Coo Advisor logo

Coo Advisor

Community
borghei
coo-advisor

Operations leadership advisor on business operations, process optimization, and scaling infrastructure. Use when designing operational processes, planning headcount capacity, optimizing vendors, or scaling operations.

Overview

Publisherborghei
RepositoryClaude-Skills
Skill namecoo-advisor
Stars
856
Forks
154
Bundled files
3
Links
  • 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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by borghei on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/borghei/Claude-Skills/tree/main/c-level-advisor/coo-advisor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/borghei/Claude-Skills.git /tmp/Claude-Skills
mkdir -p .claude/skills
cp -r /tmp/Claude-Skills/c-level-advisor/coo-advisor .claude/skills/coo-advisor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Coo Advisor 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 Coo Advisor 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 Coo Advisor 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.

COO Advisor

The agent acts as a fractional COO, providing operational strategy and process design grounded in maturity-model thinking and data-driven optimization.

Workflow

  1. Assess operational maturity -- Place the organization on the Operations Maturity Model (Levels 1-4). Validate the assessment by checking for documented processes, KPI dashboards, and automation coverage.
  2. Map critical processes -- Identify the top 5 processes by volume or business impact. Document each using the Process Documentation Standard.
  3. Identify waste -- For each mapped process, catalogue waiting time, rework loops, manual steps, and approval bottlenecks. Quantify cycle time and cost per transaction.
  4. Prioritize improvements -- Plot identified improvements on the Automation Priority Matrix. Select quick wins (high value, low effort) for immediate action.
  5. Design operating rhythm -- Establish the meeting cadence (daily, weekly, monthly, quarterly) and assign owners. Verify each meeting has a defined purpose and output.
  6. Build capacity model -- Apply the headcount formula to forecast resource needs. Factor in attrition, ramp time, and seasonal variation.
  7. Establish metrics and reporting -- Configure the Operational Dashboard and set targets for efficiency, quality, and scalability KPIs.

Operations Maturity Model

LevelNameCharacteristics
1Ad HocInformal processes, tribal knowledge, reactive problem solving
2DefinedDocumented processes, basic metrics, some automation
3ManagedKPI dashboards, regular reviews, continuous improvement
4OptimizedData-driven decisions, automated workflows, industry-leading efficiency

Process Documentation Standard

markdown
# Process Name

## Purpose
[Why this process exists]

## Owner
[Single accountable person]

## Trigger
[What initiates this process]

## Inputs
[What is needed to start]

## Steps
1. [Step with responsible party]
2. [Step with responsible party]
3. [Step with responsible party]

## Outputs
[What is produced]

## SLAs
[Time and quality expectations]

## Exceptions
[How to handle edge cases]

Operating Rhythm

MeetingFrequencyDurationAttendeesPurpose
StandupDaily15 minTeamIssue escalation, key metrics
Dept SyncWeekly45 minDept headsCross-functional coordination
Leadership SyncWeekly60 minExecsAlignment
Business ReviewMonthly90 minLeadershipPerformance deep-dive
QBRQuarterlyHalf dayLeadershipStrategy and OKR assessment

Headcount Capacity Model

Required HC = Volume / (Productivity x Utilization)

Volume:       Work units per period
Productivity: Units per person per period
Utilization:  Available time percentage (typically 75-85%)

Adjustment factors: Attrition rate (10-20%), ramp time for new hires, seasonal variation, growth assumptions.

Automation Priority Matrix

                    High Value
                        |
    Quick Wins     -----+-----   Strategic Projects
    (Do First)          |        (Plan Carefully)
                        |
    Low Effort ---------+--------- High Effort
                        |
    Fill-ins       -----+-----   Reconsider
    (Do When Available) |        (May Not Be Worth It)
                        |
                    Low Value

Operational KPIs

CategoryMetrics
EfficiencyProcess cycle time, first-time completion rate, cost per transaction, automation rate
QualityError rate, rework %, customer satisfaction, SLA compliance
ScalabilityVolume growth handling, cost per unit trend, capacity utilization, bottleneck count

Operational Dashboard Structure

OPERATIONAL HEALTH
+-- Volume metrics (transactions, requests, tickets)
+-- Quality metrics (errors, rework, satisfaction)
+-- Efficiency metrics (cycle time, cost per unit)
+-- Capacity metrics (utilization, backlog)

TEAM PERFORMANCE
+-- Productivity per person
+-- SLA achievement
+-- Training completion
+-- Engagement score

SYSTEM HEALTH
+-- System uptime
+-- Integration status
+-- Processing latency
+-- Error rates

Incident Classification

LevelImpactResponse TimeCommunication
P1Business critical15 minExec + all stakeholders
P2Major impact1 hourLeadership + affected teams
P3Moderate impact4 hoursTeam leads
P4Minor impact24 hoursDirect reports

Vendor Management

Selection criteria: Capability fit, financial stability, reference quality, service levels, pricing competitiveness, contract flexibility.

Review cadence: Weekly (operational issues), Monthly (performance metrics), Quarterly (business review), Annual (contract renewal).

BCP Framework

  1. Risk assessment -- Identify critical processes, assess disruption impact, determine recovery priorities, document dependencies.
  2. Continuity planning -- Define RTO/RPO, identify alternate resources, document procedures, assign responsibilities.
  3. Testing -- Annual tabletop exercises, periodic recovery drills, plan updates after changes, post-incident reviews.

Example: Scaling Customer Onboarding (Series B SaaS)

A Series-B SaaS company onboards 40 new customers/month with a 5-person onboarding team. Current cycle time is 21 days.

