Publish Sign in

ATM Issuance Tear Sheet Agent Skill

Generate a single-page ATM (at-the-market) program tear sheet for one public company from Verity (InsiderScore) data, headlined by the…

Install this skill Read the source first Free Written by insiderscore
Context cost
6.9k tokensestimated from the bundle, loaded when it triggers
Bundle
5 files · 60.0 kB2 scripts among them — read before you run
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Generate a single-page ATM (at-the-market) program tear sheet for one public company from Verity (InsiderScore) data, headlined by the capacity reservoir — authorized shelf capacity draining with each disclosed sale and refilling at each new program — with pace, runway in quarters, the refill habit, quarterly cadence with insider selling beneath it, agent fees, and the plan ledger. Client-accessible Verity tools only; every price is a disclosed print — no market feed, no price chart, no scores.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

analytics
Filed under

Analytics & Monitoring

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md11.9 kB · preview
--- name: atm-tearsheet ---
6# ATM Issuance Tear Sheet
7
8Build a dense, single-page HTML tear sheet (plus a one-page PDF) that judges one public company's **at-the-market equity program** the way you'd judge an insider: as a **seller of its own stock**. The audience is sophisticated (PMs, analysts); the register is an accountant's — state measured facts, let the data carry the story, never editorialize.
9
10The organizing idea: an ATM is a **revolving pipe**. The sheet answers, in order: how much more can be printed without asking anyone (live capacity), how fast it drains (pace, runway in quarters), whether "remaining" is a ceiling or a revolving figure (the refill habit and utilization of retired shelves), what it has cost and produced to date (raised, blended VWAP, fees, dilution), and whether insiders' own money behaves like the treasury's. Every price that appears is a *disclosed print* — a tranche's realized price per share, a filing's implied price (remaining_dollars ÷ remaining_shares), or an insider Form 4 transaction price. No market-data feed, no price chart, and deliberately no summary score: the program is described, not graded.
11
12The deterministic work — every metric, the reservoir reconstruction, all SVG and CSS — is owned by scripts/build_atm_tearsheet.py, which consumes the **raw tool CSVs** directly. Your job is to fetch the data, read the computed metrics, write the prose (lead, verdict, panel reads), and run the renderer + PDF exporter. You supply words; you never supply or adjust a number.
13
14**Client-tool discipline:** use only atm_announce, atm_sales, get_insider_transactions, get_company_info, and optionally get_research. Do **not** use get_company_chart_raw or get_company_chart — they are internal-only and unavailable to clients.
15
16## Sheet anatomy (fixed)
17
181. **Header** — ticker, company, sector, mcap, as-of, Verity logo, one-line verdict chip.
192. **Issuance read** — the orange-railed lead paragraph: what kind of issuer this is and the one thing to watch. Written after the metrics are computed, grounded in them.
203. **Capacity — the reservoir** *(the headline)* — authorized capacity remaining across all live programs, reconstructed as a step series that drains with every disclosed sale and refills at each New/Increase; ▲ marks each new shelf. Sidebar: live capacity (the big number), trailing-4q pace and runway in quarters, program count and median refill interval, median utilization of retired plans, and the one-line capacity_read.
214. **Program to date** — a stat strip, no chart: total raised / shares issued / ≈ % of today's count, blended VWAP (lifetime and trailing-12m), trailing-12m dollars raised, and the date of the last reported sale (a plain recency fact — most filers report only in periodic filings, so recent selling may not yet be public).
225. **Cadence & insider cross-check** *(when insider data is passed)* — one full-width chart doing double duty: quarterly company issuance on top, officer/director open-market selling beneath it, independently scaled. No stats, no commentary — the ratio between the two rows is the message, and it speaks for itself.
236. **Program economics & ledger** — current commission, estimated cumulative agent fees, forward-sale dollars, and the plan-by-plan table (authorized, sold under, % used, fee, terminal event: terminated / replaced / exhausted / live).
247. **Footer** — sources, the no-market-feed statement, dedup/exclusion counts, caveats.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,733 words
Files5
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈260
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
6,615
on trigger
The instruction body and 4 supporting files, read only when the skill fires.
3.4%
of a 200k window
Ten skills this size would take about 34% of the window before you open a file.
050k100k150k200k context window

6.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

5 files, 60.0 kB on disk. Mostly text — the instructions the model reads — with 2 scripts in it that your client would run only if the instructions tell it to.

  • SKILL.md11.9 kB
  • assets/example_well_meta.json1.5 kB
  • scripts/build_atm_tearsheet.py30.9 kB
  • scripts/to_pdf.py1.6 kB
  • scripts/verity_logo_b64.txt14.1 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 2 scripts beside the text, so the bundle is 5 files you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# ATM Issuance Tear Sheet · 6.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/atm-issuance-tear-sheet/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/atm-issuance-tear-sheet" ] && { [ ! -e .claude/skills/atm-issuance-tear-sheet ] || { mv .claude/skills/atm-issuance-tear-sheet "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/atm-issuance-tear-sheet" .claude/skills/ && echo "Installed .claude/skills/atm-issuance-tear-sheet"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add insiderscore/atm-issuance-tear-sheet

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/atm-issuance-tear-sheet/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/atm-issuance-tear-sheet/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/atm-issuance-tear-sheet" ] && { [ ! -e ~/.claude/skills/atm-issuance-tear-sheet ] || { mv ~/.claude/skills/atm-issuance-tear-sheet "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/atm-issuance-tear-sheet" ~/.claude/skills/ && echo "Installed ~/.claude/skills/atm-issuance-tear-sheet" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/atm-issuance-tear-sheet/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as atm-tearsheet in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, atm-issuance-tear-sheet.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceinsiderscore/atm-issuance-tear-sheet

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

IN
insiderscore

Publishes on mcprush.

0 servers listed8 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill