Agent skill

Icp Research

by growthack88 in growthack88/growth-marketing-os

Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation.

MITAuto-check passedMarketing & SEO

Install Icp Research

skills CLI
$ npx skills add growthack88/growth-marketing-os --skill icp-research -a claude-code

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

GitHub CLI
$ gh skill install growthack88/growth-marketing-os icp-research --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/growthack88/growth-marketing-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/community/icp-research .claude/skills/icp-research && 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
icp-research
GitHub stars
116
Token cost
~4.4k tokens
SKILL.md length
1,934 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation.

  • Works in 3 steps: Data extraction → Analysis and synthesis → Structured output
  • Tasks that involve Market research
  • SKILL.md covers Report structure, Output dimensions, Sorting rules and Rich description requirements, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Icp Research is an agent skill from growthack88/growth-marketing-os. Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.

Its SKILL.md is about 4.4k 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 Marketing & SEO, covering Market research, Market sizing and Web scraping. The repository describes itself as: Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR). The licence is MIT.

When your agent uses it

  • Tasks that involve Market research
  • Tasks that involve Market sizing
  • Tasks that involve Web scraping

Example prompts

  • “Use the icp-research skill to scrape case studies, testimonials, and solutions pages from a target website to build structured ICP documentation”
  • “/icp-research”

Workflow steps

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

  1. Data extraction
  2. Analysis and synthesis
  3. Structured output

What it can do on your machine

Read from SKILL.md and the folder at commit c6b55c7. 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

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Icp Research loads about 4.4k tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 1,934 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~4.4k

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 growthack88/growth-marketing-os at commit c6b55c7, republished under its MIT licence (© growthack88). 1,934 words, ~4,385 tokens.

Download SKILL.mdSave it as .claude/skills/icp-research/SKILL.md (or your agent's skills folder).
name
icp-research
description
Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.
version
4.2
author
genesys-growth
last_updated
2026-03-15
<!--
COMMUNITY SKILL — included under its original MIT license.
Source: https://github.com/matteotitta/genesys-skills by Matteo Titta (MIT).
License text: ../LICENSE-genesys-skills.txt
Curated into Growth Marketing OS by Mahmoud Omar (mahmoudomar.com) — this file
is NOT original work by the repo author; see /skills/community/README.md.
-->

ICP research skill

Generate ideal customer profiles for B2B SaaS clients through systematic research and structured output.

Report structure

The final ICP report follows this numbered section order:

SectionPurpose
HeaderResearch date, website, category, confidence score (1-5)
1. Executive summaryHigh-level synthesis of findings and strategic recommendations
2. TAM analysisMarket sizing with targeting strategy per layer (TAM/SAM/SOM/ICP)
3. Firmographics analysisGeographic, industry, company segment patterns, and technographics
4. Roles and personasCore use case, Champion deep-dive, Economic Buyer deep-dive, buying journey
5. Negative ICPWho is NOT a fit, disqualification criteria, and red flags
6. Customer proof pointsNamed customers, outcomes, and evidence with URLs
7. Voice of customer synthesisLanguage patterns, pain points, and outcome terminology
8. ICP segment definitionsScoring matrix, in-market signals, segment deep-dives
9. Intent signals and buying triggersObservable signals indicating purchase readiness
10. RecommendationsPrioritization and messaging by segment
11. Data gapsMissing information and follow-up suggestions
12. Source appendixAll sources with access dates, URLs, and confidence levels

Confidence score calculation: Count High/Medium/Low data points. Score 5 if >70% High, Score 4 if >50% High, Score 3 if mixed, Score 2 if >50% Low, Score 1 if >70% Low.


Output dimensions

Research produces structured outputs across multiple dimensions. See references/dimension-schemas.md for complete field definitions.

TAM analysis

Market opportunity sizing with explicit methodology, assumptions, and targeting strategy.

FieldDescription
TAM summaryRich paragraph explaining total addressable market with methodology
TAM calculation tableMetric, value, source/basis, and targeting strategy for each layer
ICP rowBelow SOM: highest priority segment based on research findings
AssumptionsDocumented assumptions underlying each estimate

TAM table structure:

MetricValueSource/BasisTargeting strategy
TAM$XB[Methodology]Long-term market awareness and category leadership
SAM$XM[Qualification]Segment-specific campaigns and channel strategy
SOM$XM[Capture estimate]Direct sales and targeted ABM
ICP$XM[Research findings]Highest-priority accounts for immediate focus
Firmographics

Company attributes that define ideal customers with segment deep-dives.

