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.
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…
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ericrisco/rsc-harness investor-materials --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "investor-materials" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materials into .claude/skills/investor-materials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investor-materials", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materialsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ericrisco/rsc-harness investor-materials --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/investor-materials .agents/skills/investor-materials && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "investor-materials" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materials into .agents/skills/investor-materials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investor-materials", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ericrisco/rsc-harness investor-materials --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/investor-materials .cursor/skills/investor-materials && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "investor-materials" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materials into .cursor/skills/investor-materials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investor-materials", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ericrisco/rsc-harness.git --path skills/investor-materials--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ericrisco/rsc-harness investor-materials --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/investor-materials .gemini/skills/investor-materials && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "investor-materials" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materials into .gemini/skills/investor-materials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investor-materials", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ericrisco/rsc-harness investor-materialsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/investor-materials .github/skills/investor-materials && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "investor-materials" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materials into .github/skills/investor-materials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investor-materials", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ericrisco/rsc-harness --skill investor-materials -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ericrisco/rsc-harness investor-materials --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/investor-materials .opencode/skills/investor-materials && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "investor-materials" agent skill from https://github.com/ericrisco/rsc-harness/tree/main/skills/investor-materials into .opencode/skills/investor-materials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investor-materials", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
investor-materialsA 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. 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.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 1f8d9bb. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
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.
The full file from ericrisco/rsc-harness at commit 1f8d9bb, republished under its MIT licence (© ericrisco). 1,285 words, ~3,148 tokens.
.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.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:
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.
| The ask | Owned here? | Route to |
|---|---|---|
| Set up / clean / rename the data room | Yes | — |
| Write the one-pager / teaser | Yes | — |
| Draft the recurring investor update | Yes | — |
| Build the slide deck / narrative arc | No | pitch-deck |
| Build projections / burn / runway / cap-table math | No | financial-model |
| Investor list, outreach strategy, SAFE vs priced, term sheet | No | fundraising |
| Cold first-touch email to a named VC | No | cold-outreach (you supply the one-pager it attaches) |
| LTV / CAC / payback / contribution-margin deep dive | No | unit-economics |
| Grant / non-dilutive funding narrative | No | grants |
| How the one-pager LOOKS (layout, brand) | No | brand-identity / presentations |
Two questions decide everything. Ask them, do not assume.
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.
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):
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 certificatesNaming convention — non-negotiable: YYYY-MM_Doc-Name_vN.ext. Date for recency, version so nobody diligences a stale file.
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.pdfThe 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:
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 fundsBad (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.
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.
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 runwayThe metrics table is the spine — same KPIs every month so trend is legible at a glance:
| 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 |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.
| Rationalization | Reality / 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. |
After generating dataroom-index.md, one-pager.md, or investor-update.md, run the structural lint:
./scripts/verify.sh path/to/one-pager.md # or dataroom-index.md / investor-update.mdIt 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/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
SKILL.md and 5 other files (scripts, references) in skills/investor-materials of ericrisco/rsc-harness.
Open the folder on GitHubat commit 1f8d9bb
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Investor Materials this skillericrisco/rsc-harness | 180 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Virtuals Protocol AcpVirtual-Protocol/openclaw-acp | 168 | 1 repos | ~6.4k | Automated safety check: Pass | None | |
| Yc Applypedronauck/skills | 634 | — | ~1.3k | Automated safety check: Pass | None | |
| Storyline Buildersruthir28/enterprise-ai-skills | 148 | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Startup Pitchferdinandobons/startup-skill | 1.2k | — | ~6.4k | Automated safety check: Pass | MIT | |
| Dd SourcingAbilityai/trinity | 636 | — | ~664 | Automated safety check: Pass | Apache-2.0 |
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.
pedronauck/skills
Prepare, review, and package Y Combinator application answers and founder-video notes using the live form and verified founder facts.
sruthir28/enterprise-ai-skills
McKinsey-style storyline framework for building presentation decks.
ferdinandobons/startup-skill
Build investor-ready pitch scripts in multiple formats (10-min, 5-min, 2-min, 1-min elevator, investor email).
Abilityai/trinity
Document sources properly for due diligence reports. An agent skill from Abilityai/trinity.
sanqiufong/slides-from-anything
Single-file horizontal-swipe HTML deck in the style of Replit Slides's landing-page template gallery.
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…
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…
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…
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…
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…
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.
Categories
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.
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.
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.
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.
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.
Going by SKILL.md and its folder, Investor Materials needs a shell for the scripts in its folder. Our summary lists: A Bash shell.
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.
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.
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.
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.
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.
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.