seed-terms

Jakeschincariol/seed-skillOther

seed-terms is a skill in Jakeschincariol/seed-skill, last changed 1 Nov 2026. It can run shell commands and bundle scripts.

From the author
Term Sheet Reader. Reads a SAFE or a term sheet in plain English, does the dilution math and flags the clauses to ask a lawyer about. Works out what a post-money SAFE owns at its cap and what it converts into at a priced round (cap price vs discount price, whichever is lower), builds a priced round's cap table with the option-pool shuffle (price per share, new shares, the pool top-up, the effective pre-money, everyone's dilution), and scans a pasted term sheet for the traps: liquidation preference over 1x, participating preferred, full ratchet, redemption, cumulative dividends, board control, operating vetoes, pay-to-play, drag-along, long no-shops, exploding deadlines, founder vesting resets, super pro rata and MFN, each with a severity and a question for the lawyer. Not legal advice. Writes seed/terms/ with --write. Use when the user says "read this term sheet", "is this a good deal", "what does this SAFE mean", "how much do I own after", "how much dilution", "what's the option pool shuffle", "what is a post-money cap", "any red flags in this", or when an investor sends terms after a /seed-closer call.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit fde8895 · 20 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

QAI Index

51/QI

We rate every listed skill the same way, from 0 to 100.

A guide to compare by, not a verdict on the skill.

How it's scored

How the QAI Index is scored

Adoption · up to 40
GitHub stars on the repo that holds the skill, shared among its skills, and copies of the skill in other repos.
Quality · up to 30
Our pattern check, the format check, a named licence and a description of a sentence or more.
Upkeep · up to 20
How recently the skill's folder changed.
Trust · up to 10
An official collection, or an organisation that has confirmed its domain with GitHub.

Get an email when its check changes.

Keep it with the other skills you use, installed with one command.

Install

Sign in to see how to install it

Free with Google or an email link, no password needed. Then pick your agent and copy its steps.

MIT
Licence
193
Repo stars
Publisher
Files

What it can touch

Sign in to see the file and line behind each one

The summary at the top stays open to everyone. Signing in is free, with Google or an email link.

Pattern check

Pattern check: nothing flagged · commit fde8895 · 20 Nov 2026

We checked every text file in this skill, at commit fde8895 on 20 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specFails

    The format our Agent Skills docs set out, held to the strictest version of each rule among the agents we check.

    • Error

      The description is 1,121 characters; the limit is 1,024. D2

      Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.

    • Warning

      Fields outside the spec: argument-hint (read by Claude Code and VS Code). Uploads to the Claude apps and API, and strict validators, reject the file; most agents ignore these fields. O1

      Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses
  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      The description is 1,121 characters; the limit is 1,024. Anthropic's validator rejects it. D2

      Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.

    • Error

      Upload and packaging fail on fields outside the spec: argument-hint. O1

      Fix: Delete them, and keep your own data under metadata as text values.

  • OpenAI (Codex & API)Fails

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Error

      The description is 1,121 characters; the limit is 1,024. Codex has no limit, but OpenAI's upload follows the spec. D2

      Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.

    • Warning

      Fields outside the spec: argument-hint. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

      Fix: Delete them, or move your own data under metadata as text values.

  • VS Code & CopilotPasses with warnings

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Warning

      The description is 1,121 characters; the limit is 1,024. VS Code cuts it at 1,024 characters. D2

      Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.

SKILL.md

Files

Changelog

Newest first: each commit that changed its folder on GitHub, and each change to its listing here.

  1. Listed on QAI
  2. Updated: The Seed skill: 11 Claude skills, v1.0 (fde8895 (opens in a new tab))

QAI Index badge

Show this skill's QAI Index in a README or on a website. It links back to this page and changes when we refresh the catalog.

Preview of the QAI Index badge
[![QAI Index](https://qai.io/badge/skills/jakeschincariol/seed-skill/seed-terms.svg)](https://qai.io/skills/jakeschincariol/seed-skill/seed-terms)

More from Jakeschincariol/seed-skill

SkillQAI IndexWhat it can touchPattern checkLicenceUpdated
seed-closerThe Closer. Sends personalised outreach emails to investors, manages the conversations and keeps following up until an investor call is booked, and nothing leaves the user's inbox without their yes. Drafts one RFC 5322 .eml per investor from seed/investors.json and a template (a real personal line, the sender's real name and an opt-out line, generic lines refused), shows the batch, records the user's yes word for word, enforces a daily cap of 20, then Claude sends through the user's own Gmail connector where the Allow once card is a second check. Schedules follow-ups on +3 and +7 business days (3 touches at most, never after a reply), sorts replies into interested / question / not now / no / out of office, stops a thread for good on a no, an opt-out or a bounce, writes a valid .ics invite and shows the funnel. Reads seed/config.json and seed/investors.json, writes seed/pipeline.json, seed/outreach/ and seed/calls/. Use when the user says "email the investors", "send the outreach", "follow up with everyone who hasn't replied", "who do I follow up with today", "sort my replies", "book the call", "send her an invite", "how is the raise going", or after /seed-investors ranks the list.
51/QI
  • Runs shell commands
  • +2 more