FieldDescription
Geography summaryParagraph with regional patterns and evidence
Geography tableRegions sorted by concentration, with URL + date evidence
Industry summaryParagraph explaining vertical patterns
Industry tableIndustries sorted by presence, with URL + date evidence
Company segments summaryParagraph describing size/stage patterns
Segments tableEnterprise → Mid-market → SMB → Startup
Segment deep-divesFor each segment: Priorities, ICP-fit, Budget & sales cycle, Unique approach, Proof points
TechnographicsRequired tools, integrations, and tech stack indicators
Adjacent stackCommon tools and integrations

Company segment deep-dive structure:

For each segment (Enterprise, Mid-market, SMB), include:

  • Priorities: Key priorities within today's market trends and dynamics
  • ICP-fit: Why this segment is a good fit for our product
  • Budget & sales cycle: Spending power and typical cycle length
  • Unique approach: How we target this segment uniquely
  • Proof points: Stats of impact from representatives with URLs and dates
Technographics

Required technology prerequisites and common stack patterns. This section identifies tools that indicate fit or readiness.

CategoryPurpose
CRMCustomer relationship management (Salesforce, HubSpot, Pipedrive)
E-commerceCommerce platforms (Shopify, BigCommerce, WooCommerce)
Marketing automationEmail and automation (Klaviyo, Mailchimp, Braze, Marketo)
CDPCustomer data platforms (Segment, mParticle, Rudderstack)
AnalyticsProduct and web analytics (Amplitude, Mixpanel, Google Analytics, Posthog)
CloudInfrastructure providers (AWS, Azure, GCP, Vercel)
Data warehouseData storage (Snowflake, BigQuery, Redshift, Databricks)
ERPEnterprise resource planning (SAP, NetSuite, Oracle)
CommunicationTeam communication (Slack, Microsoft Teams)
Project managementWork management (Jira, Asana, Monday, Linear)

Technographics table structure:

CategoryRequired/PreferredCommon toolsWhy it mattersEvidence
[Category]Required[Tool names][Product dependency or integration][Source] ([URL], [Date])
[Category]Preferred[Tool names][Better fit or faster time-to-value][Source] ([URL], [Date])
Personas

Who buys and uses the product, with explicit Champion and Economic Buyer deep-dives.

FieldDescription
Persona overviewRich paragraph summarizing buying committee structure
Personas tableSorted: Champion → Economic Buyer → User → Influencer
Core use caseBusiness process definition with steps, scenarios, alternatives, drivers, outcomes
Champion deep-diveExplicit template for the person who drives evaluation
Economic Buyer deep-diveExplicit template for the person who controls budget
User deep-dive(s)Additional personas who use the product daily
Use cases by roleChampion first, then by seniority
Alternatives mentionedCompetitors and substitutes with URLs
Buying journeyChampion → Economic Buyer → User columns

Core use case structure:

  • Use case statement: 1-2 sentences defining the business process
  • Key steps: Numbered steps in the process
  • Core scenarios: 3-4 typical scenarios
  • Current alternatives: Competitors, Manual, DIY approaches
  • Business drivers: What drives the need
  • Desired outcomes: What success looks like

Champion deep-dive structure (12 fields):

The Champion is the person who feels the pain daily, drives the evaluation, and advocates internally for the solution.

  1. Titles: Title variations with context (e.g., "Manager of X, Senior Y, Lead Z")
  2. Department & team size: Where they sit and typical team structure
  3. Responsibilities: Key responsibilities in paragraph form (2-3 sentences)
  4. Jobs to be done: 3-5 product-agnostic jobs they're trying to accomplish
  5. Success metrics / KPIs: How they're measured and what success looks like
  6. Challenges: Things that make their job harder (obstacles they struggle with)
  7. Pain points: Problems that hurt them directly (negative impact they feel)
  8. Current alternatives: How they currently achieve goals without this product
  9. Problems with alternatives: Specific issues with current approach
  10. Buying behavior: How they typically discover and evaluate solutions
  11. Channels & influences: Communities, content, events, and influencers they trust
  12. Testimonial: Verbatim quote from case study with name, title, company, and description of product usage

Economic Buyer deep-dive structure (13 fields):

The Economic Buyer is the person who controls budget and makes the final purchasing decision.

