]/100  [bar visualization]
  Reputation:       [Score]/100  [bar visualization]
  GEO/SEO:          [Score]/100  [bar visualization]
  Legal:            [Score]/100  [bar visualization]
  Sales:            [Score]/100  [bar visualization]

  (Scores marked with * are from individual audits,
   not the unified agency onboard)

================================================================
  REVENUE OPPORTUNITY
================================================================

  Proposed Tier:      [Tier name if proposal exists]
  Monthly Estimate:   $[amount]/month
  Annual Projection:  $[amount]/year
  Lifetime Value:     $[amount] (est. 2.5yr retention)

================================================================
  ANALYSIS TIMELINE
================================================================

  [Date]  [Icon] [File type] — [Key finding or score]
  [Date]  [Icon] [File type] — [Key finding or score]
  [Date]  [Icon] [File type] — [Key finding or score]
  ...

  Icons: M=Marketing  R=Reputation  G=GEO  L=Legal  S=Sales  A=Agency

================================================================
  KEY FINDINGS (Cross-Team)
================================================================

  CRITICAL ISSUES:
  1. [Finding from Team X] — [Impact]
  2. [Finding from Team Y] — [Impact]
  3. [Finding from Team Z] — [Impact]

  QUICK WINS:
  1. [Win from Team X] — [Effort: Low/Med/High]
  2. [Win from Team Y] — [Effort: Low/Med/High]
  3. [Win from Team Z] — [Effort: Low/Med/High]

================================================================
  FILES ON RECORD
================================================================

  [Full path to each file, grouped by tool suite]

  Agency:
    - AGENCY-ONBOARD-CompanyName.md (Jan 15, 2026)
    - AGENCY-PROPOSAL-CompanyName.md (Jan 18, 2026)

  Marketing:
    - MARKETING-AUDIT-CompanyName.md (Jan 15, 2026)

  Reputation:
    - REPUTATION-AUDIT-CompanyName.md (Jan 15, 2026)

  GEO/SEO:
    - GEO-AUDIT-CompanyName.md (Jan 15, 2026)

  Legal:
    - LEGAL-COMPLIANCE-CompanyName.md (Jan 15, 2026)

  Sales:
    - PROSPECT-ANALYSIS-CompanyName.md (Jan 15, 2026)

================================================================
  RECOMMENDED NEXT STEPS
================================================================

  Based on the client's current pipeline stage and data:

  1. [Specific next action]
  2. [Specific next action]
  3. [Specific next action]

  Run: /agency propose [name]   — Generate/update proposal
  Run: /agency onboard [url]    — Run fresh full audit
  Run: /agency report-pdf       — Generate PDF report
================================================================

Generate specific next-step recommendations based on the client's situation:

If stage is "New Lead":

  • Recommend running the full agency onboard
  • Suggest which individual audits would be most valuable based on industry

If stage is "Audited" (no proposal yet):

  • Recommend generating a proposal immediately
  • Highlight the strongest selling points from the audit
  • Note time since audit (urgency if >14 days)

If stage is "Proposed" (no follow-up):

  • Recommend a follow-up outreach sequence
  • Suggest running a fresh quick audit to show changes
  • Note time since proposal (urgency if >7 days)

If stage is "Active Client":

  • Recommend running updated audits to show progress
  • Suggest expanding services based on untouched areas
  • Flag any areas that have declined since last audit

If stage is "Needs Follow-Up":

  • Flag as urgent
  • Recommend immediate outreach with specific talking points
  • Suggest a quick-win implementation to re-engage

Edge Cases

  • No files found: Display a clear message: "No records found for '[name]'. Try a different spelling or run /agency onboard <url> to create the first record."
  • Multiple businesses match: List all matches and ask the user to clarify which client they mean.
  • Partial data: Display whatever is available. Mark missing scores as "Not yet audited" rather than leaving blank.
  • Very old data (90+ days): Flag as "Stale data — recommend fresh audit" in the timeline.

Output Format

All output is terminal-only. Do NOT create any files. This is a read-only lookup command.

Keep the output clean, scannable, and actionable. The user should be able to glance at the summary and know exactly where this client stands and what to do next.

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

Files

Just SKILL.md in skills/agency-client of zubair-trabzada/ai-agency-claude.

Open the folder on GitHubat commit 172a6c2

Compare with similar skills

Agency Client 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.

