Consulting Analysis logo

Consulting Analysis

Community
HezaoHezao
consulting-analysis

Consulting-grade research reports: framework + final report.

Overview

PublisherHezaoHezao
Repositorypoirot
Skill nameconsulting-analysis
Stars
252
Forks
26
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Consulting Analysis 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/HezaoHezao/poirot/tree/master/poirot/backend/agents/skill/builtin_skills/research/consulting-analysis
  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/HezaoHezao/poirot.git /tmp/poirot
mkdir -p .claude/skills
cp -r /tmp/poirot/poirot/backend/agents/skill/builtin_skills/research/consulting-analysis .claude/skills/consulting-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Consulting Analysis 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 Consulting Analysis 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 Consulting Analysis 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.

Consulting Analysis

Overview

Produces professional, consulting-grade research reports in Markdown, covering market analysis, consumer insights, brand strategy, financial analysis, industry research, competitive intelligence, and investment due diligence.

Operates in two phases:

  1. Phase 1 — Analysis Framework: chapter skeleton, data requirements, visualization plan
  2. Phase 2 — Report Generation: synthesize collected data into final report

Output adheres to McKinsey/BCG consulting voice standards.

Data Authenticity Protocol

All data in the report MUST derive from provided Data Summary or External Search Findings. No hallucinations. If data is missing, state "Data not available" rather than fabricating numbers. Every major claim must be traceable to input data.

When to Use

  • User asks for market analysis, consumer insight report, financial analysis, industry research, or any consulting-grade analytical report
  • User provides a research subject and needs a structured framework
  • User provides data summaries to synthesize into a report

Phase 1: Analysis Framework Generation

Step 1.1: Identify Domain & Dimensions

DomainTypical Dimensions
Market AnalysisMarket size, growth, segmentation, drivers, competition
Brand AnalysisPositioning, share, perception, strategy
Consumer InsightsDemographics, behavior, decision journey, pain points
Financial AnalysisMacro, industry, fundamentals, metrics, valuation
Industry ResearchValue chain, market size, competition, policy, tech
Investment DDBusiness model, financials, management, opportunity, risk
Competitive IntelCompetitor ID, comparison, SWOT, positioning

Step 1.2: Select Frameworks

Select 2-4 complementary frameworks per domain:

CategoryFrameworks
StrategicSWOT, PESTEL, Porter's Five Forces, VRIO
Market & GrowthSTP, BCG Matrix, Ansoff, TAM-SAM-SOM, PLC
ConsumerDecision Journey, AARRR, RFM, JTBD
FinancialDuPont, DCF, Comparable Company, EVA
CompetitiveBenchmarking, Value Chain, Blue Ocean, Perceptual Mapping
IndustryGartner Hype Cycle, GE-McKinsey Matrix

Selection principles: domain-first, complementary not overlapping, depth over breadth, data-feasible, explicitly mapped to chapters.

Step 1.3: Chapter Skeleton

Each chapter must include:

  1. Chapter Title — professional, concise, subject-based
  2. Analysis Objective — what this chapter reveals
  3. Analysis Logic — framework or reasoning chain
  4. Core Hypothesis — to validate or refute

Step 1.4: Data Requirements Per Chapter

FieldDescription
Data MetricSpecific metric needed
Data TypeQuantitative / Qualitative / Mixed
Suggested SourcesIndustry reports, gov stats, social media, etc.
Search KeywordsQueries for data collection
PriorityP0 (Required) / P1 (Important) / P2 (Supplementary)
Time RangePeriod data should cover

Step 1.5: Visualization Plan Per Chapter

FieldDescription
Chart TypeLine, bar, pie, scatter, radar, heatmap, table
Chart TitleDescriptive title
Data MappingWhich metrics map to axes/segments
Argument Structure"What → Why → So What" narrative outline

