Agent skills for Claude Code and Cursor
Feed it the export you already pull. Every figure in the report reconciles to the file's own totals, and anything it cannot prove is caught and named before it ships, never passed off as fact. These skills teach your agent the craft.
Built for the operator who owns the numbers: the rev-ops, FP&A, or ops analyst, or the founder wearing that hat, shipping reports people act on with no data team behind them.
Why it matters
The real return on AI at work is not a chatbot in the corner. It is you, shipping the dashboard leadership stops second-guessing, and the intranet the whole team works inside, work that used to need an engineering team and a quarter. Kymira gives your agent the judgment to build it with you, and to build it right.
A secure, certified BI intranet, built by you and an agent, this week instead of next quarter. Things you would not have attempted alone.
Every number reconciles to its source, and anything that does not is caught before it ships, so your work holds up the moment someone checks it.
The skills carry the lessons a hard production build already paid for. You skip the expensive detours, and the Monday deck ships on Monday.
Who this is for
You ship reports that executives act on, built from vendor exports, spreadsheets, and email, with no data team behind you.
You already run Claude Code or Cursor, and you want the numbers it builds to be numbers you can stake your name on.
You have shipped, or nearly shipped, a wrong number, and checking now eats more of your week than building.
You already run the agent; the skill is the judgment you drop into it. A folder of plain markdown your agent reads before it works, turning a clever first draft into a senior BI engineer that refuses to guess.
~/.claude/skills/ kymira-anchor-discovery/ SKILL.md references/ kymira-report-design/ SKILL.md kymira-verification-practice/ SKILL.md ... seventeen more
Copy the folder into ~/.claude/skills/. No build step, no runtime,
plain markdown you can read and edit.
Ask for the report you need, in plain language. "Did the promotion work." "What we shipped versus what actually sold." It builds against your real exports.
Every figure traces to its source cell. Anything the file cannot prove is named on the page, not shipped as fact.
A model on its own
A clever first draft, confident everywhere.
A model with the skills
A senior reviewer who shows the work.
The prompt you would write yourself
Always reconcile to the file's own totals. Never guess.
That sentence is roughly the first line of the doctrine. The skills are the several hundred rules for what happens after it fails, each one paid for by a real wrong number. Four it still ships:
You can write the sentence. The skills are what survives after it fails. Read the full doctrine
Twelve teach the craft of a report you can trust. Seven make it a platform. Two make it yours: one place behind a wall for your whole team, and the co-pilot that stands the whole intranet up.
✓ marks the tiers each skill ships in
✓ Everything · the superpower
Every report you build lands in one place on Cloudflare, behind a default-deny auth wall with per-audience zones. Refresh a dashboard by dropping in a new export. A live team layer sits on top: a shared task board with a kanban and threaded comments, a notification hub that tracks which partner has been told what, and flags and rulings that update for everyone at once, so the whole team works inside numbers that reconcile.
Ships with the four-layer architecture, the security-hardening gate, the CSP hashes and the backup drill you rehearse before anyone external logs in. The master intranet template is included.
And the intranet co-pilot walks you the rest of the way: from your first export to a live URL, the Cloudflare account and scoped-token setup, the provisioning, and the wall, sequenced and hand-delivered. Two skills, one superpower.
See stage 3 of the quick start →When the number in the meeting is yours, you carry the miss. These skills take that weight off you: hardened building a real reporting system, pushed until it stopped shipping a single number it could not prove. Every rule in them exists because a real report once got a number wrong, and now it cannot.
The skills did not come from a blog post or a prompt pack. They were distilled from a real reporting system that was tested, broken on purpose, and rebuilt until it stopped producing wrong numbers. Every rule you get is one that a real failure paid for.
That makes them cautious the way a careful analyst is cautious. A figure either reconciles to the totals in the file it came from, or it is caught and held back before it ships. The skills would rather tell you what they cannot prove than hand you a confident wrong answer.
And nothing is taken on trust. Every number in a finished report traces straight back to the rows in the source file that produced it.
This number reached a live page once, published as if it were real. It is wildly wrong, and one missing check let it through. These skills exist to catch it before it becomes the number in your meeting, with your name on it.
One specimen · the Metric Library
How much recurring revenue this year's cohort of existing customers grew or shrank to, counting their upsells, downgrades, and cancellations, but not any brand new customers.
The fork, why two teams get different numbers
The single most gamed SaaS metric, and the forks live in the denominator and the window. The cohort fork: NRR must measure only the customers present at the start, yet the common error is ending total MRR over starting total MRR, which sneaks new customer revenue into a retention number. The window fork: a trailing twelve month cohort figure versus a single strong month annualized. Investors read the trailing figure, internal dashboards often show the annualized one, and they rarely match.