Pattern check: Nothing flaggedMITUpdated 1 Nov 2026

51/QI
  • Runs shell commands
  • Names web addresses
  • +1 more
Pattern check: Nothing flaggedMIT1 Nov 2026
seed-coachPitch Coach. Rehearses the investor call with you: drills the hard questions investors ask (market, competition, traction, unit economics, team, why now, risks, the ask), tailored to your own numbers from the competitor scout, the financial model, the market size and the investor you are meeting ("Rover has 515,771 ratings. Why will owners switch?"), grades your written answers (a number, specifics, no hedging, under a minute spoken, answer first) and writes a 20-minute plan for a booked first call. Reads seed/competitors.json, model.json, market.json, investors.json, pipeline.json and calls/. Use when the user says "prep me for the call", "practice my pitch", "what will investors ask", "drill me", "grade my answer", "mock investor", "call agenda", or after /seed-closer books a call.
56/QI
  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 1 Nov 2026

56/QI
  • Runs shell commands
  • Bundles scripts
Pattern check: Nothing flaggedMIT1 Nov 2026
seed-dataroomData Room Builder. Assembles the data room investors ask for and tells you what is missing. Lays out the nine standard folders (01 Company, 02 Pitch deck, 03 Financials, 04 Market, 05 Product, 06 Team, 07 Legal, 08 Cap table, 09 Customers), checks the files against a 25-item checklist (present, missing, or stale by the date in the file name or its last change), writes seed/dataroom/INDEX.md describing every file, and lists what to share before a term sheet and what only after one. Flags what must never be in a data room: passwords, keys, ID documents, raw customer lists. It never uploads or shares anything. Use when the user says "build my data room", "what goes in a data room", "what am I missing for diligence", "the investor asked for the data room", "what can I share now", "make an index of my documents", or after a /seed-closer call goes well or /seed-terms reads a term sheet.
56/QI
  • Touches credentials
  • +2 more

Pattern check: Nothing flaggedMITUpdated 1 Nov 2026

56/QI
  • Touches credentials
  • Runs shell commands
  • +1 more
Pattern check: Nothing flaggedMIT1 Nov 2026
seed-deckPitch Deck Designer. Turns the business plan into a 10-slide pitch deck in the order investors expect: title, problem, solution, market, competition, business model, go-to-market, team, financials, the ask. Writes ONE self-contained 16:9 HTML file (inline CSS, no fonts or scripts from the web, arrow-key navigation, a print stylesheet that saves to PDF one slide a page) in your brand colours, with real charts drawn from your numbers. Lints it: 35 words or fewer a slide, one idea a slide, a use of funds that adds up to the raise, and every number on a slide traced to your plan, model, market or competitor files. Reads seed/plan.json, writes seed/deck.html. Use when the user says "make my pitch deck", "turn the plan into a deck", "build the slides", "check my deck", "how many words a slide", or after /seed-plan.
56/QI
  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 1 Nov 2026

56/QI
  • Runs shell commands
  • Bundles scripts
Pattern check: Nothing flaggedMIT1 Nov 2026
seed-investorsInvestor Finder. Researches the best investors for your idea from public sources only (the firm's own site, public profiles found through web search, SEC EDGAR Form D filings, the press) and ranks them by fit, 0 to 100, with the reasons and a source link on every row: stage, sectors, check size against your ask, geography, how recent their last relevant deal is, and a warm intro. Reads SEC Form D filings to see who in your space raised, how much and when. Writes seed/investors.json for the Closer and the Pitch Coach. Use when the user says "find investors", "who should I pitch", "which VCs invest in pet tech", "build my investor list", "rank these investors", "who funded companies like mine", "Form D", or after /seed-plan, before /seed-closer.
56/QI
  • Runs shell commands
  • +3 more

Pattern check: Nothing flaggedMITUpdated 1 Nov 2026

56/QI
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedMIT1 Nov 2026
seed-marketMarket Sizer. Sizes your market the way investors check it: TAM top-down (population x share x spend a year), SAM bottom-up (customers you can reach x purchases a year x price) and SOM (the share of SAM you can win in N years, with a stated reason). Every input carries a source (a URL, a named publication, or an assumption said out loud), vague sources are refused, and it refuses any result that breaks SOM <= SAM <= TAM. Records sourced facts the deck quotes. Writes seed/market.json for the plan, the deck and the pitch coach. Use when the user says "how big is my market", "TAM SAM SOM", "size the market", "market size slide", "is this market big enough", or after /seed-scout, before /seed-model and /seed-plan.
56/QI
  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 1 Nov 2026

56/QI
  • Runs shell commands
  • Bundles scripts
Pattern check: Nothing flaggedMIT1 Nov 2026
All skills in Jakeschincariol/seed-skill

Other Other skills

Same category, most repo stars first.

SkillQAI IndexWhat it can touchPattern checkLicenceUpdated
78/QI
  • Runs shell commands
  • Reaches the network
  • +1 more
Pattern check: Nothing flaggedMIT20 Oct 2026
dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

obra/superpowers

73/QI
  • Instructions only

Pattern check: Nothing flaggedMITUpdated 23 Jul 2026

73/QI
  • Instructions only
Pattern check: Nothing flaggedMIT23 Jul 2026
71/QI
  • Names web addresses
Pattern check: Nothing flaggedApache 2.01 Oct 2026
76/QI
  • Instructions only
Pattern check: Nothing flaggedMIT27 Sept 2026
77/QI
  • Instructions only
Pattern check: Nothing flaggedMIT14 Oct 2026
77/QI
  • Instructions only
Pattern check: Nothing flaggedMIT14 Oct 2026

Repo facts from GitHub on 20 Nov 2026. Files read at commit fde8895.

QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check