Step 1.6: Output Framework

markdown
# [Research Subject] Analysis Framework

## Research Overview
- **Research Subject**: [...]
- **Scope**: [Geography, time range, segment]
- **Analysis Domain**: [Market / Finance / Industry / ...]
- **Core Research Questions**: [1-3 key questions]

## Framework Selection
| Chapter | Selected Framework(s) | Application |
|---------|----------------------|-------------|

## Chapter Skeleton
### 1. [Chapter Title]
- **Analysis Objective**: [...]
- **Analysis Logic**: [...]
- **Core Hypothesis**: [...]
#### Data Requirements
| # | Metric | Type | Sources | Keywords | Priority | Time |
#### Visualization & Content Plan
[Chart plan + table design + argument structure]

## Data Collection Task List
[Consolidated P0/P1 tasks for downstream data collection]

Phase 2: Report Generation

After data collection (by deep-research or other skills), synthesize into final report.

Step 2.1: Validate Inputs

Confirm Analysis Framework + Data Summary present. Flag missing P0 data.

Step 2.2: Write Report

For each sub-chapter, follow "Visual Anchor → Data Contrast → Integrated Analysis":

  1. Visual Evidence: comparison tables (charts if available)
  2. Data Contrast: Markdown table of key metrics
  3. Integrated Narrative: "What → Why → So What" (min 200 words)

Each insight must connect Data → User Psychology → Strategy Implication:

❌ Bad: "Females are 60%. Strategy: Target females."
✅ Good: "Females constitute 60% with high TGI. This suggests purchase is
   driven by aesthetic validation. Consequently, media spend should pivot
   to visual-heavy platforms."

Step 2.3: Report Structure

markdown
# [Report Title]

## Abstract
[Executive summary with key takeaways]

## 1. Introduction
[Background, objectives, methodology]

## 2. [Body Chapter]
### 2.1 [Sub-chapter]
| Metric | Brand A | Brand B |
[Integrated narrative: What → Why → So What, min 200 words]

## N+1. Conclusion
[Pure objective synthesis, NO bullet points, neutral tone]

## N+2. References
[Formatted references]

Formatting Standards

  • Tone: McKinsey/BCG — authoritative, objective, professional
  • Number formatting: English commas (1,000 not 1,000)
  • Titling: standard numbering (1., 1.1), no "Chapter/Part/Section" prefixes
  • Forbidden words: "Decoding", "DNA", "Secrets", "Unlocking"
  • No horizontal rules (---)
  • Conclusion: flowing prose, NO bullet points

Quality Checklist

Phase 1

  • Framework covers all natural dimensions for the domain
  • 2-4 complementary frameworks selected and mapped to chapters
  • Each chapter has Objective, Logic, Hypothesis
  • Data requirements specific with search keywords
  • Every chapter has a visualization plan
  • P0/P1/P2 priorities assigned

Phase 2

  • NO HALLUCINATION: all numbers traceable to Data Summary
  • All sections in order (Abstract → Intro → Body → Conclusion → References)
  • Every sub-chapter follows "Visual Anchor → Data Contrast → Analysis"
  • Every sub-chapter ends with min 200-word analytical paragraph
  • Insights follow "Data → Psychology → Strategy" chain
  • Conclusion is flowing prose, no bullets
  • Missing P0 data explicitly flagged

Output

  • Phase 1: Analysis Framework in Markdown
  • Phase 2: Final Report in Markdown, saved to .poirot/outputs/

Frequently asked questions

What does the Consulting Analysis AI skill do?

Consulting-grade research reports: framework + final report.

Why use Consulting Analysis on TypingMind?

Because you install it once and use it with any model. Consulting Analysis 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 Consulting Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HezaoHezao/poirot/tree/master/poirot/backend/agents/skill/builtin_skills/research/consulting-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Consulting Analysis?

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 Consulting Analysis?

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

Is the Consulting Analysis AI skill free?

Yes. It is published on GitHub by HezaoHezao 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 👇