Skip to content
FunCoding

Search

Search docs, Skills and MCP

startup-analysis

Analyze a startup from three perspectives — VC investor, job applicant, and CEO/founder — covering market, traction, unit economics, team, defensibility, runway, equity value, culture, and competitive position, with a verdict for each. Use this skill whenever the user wants to evaluate a startup or private tech company: due diligence, whether to invest in it or join it, weighing a startup job offer, company health, outlook, or competitive position, or open-ended asks such as "what do you think of [company]" or "research [company] for me".

科研3.4kplugins/startup-tools/skills/startup-analysis/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/himself65/finance-skills/startup-analysis/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Startup Analysis

Produces a multi-perspective analysis of a startup, examining it through three lenses that each reveal different aspects of company health and potential:

  1. VC Investor Lens — Is this a good investment? Market size, unit economics, growth trajectory, team quality, defensibility
  2. Job Applicant Lens — Should I work here? Equity value, runway risk, culture signals, career growth, compensation fairness
  3. CEO/Founder Lens — How healthy is this company? Product-market fit, burn efficiency, competitive moat, organizational health

Each perspective surfaces insights the others miss. A company can be a great investment but a terrible place to work (or vice versa). The goal is to give the user a 360-degree view so they can make informed decisions.


Step 1: Gather Information

Before analyzing, collect as much public information as possible about the startup. Use web search, the company's website, Crunchbase data, press coverage, and any other available sources.

Key data to gather:

CategoryWhat to find
BasicsFounded year, HQ location, employee count, what the product does
FundingTotal raised, last round (size, date, valuation if known), key investors
ProductWhat they sell, who buys it, pricing model, key competitors
TractionUsers, revenue (if public), growth signals, notable customers
TeamFounders' backgrounds, key hires, LinkedIn headcount trends
MarketIndustry, market size estimates, tailwinds/headwinds
NewsRecent press, product launches, partnerships, layoffs, pivots

If certain data isn't publicly available (e.g., revenue for private companies), note the gap and infer what you can from indirect signals (hiring pace, customer logos, web traffic proxies, job postings).

When information is insufficient

Many startups — especially early-stage or niche ones — have limited public presence. If web search does not return enough information to produce a meaningful analysis (e.g., you can't determine what the company does, who founded it, or how it's funded), ask the user to provide the company's website URL before proceeding. The company website is often the single most information-dense source, and reading it directly (about page, pricing page, team page, blog) can fill most gaps.

You can also ask the user for:

  • The company's website or landing page URL
  • A Crunchbase, LinkedIn, or PitchBook link
  • Any pitch deck, job listing, or press article they have
  • Specific context they already know (e.g., "they just raised a Series A from Sequoia")

It is better to ask for a URL and produce an accurate analysis than to guess and produce a misleading one.


Step 2: Determine Which Perspectives to Cover

By default, produce all three perspectives. If the user specifies a particular angle (e.g., "I'm considering joining them" or "should I invest"), emphasize that perspective but still include the others as context — they often reveal relevant information.

User's situationPrimary perspectiveStill include
Considering investingVC InvestorJob Applicant (talent signal), CEO (operational health)
Considering a job offerJob ApplicantVC Investor (funding runway), CEO (strategic direction)
Running the company / advisoryCEO/FounderVC Investor (how investors see you), Job Applicant (talent attractiveness)
General curiosity / researchAll equally—

Step 3: Analyze from Each Perspective

Read the relevant reference files for the detailed framework for each perspective. These contain the specific criteria, metrics, and red/green flags to evaluate.

VC Investor Analysis

Read references/vc-framework.md for the full evaluation framework.

Core areas to assess:

  • Market opportunity — TAM/SAM/SOM, market timing, secular trends
  • Product & traction — Product-market fit signals, growth metrics, retention
  • Unit economics — CAC, LTV, margins, burn multiple, path to profitability
  • Team — Founder-market fit, technical depth, hiring ability
  • Defensibility — Moats (network effects, switching costs, data, brand, regulatory)
  • Deal terms context — Stage-appropriate valuation, comparable exits

Produce a clear Investment Thesis (bull case) and Key Risks (bear case). End with a verdict: Strong Pass / Lean Pass / Lean Invest / Strong Invest, with reasoning.

Job Applicant Analysis

Read references/job-applicant-framework.md for the full evaluation framework.