Agency Client compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agency Client this skillzubair-trabzada/ai-agency-claude151—~3.2kAutomated safety check: PassMIT
Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore19540 repos~3.2kAutomated safety check: PassMIT
Audit Onboarding Proposalhoangnb24/repository-harness1.2k—~4kAutomated safety check: PassMIT
No Negative EchoLB623/no-negative-echo900—~965Automated safety check: PassMIT
GEO Service Proposal Generatorzubair-trabzada/geo-seo-claude11k—~3kAutomated safety check: NotesMIT
Architectural ProposalsFritzAndFriends/SharpSite1452 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    195 GitHub starsUsed in 40 repos~3.2k tokens
    Sales & SupportAuto-check passed
  • Audit Onboarding Proposal

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $audit-onboarding-proposal.

    1.2k GitHub stars~4k tokensUpdated 7 days ago
    Sales & SupportAuto-check passed
  • No Negative Echo

    LB623/no-negative-echo

    Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs.

    900 GitHub stars~965 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • GEO Service Proposal Generator

    zubair-trabzada/geo-seo-claude

    Builds a client-ready AI-search-optimization proposal from an existing GEO audit, with pricing tiers, an ROI estimate and a markdown document ready to send.

    11k GitHub stars~3k tokensUpdated yesterday
    Sales & SupportAuto-check: notes
  • Architectural Proposals

    FritzAndFriends/SharpSite

    How to write comprehensive architectural proposals that drive alignment before code is written

    145 GitHub starsUsed in 2 repos~1.6k tokens
    Sales & SupportAuto-check passed
  • Counter Proposal Generator

    zubair-trabzada/ai-legal-claude

    Generates specific counter-proposals for every unfavorable clause, with replacement language, negotiation talking points, and a ready-to-send email template

    1.8k GitHub stars~2.4k tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed

More from zubair-trabzada/ai-agency-claude

  • Agency Pipeline

    zubair-trabzada/ai-agency-claude

    Prospect Pipeline Manager — scans all audit files to build a scored, staged pipeline view with revenue projections

    151 GitHub stars~3.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Agency Propose

    zubair-trabzada/ai-agency-claude

    Unified Agency Proposal Generator — builds a three-tier service proposal with ROI projections from all available audit data

    151 GitHub stars~4.5k tokensUpdated 6 mo ago
    Auto-check passed
  • Agency Quick

    zubair-trabzada/ai-agency-claude

    60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard

    151 GitHub stars~4.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Agency Report PDF

    zubair-trabzada/ai-agency-claude

    Unified PDF report generator — combines all audit scores into a professional client-ready PDF

    151 GitHub stars~4.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Agency Status

    zubair-trabzada/ai-agency-claude

    Agency dashboard — shows agency-wide status, pipeline metrics, installed tools, and recent activity

    151 GitHub stars~2.9k tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Agency Client

What does Agency Client do?

Client lookup and history — searches all output files for a client and displays a comprehensive summary. Agency Client is an agent skill from zubair-trabzada/ai-agency-claude.

When should I use Agency Client?

Agency Client fits situations like: tasks that involve Proposals and quotes.

How do I install Agency Client in Claude Code?

Run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-client -a claude-code`. Or copy the skill folder (skills/agency-client in zubair-trabzada/ai-agency-claude) into .claude/skills/agency-client in your project. Claude Code loads it when a task matches its description.

How do I install Agency Client in Codex?

Run `npx skills add zubair-trabzada/ai-agency-claude --skill agency-client -a codex`. Or copy the skill folder (skills/agency-client in zubair-trabzada/ai-agency-claude) into .agents/skills/agency-client in your project. Codex loads it when a task matches its description.

Can I use Agency Client 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 zubair-trabzada/ai-agency-claude --skill agency-client -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agency-client, .gemini/skills/agency-client, .github/skills/agency-client and .opencode/skills/agency-client in your project.

What does Agency Client need to run?

SKILL.md names no scripts, command-line tools or credentials: Agency Client is instructions for the agent only.

Does Agency Client 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 Agency Client 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 Agency Client use?

Agency Client is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agency Client use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agency Client?

Skills that share tags, products or a category with Agency Client: Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Audit Onboarding Proposal (hoangnb24/repository-harness, 1.2k stars), No Negative Echo (LB623/no-negative-echo, 900 stars) and GEO Service Proposal Generator (zubair-trabzada/geo-seo-claude, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agency Client?

zubair-trabzada (a GitHub user) maintains it in zubair-trabzada/ai-agency-claude, which has 151 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on April 8, 2026.

Source: zubair-trabzada/ai-agency-claude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.