  1. Titles: Title variations with context (e.g., "VP of X, Director of Y, Head of Z")
  2. Department & team size: Where they sit, reporting structure, direct reports
  3. Responsibilities: Key responsibilities in paragraph form (2-3 sentences)
  4. Jobs to be done: 3-5 business-level jobs they're trying to accomplish
  5. Success metrics / KPIs: Business metrics they're accountable for
  6. Challenges: Business-level obstacles they face
  7. Pain points: Business impacts that create urgency
  8. What they actually care about: Beyond stated concerns — what drives decisions
  9. Common objections: Typical pushback during sales process
  10. What a "no-brainer" looks like: Conditions that make approval easy
  11. Buying behavior: How they evaluate and approve purchases
  12. Channels & influences: Where they get information and who they trust
  13. Testimonial: Verbatim quote from case study with name, title, company
Negative ICP

Identifying who is NOT a fit helps sales disqualify quickly and avoid bad-fit deals.

FieldDescription
Disqualification criteriaTable of attributes that indicate poor fit
Red flagsWarning signs from churned or unsuccessful customers
Objection patternsObjections that signal poor fit vs. legitimate concerns
Intent signals and buying triggers

Observable events or behaviors indicating a company or persona is more likely to buy now.

FieldDescription
OverviewParagraph explaining signal detection strategy
Company-level signalsEvents at the organization level
Persona-level signalsBehaviors from individual buyers
Signal sourcesWhere to detect each signal

Sorting rules

Apply consistent sorting across all tables:

DimensionSort order
Decision roleChampion → Economic Buyer → User → Influencer
Company sizeEnterprise → Mid-market → SMB → Startup
FrequencyVery high → High → Medium → Low
ConfidenceHigh → Medium → Low
Customer concentrationHigh → Medium → Low
Priority1 → 2 → 3 → 4
Industry presenceStrong → Moderate → Emerging

Show full SKILL.md (785 more words)Show less

Rich description requirements

Every section must include contextual paragraphs, not just tables. All evidence must include URL and access date.

Minimum requirements
SectionRequired prose
Each macro section (1-12)Opening paragraph (3-5 sentences) summarizing findings
Each industry vertical2-3 sentences explaining why this industry fits and evidence
Each company segmentDeep-dive with Priorities, ICP-fit, Budget & sales cycle, Unique approach, Proof points
Champion personaFull deep-dive with all 12 fields including Channels & influences
Economic Buyer personaFull deep-dive with all 13 fields including Channels & influences
Core use caseFull definition with steps, scenarios, alternatives, drivers, outcomes
Each ICP segmentDeep-dive with Priorities, ICP-fit, Budget & sales cycle, Unique approach, Proof points
Negative ICPDisqualification criteria, red flags, and objection patterns
Intent signalsCompany-level and persona-level signals with detection sources
Data gapsParagraph explaining impact of missing data and mitigation
Paragraph quality checklist
  • Opens with the key insight, not setup
  • Includes specific evidence (names, numbers, sources)
  • Includes URL and date for all evidence
  • Explains the "so what" — why this matters
  • Avoids generic language that could apply to any company

Workflow

Phase 1: Data extraction
  1. Discover key pages

    Fetch: [domain]/customers OR /case-studies OR /success-stories
    Fetch: [domain]/solutions OR /use-cases OR /industries
    Fetch: [domain]/pricing
    Fetch: [domain]/integrations OR /partners
    Search: site:[domain] case study testimonial
    Search: site:g2.com "[company]" reviews
    Search: site:linkedin.com "[company]" hiring [relevant role]
  2. Extract raw data per source (record URL and date for each):

    • Customer names and logos
    • Job titles and roles mentioned
    • Industry and company size indicators
    • Quantified outcomes and stats
    • Verbatim quotes and pain point language
    • Use case descriptions and workflows
    • Tech stack and integrations
    • Community and content references
  3. Normalize attributes

