Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Operating Kpi Cadence

ASecurity

Installs the monthly operating review -- a short measure set defined precisely enough to be uncontestable, each with an escalation rule that fires automatically, when you need reporting that changes decisions.

8 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgotestingapiperformance

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-finance-skills --skill operating-kpi-cadence --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Operating Kpi Cadence?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Operating Kpi Cadence
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-operating-kpi-cadence/badge)](https://www.skillsdirectory.com/skills/andreworia-operating-kpi-cadence)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: Operating KPI Cadence
description: Installs the monthly operating review -- a short measure set defined precisely enough to be uncontestable, each with an escalation rule that fires automatically, when you need reporting that changes decisions.
---

# Operating KPI Cadence

## When to use

Use this skill in the first weeks of ownership, when the reporting rhythm is set, and whenever the monthly pack has grown to forty pages nobody reads. Reach for it after a covenant scare, when the board finds it was watching the wrong measures a month too late.

## What it does

Produces the operating review as an installed process: a fixed calendar, eight to twelve measures each with a written definition, the reference against which each is read, escalation rules agreed before any variance appears, and an agenda that runs to decisions.

## Method

1. **Fix the calendar first.** Close by working day eight, pack out working day ten, review on working day twelve, actions within two days, published a year ahead. The dates should be boring and immovable; the 100-day plan's reporting rebuild exists to make them achievable.
2. **Choose eight to twelve measures, no more.** Four families: trading in the month, the unit economics behind it, cash and balance sheet, and covenant. Each earns its place by tracking a named lever in the EBITDA bridge or a covenant test; one mapping to neither is interesting, not operational.
3. **Write the definition contract.** For each measure: numerator, denominator, source system, cut-off, owner, restatement policy. A measure whose definition is argued in the meeting has already failed -- the argument displaces the decision it was meant to prompt.
4. **Never show an actual alone.** Every measure appears against budget, prior year and a trailing twelve-month trend. A single month is noise; the turn in a trend is the signal worth acting on early.
5. **Set the escalation rule before the first variance.** For each measure: threshold, trigger, responder, deadline. Agree it once, in calm conditions -- a rule negotiated in the month it fires is not a rule. Thresholds must catch both a single bad month and a slow drift across several.
6. **Run the meeting to variance and decision.** The pack is read before, not during. The agenda is variances outside tolerance, escalations triggered, decisions required, actions from last month. Anything needing a slide walkthrough belongs elsewhere.
7. **Keep the operating review separate from the board.** Monthly is management and the operating partner, and it is operational; quarterly is the board, and it is strategy, plan and capital. Merged, strategy becomes a read-through of the accounts.
8. **Re-cut the measure set annually.** Retire any measure that has not triggered a decision in twelve months; add the ones the year's surprises would have caught. Dashboards grow by default; only pruning keeps them readable.

## Inputs

- The EBITDA bridge and value-creation workstream KPIs
- Covenant definitions, test dates and levels from the credit agreement
- Chart of accounts and the source system behind each measure
- The management accounts timetable and current close performance
- The board calendar and existing pack

## Output format

- The published calendar: close, pack, review and action dates for a year
- Eight to twelve measures, each with its definition contract in prose
- The reference set for each: budget, prior year, trailing twelve months
- Escalation rules: threshold, trigger, responder, deadline
- The standing agenda, and its separation from the quarterly board
- Present the measure set and all schedules in prose, never as markdown tables

## Example

Marlow Testing Group (fictional, illustrative): net debt at close is 100 on LTM EBITDA of 25, so net leverage is 4.0x against a 5.0x covenant. EBITDA can fall to 20 before breach, a cushion of 5, or 20% -- so the escalation rule is written in EBITDA, not the ratio: if LTM EBITDA falls below 23.5, leaving under 15% cushion, the CFO produces a thirteen-week cash forecast and covenant reforecast within ten working days, and the chair is told that day. Order intake carries its definition contract: the signed value of orders with a purchase order number received in the month, excluding framework renewals, from the order book at the last calendar day, owned by the commercial director, restated only for cancellations inside thirty days. A dull sentence that ends the monthly argument about whether a verbal commitment counts.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →