Agent skill

Investor Materials

by ericrisco in ericrisco/rsc-harness

A skill your agent uses when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first…

MITAuto-check passedBusiness, Finance & HR

Install Investor Materials

skills CLI
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a claude-code

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

GitHub CLI
$ gh skill install ericrisco/rsc-harness investor-materials --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/ericrisco/rsc-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/investor-materials .claude/skills/investor-materials && 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
investor-materials
GitHub stars
180
Token cost
~3.1k tokens
SKILL.md length
1,285 words
Files
6 (incl. scripts, references)
Skills in repo
233
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first…

  • Works in 3 steps: The data room — the organized, numbered,… → The one-pager / teaser — the single page… → The investor update — the recurring…
  • Circulating the documents an investor reads outside the meeting — setting up
  • SKILL.md covers Decision table — is it yours?, Intake gate (run before…, Data room and One-pager / teaser, plus 4 more sections
  • Runs Shell scripts from its folder

What it does

Investor Materials is an agent skill from ericrisco/rsc-harness. Use when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first meeting, or drafting the recurring monthly investor update. NOT the slide narrative (that is pitch-deck), NOT the projection spreadsheet (that is financial-model), NOT round strategy and the investor pipeline (that is fundraising).

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `evals/README.md`, `evals/cases.yaml` and `references/dataroom-checklist.md`).

It sits in Business, Finance & HR, covering Fundraising and pitch decks. The repository describes itself as: Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the… The licence is MIT.

When your agent uses it

  • Circulating the documents an investor reads outside the meeting — setting up
  • Cleaning a data room
  • Writing the one-pager
  • Teaser that earns the first meeting

Example prompts

  • “/investor-materials”

Requirements

  • A Bash shell

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. The data room — the organized, numbered, access-tracked folder of diligence files an investor opens after the meeting.
  2. The one-pager / teaser — the single page that earns the first meeting and rides along on a cold email.
  3. The investor update — the recurring email that keeps existing backers warm and primed for the follow-on.

What it can do on your machine

Read from SKILL.md and the folder at commit 1f8d9bb. 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

    Ships 1 file in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Investor Materials loads about 3.1k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 1,285 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.6k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from ericrisco/rsc-harness at commit 1f8d9bb, republished under its MIT licence (© ericrisco). 1,285 words, ~3,148 tokens.

Download SKILL.mdSave it as .claude/skills/investor-materials/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
investor-materials
description
Use when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first meeting, or drafting the recurring monthly investor update. NOT the slide narrative (that is `pitch-deck`), NOT the projection spreadsheet (that is `financial-model`), NOT round strategy and the investor pipeline (that is `fundraising`).
tags
fundraising, data-room, investor-update, one-pager, investor-relations, due-diligence
recommends
pitch-deck, financial-model, fundraising, cold-outreach, unit-economics, grants
origin
risco

Investor Materials — Data Room, One-Pager, Investor Update

The packaging layer of fundraising. You consume the deck, the model, and the metrics — then you organize, name, and circulate the documents an investor reads on their own time. You do not build the story, the spreadsheet, or the round strategy.

This skill produces exactly three artifacts:

  1. The data room — the organized, numbered, access-tracked folder of diligence files an investor opens after the meeting.
  2. The one-pager / teaser — the single page that earns the first meeting and rides along on a cold email.
  3. The investor update — the recurring email that keeps existing backers warm and primed for the follow-on.

One-line route-out: the persuasive story in slides is ../pitch-deck/SKILL.md; the numbers in a spreadsheet are ../financial-model/SKILL.md; the round strategy and investor pipeline are ../fundraising/SKILL.md. You package what they produce.

Decision table — is it yours?

The askOwned here?Route to
Set up / clean / rename the data roomYes—
Write the one-pager / teaserYes—
Draft the recurring investor updateYes—
Build the slide deck / narrative arcNopitch-deck
Build projections / burn / runway / cap-table mathNofinancial-model
Investor list, outreach strategy, SAFE vs priced, term sheetNofundraising
Cold first-touch email to a named VCNocold-outreach (you supply the one-pager it attaches)
LTV / CAC / payback / contribution-margin deep diveNounit-economics
Grant / non-dilutive funding narrativeNogrants
How the one-pager LOOKS (layout, brand)Nobrand-identity / presentations

Intake gate (run before producing anything)

Two questions decide everything. Ask them, do not assume.

  1. Stage? pre-seed / seed / Series A — sets data-room size (seed skews 30–40 docs, Series A 55–70) and whether the one-pager leads with team or traction.
  2. What already exists? Is there a deck, a model, current metrics? You consume these. If they are missing and the real ask is to create them, STOP and route — building the deck is pitch-deck, building the model is financial-model. Producing a one-pager with invented traction or a data room that points at a nonexistent model is the failure this gate prevents.