Core areas to assess:

  • Financial stability — Runway, burn rate, funding trajectory, revenue health
  • Equity value — Option/equity package analysis, dilution risk, liquidation preferences, realistic exit scenarios
  • Career growth — Role scope, learning opportunity, resume value, mentorship
  • Culture & work-life — Glassdoor signals, employee tenure data, leadership style
  • Product & market risk — Is PMF real? What happens if the startup fails?
  • Red flags — High turnover, constant pivots, vague metrics, founders cashing out

Produce a clear Why Join (pros) and Watch Out For (risks). End with a verdict: Strong Pass / Lean Pass / Lean Join / Strong Join, with reasoning.

CEO/Founder Analysis

Read references/ceo-framework.md for the full evaluation framework.

Core areas to assess:

  • Product-market fit — Retention curves, organic growth, Sean Ellis test proxy
  • Growth efficiency — Burn multiple, CAC payback, magic number
  • Competitive position — Moat strength, competitive dynamics, market share trajectory
  • Organizational health — Hiring pipeline, attrition, team capability gaps
  • Fundraising readiness — Metrics vs. benchmarks for next round, investor narrative
  • Strategic risks — Platform dependency, customer concentration, regulatory exposure

Produce a clear Strengths to Double Down On and Urgent Areas to Address. End with a health grade: Critical / Struggling / Stable / Strong / Exceptional, with reasoning.


Step 4: Synthesize Cross-Perspective Insights

After the three analyses, add a synthesis section that highlights:

  1. Where perspectives agree — If all three lenses flag the same strength or weakness, it's probably real
  2. Where perspectives diverge — A company can be VC-attractive (huge market) but employee-risky (high burn, low runway). Call these out.
  3. The bottom line — One paragraph summary: what kind of company is this, what's its most likely trajectory, and what should the user do based on their stated (or implied) situation

Step 5: Present the Report

Write it as a scannable report titled [Company Name] — Startup Analysis:

  • Summary — a short overview that states the three verdicts up front.
  • One section per perspective, in the order that fits the user's situation from Step 2. Each covers the core areas from Step 3 with the evidence behind every judgment, and ends with its verdict on the scale defined there — Investment Verdict (Strong Pass / Lean Pass / Lean Invest / Strong Invest), Employment Verdict (Strong Pass / Lean Pass / Lean Join / Strong Join), or Health Grade (Critical / Struggling / Stable / Strong / Exceptional) — followed by the reasoning.
  • Cross-perspective synthesis — where the lenses agree, where they diverge, and the bottom line.

Scale each section to the evidence: where financials or other areas are opaque, say so in a line and spend the space on what's observable, rather than filling a heading for its own sake. Don't fabricate metrics; make informed inferences and state your confidence level.


Reference Files

  • references/vc-framework.md — VC due diligence checklist with metrics, benchmarks, and red/green flags
  • references/job-applicant-framework.md — Job seeker evaluation framework with equity analysis and culture assessment
  • references/ceo-framework.md — CEO self-assessment framework with operational metrics and strategic analysis

Read these when you need the detailed criteria and benchmarks for each perspective.

Similar Skills

lead-research-assistant
ComposioHQ/awesome-claude-skills77k

lead-research-assistant

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

Science

13c-metabolic-flux
K-Dense-AI/scientific-agent-skills48k

13c-metabolic-flux

Estimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrained multistart fitting, and flux-profile diagnostics. Use for 13C-MFA, carbon tracing, mass isotopomer distributions (MDVs/MIDs), positional isotopomers, parallel tracer experiments, and determining whether labeling data constrain a pathway flux. Distinguishes measured-label inference from COBRA flux balance analysis and flags experiments requiring nonstationary MFA.

Science

datamol
K-Dense-AI/scientific-agent-skills48k

datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Science

biopython
K-Dense-AI/scientific-agent-skills48k

biopython

Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.

Science

bulk-rnaseq
K-Dense-AI/scientific-agent-skills48k

bulk-rnaseq

Prepares bulk RNA-seq FASTQ, Salmon, STAR or featureCounts output for gene-level differential expression. Covers nf-core/rnaseq and standalone quantification, biological replication, strandedness, reference provenance, validated count assembly and a PyDESeq2 handoff. Use for FASTQ-to-counts analysis, nf-core/rnaseq configuration, STAR/Salmon quantification, or building a counts matrix for DESeq2. For single-cell data use scanpy; for statistical fitting alone use pydeseq2.

Science

alphagenome
K-Dense-AI/scientific-agent-skills48k

alphagenome

Looks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), scores variants or scans windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and builds Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.

Science