    AttributeNormalization rules
    GeographyMap to: US, North America, EMEA, APAC, LATAM, Global
    IndustryUse standard verticals: SaaS, E-commerce, Finance, Healthcare, etc.
    Company sizeRevenue bands: <$1M, $1-10M, $10-50M, $50-100M, $100M+
    Team sizeEmployee bands: 1-10, 11-50, 51-200, 201-500, 501-1000, 1000+
    Tech stackCategory + tool name: CRM (Salesforce), CDP (Segment)
Phase 2: Analysis and synthesis

For each segment (by industry x company size):

  1. Identify patterns across extracted data
  2. Define core use case with steps, scenarios, alternatives, drivers, outcomes
  3. Build Champion deep-dive with all 12 fields including Channels & influences
  4. Build Economic Buyer deep-dive with all 13 fields including Channels & influences
  5. Map use cases to segment-specific needs
  6. Identify negative ICP criteria and red flags
  7. Identify intent signals at company and persona level
  8. Collect proof points with testimonials for personas and segments
  9. Document technographics with required and preferred tools
  10. Calculate TAM estimate with targeting strategy per layer
  11. Identify ICP as highest-priority segment below SOM
Phase 3: Structured output

Generate numbered sections following the report structure above.

Apply sorting rules to all tables (Champion first for personas).

Include rich descriptions with URLs and dates for all evidence.

Include deep-dives for company segments, personas (Champion and Economic Buyer explicitly), and ICP segments.


Input requirements

Required
  • Website URL: Primary company website
Optional (improves quality)
InputPurpose
Case studies URLDirect link to case studies page
Testimonials URLDirect link to testimonials
Market contextCategory, competitors, GTM approach
Sales call notesWin/loss context, objections
Existing ICP docsValidate or expand current understanding

Anti-hallucination guardrails

  1. Never invent customer names. Only cite publicly referenced customers.
  2. Quote verbatim. Use exact customer language in quotes.
  3. Mark confidence levels. Tag data as High/Medium/Low confidence.
  4. Cite sources with URLs and dates. Include URL and access date for every claim.
  5. Acknowledge gaps. Explicit "Not available" for missing data.
ConfidenceDefinition
HighDirect from official source, verifiable
MediumThird-party source, multiple signals
LowSingle indirect source, inferred

Reference files

FilePurpose
references/dimension-schemas.mdComplete field definitions for all dimensions
references/icp-output-template.mdFull report template with numbered sections
references/search-patterns.mdDetailed search queries per data type
references/examples/example-strapi.mdWorked example: Strapi (headless CMS)

Quality checklist

  • All 12 numbered sections present
  • Every section has opening synthesis paragraph
  • All tables sorted per sorting rules (Champion first for personas)
  • TAM table includes ICP row with targeting strategy
  • Technographics section included with Required/Preferred tools
  • Core use case defined with steps, scenarios, alternatives, drivers, outcomes
  • Champion deep-dive includes all 12 fields with Channels & influences
  • Economic Buyer deep-dive includes all 13 fields with Channels & influences
  • Persona deep-dives include testimonials with quotes
  • Company segment deep-dives include Priorities, ICP-fit, Budget & sales cycle, Unique approach, Proof points
  • Negative ICP documented with disqualification criteria and red flags
  • Intent signals documented with company-level and persona-level signals
  • ICP segment deep-dives include Priorities, ICP-fit, Budget & sales cycle, Unique approach, Proof points
  • Customer names sourced from public references only
  • Firmographics normalized to standard attributes
  • VOC quotes are verbatim with source URLs and dates
  • All evidence includes URL and access date
  • Confidence levels assigned to all key data
  • Data gaps documented with follow-up suggestions

© growthack88, 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/community/icp-research of growthack88/growth-marketing-os.

Open the folder on GitHubat commit c6b55c7

Compare with similar skills

Icp Research 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.

Icp Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Icp Research this skillgrowthack88/growth-marketing-os116—~4.4kAutomated safety check: PassMIT
Competitor Analysissocial-media-skills/skills134—~1.3kAutomated safety check: PassMIT
Marketing Campaignaffaan-m/ECC277k1 repos~1.3kAutomated safety check: PassMIT
Copynicepkg/ai-workflow285—~3.1kAutomated safety check: PassMIT
Startup Designferdinandobons/startup-skill1.2k—~8.1kAutomated safety check: PassMIT
Yao Positioning Skillyaojingang/yao-open-skills1.3k—~805Automated safety check: PassMIT

Similar skills

  • Competitor Analysis

    social-media-skills/skills

    Competitor analysis for social media — public-data competitive reconnaissance to find the gap a brand can own.