Rule with a why: if the request is really the narrative or the numbers, you are the wrong skill — route, do not fake. A polished package around hollow content wastes the founder's one shot with each investor.

Data room

A complete startup data room is ~50–70 documents across 8 numbered categories. Number the folders so an investor (who spends only ~2–3 hours total, and 8–12 minutes on cap table + SAFEs alone) navigates without asking. 68% of failed deals cite disorganized documentation as a primary factor, and organized rooms close ~35% faster — investors assume you run the company the way you run the deal room. That is the entire reason for the numbering and naming rules below.

The 8 categories (full per-doc checklist with seed vs Series-A inclusion flags → references/dataroom-checklist.md):

text
01_Corporate        incorporation, bylaws, board minutes, shareholder agreements
02_Financial        financial model, historical P&L, balance sheet, bank statements
03_Legal_Contracts  customer/supplier contracts, NDAs, leases, litigation log
04_IP               trademarks, patents, domains, IP-assignment agreements
05_Team_HR          org chart, key employment + founder vesting, option plan
06_Product_Metrics  product overview, roadmap, KPI dashboard, cohort/retention data
07_CapTable_Equity  cap table, SAFEs/convertibles, prior round docs, 409A
08_Tax_Compliance   tax filings, registrations, licenses, compliance certificates

Naming convention — non-negotiable: YYYY-MM_Doc-Name_vN.ext. Date for recency, version so nobody diligences a stale file.

text
Bad   final_model(2)(FINAL).xlsx
Bad   captable_new_updated.xlsx
Good  2026-03_Financial-Model_v4.xlsx
Good  2026-03_Cap-Table_v2.xlsx
Good  07_CapTable_Equity/2026-02_SAFE-AngelRound_v1.pdf
  • Surface the most-scrutinized first. Cap table, SAFEs/convertibles, and the financial model get the most eyes — put them where they cannot be missed and make sure they are the current version. Too many files dilutes focus and signals poor prioritization.
  • Leave half-baked docs OUT. A folder with 70 files where 15 are drafts reads worse than 45 clean ones. Omit until ready; an empty-looking "08_Tax" with a placeholder is worse than a note "tax filings available on request."
  • Share a link per investor and read the analytics. DocSend-style tooling tracks who opened what, time-per-page, and forwards. Use drop-off to fix the materials and warmth signals to prioritize follow-up. You advise the link-per-investor practice and read the analytics — you do not build the VDR software.

One-pager / teaser

The one-pager's job is to GET the meeting; the deck's job is to close it. They are different artifacts — one-pagers get ~2.5x higher response rates than full decks for cold outreach. The one-pager is 7 blocks:

text
1. Headline / one-liner   what you do, for whom, in one sentence
2. Problem                the pain, sized and concrete
3. Solution               your product, one line of how it works
4. Traction               the 3–5 metrics that prove pull (MRR, growth %, logos)
5. Market                 TAM / SAM / SOM with the SOM you can actually win
6. Team                   why THIS team wins this market
7. The ask                specific amount + use of funds
  • Lead order by stage. Pre-revenue leads with team (there is no traction to lead with). Post-traction leads with traction (the metrics are the strongest card). Re-order blocks accordingly; do not bury the strongest one at the bottom.
  • A teaser carries NO confidential financials. A teaser is 1–5 pages with no detailed P&L, no full cap table, no confidential customer data — those live in the deck and the data room behind an access link. Leaking them into the first-touch attachment is a defect.
  • The ask is specific. "Raising $1.5M to extend runway 18 months and hire 4 engineers" — not "raising a round." A vague ask reads as an unprepared founder.
text
Bad  (ask)       "We're raising a round to grow the business."
Good (ask)       "Raising $1.5M seed — 18mo runway: 4 eng hires, 2 GTM, to reach $1M ARR."
Bad  (headline)  "An AI-powered platform revolutionizing the future of work."
Good (headline)  "Payroll for restaurant groups — cut weekly close from 6 hours to 20 min."

Fill-in 7-block template + a filled mini-example → references/update-and-onepager-templates.md.

Show full SKILL.md (531 more words)Show less

Investor update

The monthly update is ~6 fixed sections in ~250 words. Top VCs prefer short and consistent over long and sporadic — the format itself signals operational discipline.

text
1. Headline       one line: the month in a sentence
2. Highlights     3–5 bullets, the wins that matter
3. Metrics table  4–6 KPIs: actual vs target vs prior period
4. Challenges     2–3, each PAIRED with a solution or learning (never a naked problem)
5. Asks           specific, named — "intro to the VP Sales at X", not "let me know"
6. Cash / runway  current cash, monthly burn, months of runway

The metrics table is the spine — same KPIs every month so trend is legible at a glance:

text
| Metric        | This month | Target | Last month |
| ------------- | ---------- | ------ | ---------- |
| MRR           | $42k       | $45k   | $38k       |
| New logos     | 7          | 8      | 5          |
| Net churn     | 1.2%       | <2%    | 1.8%       |
| Cash runway   | 14 mo      | —      | 15 mo      |
  • Fixed cadence, never broken. Monthly for early-stage, quarterly for growth-stage. Pick a day (e.g. the 5th) and hold it — consistency is the signal. Only emailing investors when you need money trains them to brace, not to help.
  • Every challenge is PAIRED with a solution or learning. A naked problem reads as a founder who is stuck; a problem-with-a-plan reads as a founder who is in control.
  • Asks are named, not vague. Vague asks ("let me know if you can help") get ignored; named asks ("intro to the VP Sales at Acme") convert passive backers into active allies.
text
Bad  (ask)         "Let me know if you can help with anything."
Good (ask)         "Need a warm intro to a Head of RevOps at a 200+ Series-B SaaS — who do you know?"
Bad  (challenge)   "Sales cycle is too long."
Good (challenge)   "Sales cycle stretched to 70 days — fix: added a security-review pack to the deck, two deals already re-accelerated."

Fill-in 6-section template + a filled mini-example + the vague-ask banlist → references/update-and-onepager-templates.md.

Anti-patterns / rationalizations → STOP

RationalizationReality / Fix
"I'll dump every file in one folder, they'll find it"Investors spend ~2–3h total; disorganization kills 68% of failed deals. Number the 8 categories, name YYYY-MM_Doc_vN.
"final_v2_FINAL(2) is fine, I know which is current"They don't. A stale un-versioned file gets diligenced as truth. Date + version every file.
"Send the full deck for cold outreach"The deck closes; it doesn't open. Send the one-pager — ~2.5x the response rate — deck stays behind the link.
"Put the P&L and cap table in the teaser so they have everything"A teaser carries no confidential financials. Those live in the data room behind a per-investor link.
"'Let me know if you can help' covers it"Vague asks get ignored. Name the intro, the role, the company.
"I'll email investors when I have news / need money"Sporadic updates train backers to brace. Fixed cadence (monthly/quarterly), never broken.
"List the challenge, they'll appreciate the honesty"A naked problem reads as stuck. Pair every challenge with a solution or learning.
"I'll write the deck / model in here too"Out of scope. Route to pitch-deck / financial-model; package what they produce.
"Pad the room to 70 files so it looks thorough"Drafts dilute focus and signal poor prioritization. Omit until ready; clean beats padded.

Verify + handoffs

After generating dataroom-index.md, one-pager.md, or investor-update.md, run the structural lint:

bash
./scripts/verify.sh path/to/one-pager.md     # or dataroom-index.md / investor-update.md

It asserts the 8 numbered categories (data room), the 7 blocks + a numeric ask (one-pager), and the 6 sections incl. a metrics table + runway line (update); and it flags placeholders (TBD, XX, [amount]), vague asks, and confidential financials leaking into a teaser. Structural lint only — persuasion, metric selection, and framing are judgement the capability eval scores, not the script.

Handoffs:

  • ../pitch-deck/SKILL.md — the slide narrative and story arc you consume.
  • ../financial-model/SKILL.md — the projections, burn/runway, cap-table math you reference.
  • ../fundraising/SKILL.md — the round strategy, investor pipeline, SAFE vs priced.
  • ../cold-outreach/SKILL.md — the first-touch email your one-pager attaches to.
  • ../unit-economics/SKILL.md — the LTV/CAC/payback figures you surface in the update and one-pager.

References

  • references/dataroom-checklist.md — the full 8-category, ~60-document checklist with per-stage (seed vs Series-A) inclusion flags, the file-naming/versioning convention, and the "surface first" vs "omit until ready" lists.
  • references/update-and-onepager-templates.md — fill-in monthly-update template (6 sections + metrics table) and one-pager template (7 blocks), each with a filled mini-example, plus the vague-ask banlist with Bad→Good rewrites.

© ericrisco, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in skills/investor-materials of ericrisco/rsc-harness.

  • SKILL.md
  • evals/README.md
  • evals/cases.yaml
  • references/dataroom-checklist.md
  • references/update-and-onepager-templates.md
  • scripts/verify.sh

Open the folder on GitHubat commit 1f8d9bb

Compare with similar skills

Investor Materials 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.

