agentleFS
Overdrive-ConsultingOverdrive-Consulting/vc-fundraising-skill/.claude/skills/clarify-thesis/SKILL.md

clarify-thesis

Skill4 starsChanged 8 months agoMITView on GitHub

Turn a startup description into a structured fundraising brief for VC targeting. Ask only the clarifying questions that materially affect investor targeting. Triggers on: "start fundraising", "find investors", "raise capital", "clarify thesis", "I'm fundraising", "help me raise", "find VCs", "we're raising a round".

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 1 is distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before starting, check that APIFY_TOKEN is set (needed for later steps):

    line 18
  2. Very specific:

    If missing, ask the founder to run export APIFY_TOKEN=<your_token> before proceeding past step 2.

    line 22
  3. Distinctive:

    Only when the answer would materially change the investor targeting

    line 62
  4. Very specific:

    Write a JSON file to data/normalized/company_profile.json conforming to schemas/company_profile.schema.json.

    line 71
  5. Very specific:

    If a recommended field is missing, include it as null and note it in open_questions.

    line 73
  6. Very specific:

    If you infer something not explicitly stated, include it in assumptions_made.

    line 74
  7. Very specific:

    After writing data/normalized/company_profile.json, present the structured brief to the founder for review:

    line 78
  8. Very specific:

    Do not proceed to find-vcs until the founder confirms or corrects the brief.

    line 105

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Clarify Thesis

Pipeline: clarify-thesis → find-vcs → map-investors → enrich-vc-contacts → score-vc-fit → draft-investor-outreach

You are step 1 of 6. Your job is to turn a founder's description into a structured fundraising brief so the pipeline has a clean, complete profile to work from.

Environment

Before starting, check that APIFY_TOKEN is set (needed for later steps):

test -n "$APIFY_TOKEN" && echo "set" || echo "missing"

If missing, ask the founder to run export APIFY_TOKEN=<your_token> before proceeding past step 2.

Tools

None. This step is conversation + reasoning only.

Input

The founder's description of their company — can be a deck summary, website copy, raw notes, or a direct message. If nothing is provided, ask: "Tell me about your company and what you're raising."

Intake conversation

Collect the following fields. Ask only if the answer is not inferable from what the founder has shared.

Required fields (block progress if missing):

FieldGood clarifying question
Company name—
One-line thesis"How would you describe what your company does in one sentence?"
Stage"What stage are you raising at — pre-seed, seed, or Series A?"
Geography"Where is your company based, and which geographies are your target customers?"
Sector / sub-sector"What sector does your company operate in — e.g. B2B SaaS, fintech, climate, devtools, deeptech?"
Business model"How does the company make money?"
Target check size"What check size are you targeting from a lead investor?"
Lead vs. follow"Are you looking for investors that lead rounds, co-lead, or are strong co-investors acceptable?"

Recommended fields (proceed with a warning if missing):

FieldGood clarifying question
Comparable companies"What companies would you compare yourselves to — especially ones that have raised from VCs you admire?"
Must-have investor traits"Are there traits you need in an investor — e.g. deep sector expertise, operator background, specific geography?"
Must-avoid investor traits"Any investor types or firms you want to avoid?"
Traction summary"What does your traction look like — ARR, users, pilots, contracts, notable customers?"
Warm intro preference"Do you have warm intro access to any VC networks, or are you open to cold outreach?"

Good clarifying questions:

  • One at a time
  • Specific, not open-ended
  • Only when the answer would materially change the investor targeting

Bad clarifying questions:

  • Repeating what the founder already said
  • Nice-to-know but not targeting-relevant
  • Vague discovery questions

Output

Write a JSON file to data/normalized/company_profile.json conforming to schemas/company_profile.schema.json.

If a recommended field is missing, include it as null and note it in open_questions. If you infer something not explicitly stated, include it in assumptions_made.

Review checkpoint

After writing data/normalized/company_profile.json, present the structured brief to the founder for review:

Here's your fundraising brief:

  Company: [company_name]
  Thesis: [one_line_thesis]
  Stage: [stage]
  Sector: [sector]
  Geography: [geo]
  Check size: [check_size_target_usd]
  Lead preference: [lead]
  Comparables: [comparable_companies]
  Traction: [traction_summary]

[If any required fields are null]:
  ⚠ Missing required fields: [list]. Please provide these before we continue.

[If any assumptions were made]:
  Assumptions I made: [assumptions_made]

[If any recommended fields are null]:
  Note: [open_questions] — we can proceed without these but targeting may be broader.

Does this look right? Confirm to move to step 2 (finding VC firms), or correct anything above.

Do not proceed to find-vcs until the founder confirms or corrects the brief.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.