Business Ops logo

Business Ops

Community
notque
business-ops

Business operations: strategy, technology, growth, competitive intelligence, support, finance, HR, legal, operations, sales, productivity, product management.

Overview

Publishernotque
Repositoryvexjoy-agent
Skill namebusiness-ops
Stars
443
Forks
50
Bundled files
65
LicenseMIT
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.

  • 65 bundled files

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

  • Open source

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

Installation

Install the Business Ops 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/notque/vexjoy-agent/tree/main/skills/business/business-ops
  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/notque/vexjoy-agent.git /tmp/vexjoy-agent
mkdir -p .claude/skills
cp -r /tmp/vexjoy-agent/skills/business/business-ops .claude/skills/business-ops
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Business Ops 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 Business Ops 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 Business Ops 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.

Business Operations

Thirteen modes covering executive strategy through daily productivity. Classify the request into one mode, load its reference, follow that reference's framework.

Mode Detection

ModeSignalFramework
STRATEGYMarket entry, partnerships, resource allocation, "should we"FRAME -> ANALYZE -> DECIDE
TECHNOLOGYBuild vs buy, vendor, SaaS, tech stackTCO analysis -> Vendor scoring -> Decision
GROWTHAudience, SEO, brand, community, channelSegment -> Channel-score -> Plan
COMPETITIVECompetitor, market landscape, differentiationMap landscape -> Position -> Track
EVALUATIONFeasibility, ROI, go/no-go, effort estimateFeasibility score -> ROI model -> Verdict
SUPPORTTicket triage, response, KB article, escalationTRIAGE/RESPOND/KB/ESCALATE/RESEARCH
FINANCEJournal entry, reconciliation, variance, SOXCLASSIFY -> GATHER -> PRODUCE -> VERIFY
HRRecruiting, performance review, compensation, hiringDEFINE -> PIPELINE/EVALUATE -> DOCUMENT
LEGALContract review, compliance, NDA, DSGVO, GoBDINTAKE -> ANALYZE -> FLAG -> OUTPUT
OPERATIONSRunbook, process docs, risk, vendor, change mgmtSCOPE -> AUTHOR/ASSESS -> VERIFY
SALESCall prep, pipeline, outreach, forecastRESEARCH -> PREPARE/ANALYZE -> OUTPUT
PRODUCTIVITYTask management, daily plan, meeting, standupCAPTURE -> DECOMPOSE -> PRIORITIZE
PRODUCTFeature spec, PRD, roadmap, user research, metricsUNDERSTAND -> GATHER -> GENERATE

If the request spans modes, pick the primary. Note the secondary.


Shared Workflow

  1. Classify the request into exactly one mode from the table.
  2. Load the mode's reference file (see Deep References). Each reference contains full framework, sub-modes, phases, and deeper reference pointers.
  3. Follow the reference's instructions. Do not improvise a framework when one exists.
  4. Every mode's top-level reference also specifies an LLM failure-modes guardrail file. Load it alongside the main reference.

Executive Modes (STRATEGY, TECHNOLOGY, GROWTH, COMPETITIVE, EVALUATION)

Load references/csuite.md for the full C-suite framework. All five modes share the same 3-phase pattern:

Phase 1: FRAME -- Convert the question into a structured decision. Name the actual decision (users present symptoms; the real decision is broader). Identify irreversibility. Set time horizon. List 2-4 options. State what makes it hard.

Phase 2: ANALYZE -- Per option: upside (best realistic + expected), downside (worst realistic + recovery + irreversible losses), requirements, opportunity cost. Separate facts from assumptions. Quantify.

Phase 3: DECIDE -- Score options via weighted criteria. Present verdict with driving factors, risk mitigations, and reversibility assessment. Load mode-specific deep references for scoring matrices.


Support Mode

Load references/customer-support.md. Five sub-modes: TRIAGE (classify ticket, assign priority P1-P4, route), RESPOND (draft calibrated reply with tone matching emotional state), KB (convert resolution into publish-ready article), ESCALATE (build structured brief with impact assessment), RESEARCH (investigate history with confidence scoring).

Key guardrail: never fabricate ticket history, resolution steps, or customer quotes.


Finance Mode

Load references/finance.md. Six sub-modes: JOURNAL ENTRY, RECONCILIATION, VARIANCE, STATEMENTS, AUDIT/SOX, CLOSE. All output is working material for qualified professionals -- not financial advice.

Key guardrails: never fabricate account codes, balances, or transaction details. Source all numbers from user-provided data. Always state GAAP/IFRS basis.


HR Mode

Load references/hr.md. Nine sub-modes: RECRUITING, PERFORMANCE, COMPENSATION, OFFER, INTERVIEW, ONBOARDING, ORG-PLANNING, PEOPLE-ANALYTICS, POLICY.