The trap
The denominator swap. A company adding logos fast can show 130% NRR while its actual cohort is shrinking, a growth rate wearing a retention label.
Priced for the operator, not the procurement cycle. Every paid tier is a one-time purchase with lifetime updates: no monthly seats, no subscription, no lock-in. Your company already rents BI seats that mostly go unopened; this is the opposite trade.
Core teaches your agent to build one report you can trust. Everything turns reporting into a system: the platform skills, the intranet, and both libraries. Three or more people? The team license already costs less than three personal copies.
The files are plain text with no copy protection, because a tool you cannot read is not one you can trust. Own them once, edit them freely, keep them forever. And lifetime updates mean buying any tier now buys the whole road: deeper libraries, more templates, the self-serve hosted tool, every future release at no new cost. The changelog is the proof. Every paid tier carries a 14 day, no questions asked refund.
In build: the hosted tool. Upload a raw export, get an audited report site, no agent required. Join the waitlist.
What is Kymira?
Installable skills and two reference libraries for the agent you already run, Claude Code or Cursor. They teach it to turn raw exports into business intelligence where every number reconciles to the file's own totals, and anything it cannot prove is caught before it ships.
What do the skills actually do?
Each skill is a plain markdown playbook your agent reads before it builds a report: find what a file asserts about itself, reconcile every figure to it, resolve the metric definitions teams disagree on, and design a dashboard that reads at a glance. Plus the skills that turn your reports into a secure internal platform, with maps, exports, delivery, alerts, decks, annotations, and the metric store. Twenty-one skills in all. For what this is actually like, day by day, read your first week.
How do I install a skill?
Copy the skill's
folder into your agent's skills directory, ~/.claude/skills/ for Claude Code, or
the generated AGENTS.md rule for other agents, and start a fresh session. There is no build
step, a skill is just files. The install guide walks through each agent.
What is in the Metric and Format libraries?
The Metric Library has 351 metric definitions across twelve departments, each naming the competing definitions teams argue over (the fork) and how the number lies in real exports (the trap). The Format Library maps 47 vendor export shapes, Stripe, QuickBooks, Shopify, Salesforce, GA4 and more, with the structural traps in each and the anchor that reconciles it.
Do I own the skills, or is it a subscription?
You own them. Every paid tier is a one-time purchase with lifetime updates, no subscription. The files are plain text with no copy protection, because a tool you cannot read is not one you can trust.
Can you build it for me?
Yes. Built for you is a founder-led engagement: the engineer behind the engine builds a custom, certified BI site on your real exports. It is by application, priced on the scope.
Where does my data go?
Nowhere. The skills
are static text files that run inside your own agent, on your machine; Kymira has no server
that ever sees your exports, and the files contain no telemetry. The only network calls in
the product are the optional installer checking your license key and the optional
kymira update command fetching new skill versions; neither ever transmits your
data.
Couldn't I just prompt this myself?
You can write the sentence: always reconcile to the file's own totals, never guess. The skills are the several hundred rules for what happens after that sentence fails: the Total row that is also a data row, the check that cannot fire, the tolerance that absorbs the exact error it exists to catch. Each rule was paid for by a real wrong number, which is precisely why a one-line prompt does not contain it.
Won't a better model make this unnecessary?
The guarantees here are process, not model behavior: reconciliation runs as code your agent writes and re-runs, and gates that fail closed cannot be talked out of by a smarter model, because they are not requests to the model. And most of the content is facts about vendor files and your own definitions, which no model upgrade supplies: a better model still does not know which churn definition your CFO ruled on. When models change, lifetime updates cover the port.
What if it still ships a wrong number, or is not for me?
The method's whole posture is that anything unproven is caught and held, not shipped, and a failed check keeps the last good version live. And commercially: every paid tier carries a 14 day, no questions asked refund. Try the free skill first; if a pack is not what you needed, one email refunds it in full.
Does it work with Cursor and other agents?
Yes.
Every skill ships in four formats: the Claude Code skill folder, a Cursor rule file for
.cursor/rules/, an AGENTS.md variant, and a plain prompt for any other agent.
The install guide covers each.
Can I upgrade from Core to Everything later?
Yes. Upgrading is the same motion as updating: get the Everything pack and re-run the installer, which replaces the Core pack cleanly. Write to the support address for the upgrade price; you pay the difference, not twice.
Is there a version that does not need a coding agent?
In build: the self-serve hosted tool, where you upload a raw export and get an audited, certified report site with no install and no agent. The skills are the engine behind it. Join the waitlist to be first in line.