Investor Materials compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Investor Materials this skillericrisco/rsc-harness180—~3.1kAutomated safety check: PassMIT
Virtuals Protocol AcpVirtual-Protocol/openclaw-acp1681 repos~6.4kAutomated safety check: PassNone
Yc Applypedronauck/skills634—~1.3kAutomated safety check: PassNone
Storyline Buildersruthir28/enterprise-ai-skills1481 repos~1.9kAutomated safety check: PassMIT
Startup Pitchferdinandobons/startup-skill1.2k—~6.4kAutomated safety check: PassMIT
Dd SourcingAbilityai/trinity636—~664Automated safety check: PassApache-2.0

Similar skills

  • Virtuals Protocol Acp

    Virtual-Protocol/openclaw-acp

    Hire specialised agents to handle any task — data analysis, trading, content generation, research, on-chain operations, 3D printing, physical goods, gift delivery, and more.

    168 GitHub starsUsed in 1 repo~6.4k tokens
    Business, Finance & HRAuto-check passed
  • Yc Apply

    pedronauck/skills

    Prepare, review, and package Y Combinator application answers and founder-video notes using the live form and verified founder facts.

    634 GitHub stars~1.3k tokensUpdated 25 days ago
    Business, Finance & HRAuto-check passed
  • Storyline Builder

    sruthir28/enterprise-ai-skills

    McKinsey-style storyline framework for building presentation decks.

    148 GitHub starsUsed in 1 repo~1.9k tokens
    Business, Finance & HRAuto-check passed
  • Startup Pitch

    ferdinandobons/startup-skill

    Build investor-ready pitch scripts in multiple formats (10-min, 5-min, 2-min, 1-min elevator, investor email).

    1.2k GitHub stars~6.4k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Dd Sourcing

    Abilityai/trinity

    Document sources properly for due diligence reports. An agent skill from Abilityai/trinity.

    636 GitHub stars~664 tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Replit Deck

    sanqiufong/slides-from-anything

    Single-file horizontal-swipe HTML deck in the style of Replit Slides's landing-page template gallery.

    132 GitHub starsUsed in 1 repo~2.9k tokens
    Business, Finance & HRAuto-check passed

More from ericrisco/rsc-harness

All 233 skills in this repo
  • Ab Testing

    ericrisco/rsc-harness

    A skill your agent uses when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go…

    180 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Accessibility

    ericrisco/rsc-harness

    A skill your agent uses when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast…

    180 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Ads

    ericrisco/rsc-harness

    A skill your agent uses when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platform-fit creative, budget/scaling rules…

    180 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Agent Eval

    ericrisco/rsc-harness

    A skill your agent uses when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual…

    180 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • AI Media

    ericrisco/rsc-harness

    A skill your agent uses when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-video clips, score — then glue them with…

    180 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Analytics

    ericrisco/rsc-harness

    A skill your agent uses when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PII scrubbing.

    180 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Questions about Investor Materials

What does Investor Materials do?

A skill your agent uses when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first…. Investor Materials is an agent skill from ericrisco/rsc-harness. Use when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first meeting, or drafting the recurring monthly investor update.

When should I use Investor Materials?

Investor Materials fits situations like: circulating the documents an investor reads outside the meeting — setting up; cleaning a data room; writing the one-pager; teaser that earns the first meeting.

How do I install Investor Materials in Claude Code?

Run `npx skills add ericrisco/rsc-harness --skill investor-materials -a claude-code`. Or copy the skill folder (skills/investor-materials in ericrisco/rsc-harness) into .claude/skills/investor-materials in your project. Claude Code loads it when a task matches its description.

How do I install Investor Materials in Codex?

Run `npx skills add ericrisco/rsc-harness --skill investor-materials -a codex`. Or copy the skill folder (skills/investor-materials in ericrisco/rsc-harness) into .agents/skills/investor-materials in your project. Codex loads it when a task matches its description.

Can I use Investor Materials 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 ericrisco/rsc-harness --skill investor-materials -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/investor-materials, .gemini/skills/investor-materials, .github/skills/investor-materials and .opencode/skills/investor-materials in your project.

What does Investor Materials need to run?

Going by SKILL.md and its folder, Investor Materials needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Investor Materials access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Investor Materials 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Investor Materials use?

Investor Materials 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 Investor Materials use?

About 3.1k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Investor Materials?

Skills that share tags, products or a category with Investor Materials: Virtuals Protocol Acp (Virtual-Protocol/openclaw-acp, 168 stars), Yc Apply (pedronauck/skills, 634 stars), Storyline Builder (sruthir28/enterprise-ai-skills, 148 stars) and Startup Pitch (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 Investor Materials?

ericrisco (a GitHub user) maintains it in ericrisco/rsc-harness, which has 180 GitHub stars. The repository holds 233 skills in this directory. The repository was last updated on October 9, 2026.

Source: ericrisco/rsc-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.