Key guardrails: source compensation data from user-provided or public databases. Focus on skills, behaviors, outcomes -- not demographics. Include legal review disclaimer on binding language. Ask for jurisdiction before compliance advice. Minimize PII retention.


Legal Mode

Load references/legal.md. Six sub-modes: CONTRACT (clause-by-clause GREEN/YELLOW/RED analysis), COMPLIANCE (regulation checklist with German compliance for DSGVO/GoBD/TDDDG), NDA (triage classification), RISK (severity x likelihood matrix), WRITING (structured legal documents), VENDOR (agreement inventory and gap analysis).

Key guardrail: analysis support only, not legal advice. All binding language needs qualified counsel review. Load references/legal/german-business-compliance.md for German-specific regulation.


Operations Mode

Load references/operations.md. Nine sub-modes: RUNBOOK, RISK, VENDOR, PROCESS, CHANGE, CAPACITY, COMPLIANCE, STATUS, OPTIMIZE.

Key patterns: RUNBOOK uses SCOPE -> AUTHOR -> VERIFY with prerequisite checklists. RISK produces severity x likelihood matrices. CHANGE follows RFC -> REVIEW -> IMPLEMENT -> VERIFY. All operations docs require rollback procedures.


Sales Mode

Load references/sales.md. Seven sub-modes: CALL-PREP, PIPELINE, OUTREACH, COMPETITIVE, FORECAST, CALL-SUMMARY, RESEARCH.

Key patterns: CALL-PREP researches prospect then builds agenda with questions. PIPELINE applies health scoring and flags stale deals. OUTREACH personalizes from research (never generic templates). FORECAST uses weighted probability with scenario analysis.


Productivity Mode

Load references/productivity.md. Six sub-modes: TASK (decompose and prioritize), PLAN (daily/weekly time blocks), MEETING (optimize or eliminate), STATUS (structured updates), REVIEW (weekly retrospective), GOAL (OKRs).

Key patterns: vertical slicing for task decomposition (shippable slices, not horizontal layers). 1/2/4-hour time buckets. Tasks over 4 hours need decomposition.


Product Mode

Load references/product-management.md. Eight sub-modes: SPEC (PRD with acceptance criteria), ROADMAP (Now/Next/Later prioritization), STAKEHOLDER (structured updates), RESEARCH (synthesis with thematic analysis), COMPETITIVE (battle cards), METRICS (funnel/cohort/retention analysis), SPRINT (backlog grooming with capacity), BRAINSTORM (Socratic exploration).


Error Handling

ErrorResponse
Too many options (5+)Eliminate obviously inferior first. Get to 2-4.
Not enough informationIdentify 2-3 critical unknowns. Recommend research sprint.
Analysis paralysisReversibility test. If reversible, recommend best option with checkpoint.
Emotional attachmentName the pattern. Ask: stress-test, or genuinely evaluate?

Deep References

All references contain >100 lines of domain-specific frameworks, templates, and guardrails. Load on demand per mode.

ModePrimarySub-references
STRATEGYreferences/csuite.mdreferences/strategic-frameworks.md, references/decision-matrices.md
TECHNOLOGYreferences/csuite.mdreferences/tco-framework.md, references/vendor-evaluation.md
GROWTHreferences/csuite.mdreferences/audience-segmentation.md, references/channel-evaluation.md
COMPETITIVEreferences/csuite.mdreferences/competitive-mapping.md, references/market-positioning.md
EVALUATIONreferences/csuite.mdreferences/feasibility-scoring.md, references/roi-frameworks.md
SUPPORTreferences/customer-support.mdreferences/customer-support/*.md
FINANCEreferences/finance.mdreferences/finance/*.md
HRreferences/hr.mdreferences/hr/*.md
LEGALreferences/legal.mdreferences/legal/*.md
OPERATIONSreferences/operations.mdreferences/operations/*.md
SALESreferences/sales.mdreferences/sales/*.md
PRODUCTIVITYreferences/productivity.mdreferences/productivity/*.md
PRODUCTreferences/product-management.mdreferences/product-management/*.md
Cross-cuttingreferences/content-funnel.md, references/trend-analysis.md, references/risk-assessment.md, references/estimation-techniques.md, references/migration-planning.mdShared frameworks

Bundled files

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

and 5 more files.

Frequently asked questions

What does the Business Ops AI skill do?

Business operations: strategy, technology, growth, competitive intelligence, support, finance, HR, legal, operations, sales, productivity, product management.

Why use Business Ops on TypingMind?

Because you install it once and use it with any model. Business Ops 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 Business Ops in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/notque/vexjoy-agent/tree/main/skills/business/business-ops. 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 Business Ops?

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 Business Ops?

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

Is the Business Ops AI skill free?

Yes. It is published on GitHub by notque 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

Set up your own AI workspace now

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