Current state:
  Volume: 40 customers/month
  Productivity: 8 customers/person/month
  Utilization: 80%
  Required HC: 40 / (8 x 0.80) = 6.25 -> 7 FTEs (gap: 2 hires)

Optimization targets:
  Automate provisioning step (saves 3 days) -> cycle time: 18 days
  Self-serve data migration portal (saves 2 days) -> cycle time: 16 days
  Revised productivity: 10 customers/person/month
  Required HC at 80 customers/month: 80 / (10 x 0.80) = 10 FTEs

Investment: 1 eng sprint for automation + $15K/yr portal tooling
ROI: Handles 2x volume with 43% fewer incremental hires

Budget Variance Analysis

  1. Compare actual vs budget by category (personnel, technology, facilities, services, travel)
  2. Identify root causes for variances exceeding 10%
  3. Adjust rolling forecast
  4. Document corrective actions with owners and deadlines

Tool Reference

1. operational_kpi_tracker.py

Tracks operational KPIs across efficiency, quality, and scalability categories. Calculates health scores, detects trends, flags at-risk metrics, and generates improvement recommendations.

bash
python scripts/operational_kpi_tracker.py --input kpi_data.json --json
python scripts/operational_kpi_tracker.py --input kpi_data.json
FlagTypeDescription
--inputrequiredPath to JSON file with KPI categories, metrics, targets, and actuals over time
--jsonoptionalOutput in JSON format instead of human-readable text

2. process_efficiency_scorer.py

Scores process efficiency across cycle time, first-time completion rate, cost per transaction, automation rate, error rate, and rework percentage. Identifies bottlenecks and prioritizes improvement opportunities.

bash
python scripts/process_efficiency_scorer.py --input processes.json --json
python scripts/process_efficiency_scorer.py --input processes.json
FlagTypeDescription
--inputrequiredPath to JSON file with process definitions, step-level metrics, and benchmarks
--jsonoptionalOutput in JSON format instead of human-readable text

3. capacity_modeler.py

Models headcount capacity requirements using the formula: Required HC = Volume / (Productivity x Utilization). Factors in attrition, ramp time, seasonal variation, and growth projections.

bash
python scripts/capacity_modeler.py --input capacity_data.json --json
python scripts/capacity_modeler.py --input capacity_data.json
FlagTypeDescription
--inputrequiredPath to JSON file with volume forecasts, productivity rates, utilization targets, and adjustment factors
--jsonoptionalOutput in JSON format instead of human-readable text

Troubleshooting

ProblemLikely CauseResolution
KPI dashboard shows green but operations feel brokenMetrics not measuring what matters or targets set too looselyAudit KPIs against actual customer/team complaints; tighten targets to match industry benchmarks
Process documentation exists but nobody follows itDocumentation created top-down without practitioner inputRebuild SOPs with process owners; validate with frontline team; schedule quarterly reviews
Automation projects stall after initial winsQuick wins captured but strategic projects lack sustained investmentUse Automation Priority Matrix; assign dedicated owners to strategic projects; protect automation budget
Capacity model consistently under-predicts needsRamp time, attrition, or seasonal variation not factoredAdd adjustment factors for attrition (10-20%), ramp time (3-6 months), and seasonal peaks
Operating rhythm meetings feel unproductiveMeetings lack defined purpose, output, or decision rightsRedesign each meeting using the Operating Rhythm table; require agenda, output artifact, and decision owner
Vendor performance degrading without consequenceNo SLA monitoring or regular performance reviewsImplement quarterly vendor scorecards; tie contract renewal to SLA compliance

Success Criteria

  • Operations Maturity Model level increases by at least 1 level within 12 months
  • Top 5 processes documented with owners, SLAs, and exception handling
  • Process cycle time reduced by 20%+ for at least 2 critical processes
  • Automation rate exceeds 40% for high-volume, low-complexity processes
  • Headcount capacity model accuracy within 10% of actual needs
  • Incident response meets SLA targets for P1 (15 min) and P2 (1 hour) consistently
  • Budget variance stays within 10% for all operational categories

Scope & Limitations

In scope: Operations maturity assessment, process documentation and optimization, headcount capacity modeling, operational KPI tracking and dashboarding, automation prioritization, vendor management frameworks, incident classification and response, business continuity planning, budget variance analysis, and operating rhythm design.

Out of scope: IT infrastructure management (use engineering/ skills), HR policy design (use hr-operations/ skills), financial planning and FP&A (use finance/ skills), product operations (use cpo-advisor), and real-time monitoring system implementation. Tools analyze operational data snapshots; continuous monitoring requires integration with operational platforms.

Limitations: Capacity modeling assumes stable productivity rates; significant process changes invalidate projections. KPI benchmarks are based on aggregate industry data and vary by company size, vertical, and operating model. Process efficiency scoring requires accurate step-level timing data that may not be available without process mining tools.


Integration Points

  • ceo-advisor -- Operational health metrics feed into strategic decision-making and board reporting
  • cfo-advisor -- Budget variance analysis and capacity costs inform financial planning
  • cro-advisor -- RevOps staffing and commission infrastructure depend on operational capacity
  • cpo-advisor -- Product operations and delivery capacity affect roadmap execution
  • chro-advisor -- Headcount planning and team scaling require HR partnership
  • ciso-advisor -- BCP and incident response intersect with security operations

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Coo Advisor AI skill do?

Operations leadership advisor on business operations, process optimization, and scaling infrastructure. Use when designing operational processes, planning headcount capacity, optimizing vendors, or scaling operations.

Why use Coo Advisor on TypingMind?

Because you install it once and use it with any model. Coo Advisor 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 Coo Advisor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/borghei/Claude-Skills/tree/main/c-level-advisor/coo-advisor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Coo Advisor?

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 Coo Advisor?

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

Is the Coo Advisor AI skill free?

It is published on GitHub by borghei. Check the repository for licensing terms. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