    134 GitHub stars~1.3k tokensUpdated 9 days ago
    Marketing & SEOAuto-check passed
  • Marketing Campaign

    affaan-m/ECC

    End-to-end marketing campaign planning and execution. An agent skill from affaan-m/ECC.

    277k GitHub starsUsed in 1 repo~1.3k tokens
    Marketing & SEOAuto-check passed
  • Copy

    nicepkg/ai-workflow

    Professional copywriter for SaaS and startups. An agent skill from nicepkg/ai-workflow.

    285 GitHub stars~3.1k tokensUpdated 8 mo ago
    Marketing & SEOAuto-check passed
  • Startup Design

    ferdinandobons/startup-skill

    Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~8.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Yao Positioning Skill

    yaojingang/yao-open-skills

    Generate evidence-aware positioning reports for personal IPs, courses, products, services, brands, or companies by combining positioning theory, course-marketing analysis, user intent, competitor…

    1.3k GitHub stars~805 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Product Strategist

    nicepkg/auto-company

    Expert product strategy covering market analysis, competitive positioning, go-to-market planning, and product-led growth.

    195 GitHub starsUsed in 1 repo~2.4k tokens
    Marketing & SEOAuto-check passed

More from growthack88/growth-marketing-os

All 14 skills in this repo
  • Experiment Coach

    growthack88/growth-marketing-os

    Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat.

    116 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Mena Ads

    growthack88/growth-marketing-os

    MENA Ads Command Center — a complete paid-ads operating system for the Arab world (Egypt, KSA, UAE, GCC, Levant, North Africa) and global accounts.

    116 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Arabic Copy Localizer

    growthack88/growth-marketing-os

    Marketing copy localization skill that converts English marketing copy (ads, landing pages, emails, CTAs) into native Egyptian Arabic عامية — or GCC dialect on request — with natural English…

    116 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Benchmark Analyst

    growthack88/growth-marketing-os

    Marketing benchmark triage skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Cod Operations Analyst

    growthack88/growth-marketing-os

    COD (cash-on-delivery) e-commerce operations skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Conversion Copywriter

    growthack88/growth-marketing-os

    Direct-response copywriting skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Icp Research

What does Icp Research do?

Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Icp Research is an agent skill from growthack88/growth-marketing-os. Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation.

When should I use Icp Research?

Icp Research fits situations like: tasks that involve Market research; tasks that involve Market sizing; tasks that involve Web scraping.

How do I install Icp Research in Claude Code?

Run `npx skills add growthack88/growth-marketing-os --skill icp-research -a claude-code`. Or copy the skill folder (skills/community/icp-research in growthack88/growth-marketing-os) into .claude/skills/icp-research in your project. Claude Code loads it when a task matches its description.

How do I install Icp Research in Codex?

Run `npx skills add growthack88/growth-marketing-os --skill icp-research -a codex`. Or copy the skill folder (skills/community/icp-research in growthack88/growth-marketing-os) into .agents/skills/icp-research in your project. Codex loads it when a task matches its description.

Can I use Icp Research 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 growthack88/growth-marketing-os --skill icp-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/icp-research, .gemini/skills/icp-research, .github/skills/icp-research and .opencode/skills/icp-research in your project.

What does Icp Research need to run?

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

Does Icp Research access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Icp Research 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 Icp Research use?

Icp Research 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 Icp Research use?

About 4.4k tokens (SKILL.md is roughly 18k 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 Icp Research?

Skills that share tags, products or a category with Icp Research: Competitor Analysis (social-media-skills/skills, 134 stars), Marketing Campaign (affaan-m/ECC, 277k stars), Copy (nicepkg/ai-workflow, 285 stars) and Startup Design (ferdinandobons/startup-skill, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Icp Research?

growthack88 (a GitHub user) maintains it in growthack88/growth-marketing-os, which has 116 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 2, 2026.

Source: growthack88/growth-marketing-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.