agentleFS
peaknr35peaknr35/shark-Tank-proof/skills/first-dollar/SKILL.md

first-dollar

Skill3 starsChanged 12 days agoMITView on GitHub

Finds the money and opportunities that fit this founder and this business right now: government research funding (SBIR, STTR, NSF America's Seed Fund, Innovate UK, EIC, IRAP), procurement requests for proposals, foundations, company credit and pilot programs, college partners, small business loans and local grants, and pre-sales. Checks eligibility first, records every match in the founder folder with its official link, the first step and the deadline exactly as the official page states it, and never invents an amount or a date. Use when the user says "find funding", "grants for this", "who would fund this", "SBIR", "RFPs", "non-dilutive", "loans", or "where do I get money".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read founder/me.md, founder/idea.md, founder/cfo.md (the cash needed) and founder/evidence/claims.md.

    line 28
  2. Very specific:

    Start from ${CLAUDE_SKILL_DIR}/funding-list.md, keeping only the entries whose eligibility fits.

    line 44
  3. Distinctive:

    Read each candidate's official page.

    line 48
  4. Distinctive:

    Never invent an amount, a deadline, an eligibility rule or a past award.

    line 73
  5. Distinctive:

    No paid grant finders, and warn about anyone who charges to apply.

    line 75
  6. Distinctive:

    Not legal, tax or financial advice.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

first-dollar

Money follows evidence and fit. This skill finds the calls this founder can actually win this month, and is honest about the ones they cannot yet.

What the user typed after /first-dollar: $ARGUMENTS

Read ${CLAUDE_SKILL_DIR}/../receipts/rules.md and ${CLAUDE_SKILL_DIR}/finding-money.md first.

Step 1: what fits

Read founder/me.md, founder/idea.md, founder/cfo.md (the cash needed) and founder/evidence/claims.md. If me.md is missing, run the "About them" and "About the next yes" questions from ${CLAUDE_SKILL_DIR}/../receipts/interview.md, one at a time.

Say the stage honestly, from the ledger: "idea" if nothing is measured, "pilot" if a real customer is running it, "revenue" if someone pays. Many programs filter on this.

Money from selling comes first: in Stage One, a pre-sale or a paid pilot usually funds the next step faster and with fewer strings than a grant or a loan (Ready, Fire, Aim, rule 11 in rules.md). Put the fastest way to sell the first units at the top of the list, then the outside money that fits.

Step 2: search

Start from ${CLAUDE_SKILL_DIR}/funding-list.md, keeping only the entries whose eligibility fits. Then use the six places and the searches in finding-money.md for what the list misses. Search the web if you can; if you cannot, say so and give the founder the searches to run. Read each candidate's official page. Check eligibility first and drop anything that fails it.

Step 3: record each real match

One file per match in founder/opportunities/<name>.md (shape: ${CLAUDE_SKILL_DIR}/opportunity.md): the link, who it is for, what it gives, the deadline and the date you checked, the first step, the fit and why, what they ask for in their headings, which ledger claims already answer each, and the gaps.

Step 4: tell the founder

  1. The hard truth: what the founder can and cannot win today, and why. For example: "Nothing here funds an untested idea without a technical question. The NSF pitch is a fit if you frame the open technical risk."
  2. The short list, best fit first: name, amount and deadline as stated (or "check"), the first step, the fit.
  3. Registrations that take weeks, flagged as the first step.
  4. The gaps across the list, and which one to fill first.
  5. That search always misses some: set alerts on the two or three portals that fit best.

Rules

  • Never invent an amount, a deadline, an eligibility rule or a past award. Unconfirmed means "check".
  • No paid grant finders, and warn about anyone who charges to apply.
  • Applying, registering and submitting are the founder's job. Prepare; do not submit.
  • Not legal, tax or financial advice.

Output

founder/opportunities/*.md. Next: /handshake writes the pitch for the best match; /receipts job 4 lists what it still needs.

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.