Hundred-Day Plan
SkillCommerce & financeProduces the first hundred days as a bandwidth-budgeted, sequenced plan with the reporting cadence installed in week one and an explicit cut list, when you need a plan management can execute rather than a wish list.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Hundred-Day Plan skill
What this skill tells your AI
The instructions your AI receives, as published by andreworia/claude-finance-skills in packs/private-equity/skills/hundred-day-plan/SKILL.md and read by ahel’s review.
When to use
Use this skill between signing and completion, when the team converts the investment thesis into what actually happens after the wire clears. It applies equally to a carve-out carrying TSA obligations and to a bolt-on where the hundred days belong to integration. Reach for it when the draft already runs to thirty actions -- the failure mode it exists to fix.
What it does
Produces a plan in four parts: a bandwidth budget in executive-days, three to five moves priced against it, a dependency-ordered sequence with the week-one reporting cadence, and a published list of what is deliberately not being done.
Method
- Budget the bandwidth before choosing the moves. Count the executive-days genuinely available: executives who can carry change work, times fourteen weeks, times the share of their week not spent running the business -- usually one day in five. A plan costing more than that budget is a wish list, and saying so now is cheaper than finding out at day sixty.
- Choose three to five moves. Each must protect value acquired, unlock a named lever in the EBITDA bridge, or buy information diligence could not. Anything failing all three waits for the year-one budget. Price each in executive-days and hold back about 20%, because something unforecast always arrives in month one.
- Install the reporting cadence in week one. Before any initiative: the monthly close date, the pack, the board calendar, the weekly cash report and the covenant certificate cycle. Everything else is measured through it, so it goes first even though it feels like plumbing.
- Do first what only completion permits. Retention conversations, top-ten customer calls, the bank and insurance handover, the authority matrix. Short window, no substitute.
- Sequence on dependencies, not enthusiasm. Order by prerequisite: reporting before data, data before the pricing review that consumes it. Where two moves want the same executive in one fortnight, one of them moves.
- Give each move an owner, a success criterion and a stop condition. The stop condition is the discipline -- the observable that means the move should be halted or deferred. Without one, a slipping plan is indistinguishable from a wish list.
- Publish the cut list. Write down what is not being done and why, with the date each item is reconsidered. Unpublished, they return as informal asks and eat the contingency.
- Hold a day-100 gate, not a celebration. Mark each move landed, partly landed or not landed, reconcile days spent against budget, and roll what remains into the year-one plan. Two moves fully delivered beat six half delivered -- and the second pattern teaches management that plan dates are optional.
Inputs
- The investment thesis and EBITDA bridge from the IC memo
- Org chart with realistic executive time commitments
- Signing-to-completion timetable and any TSA obligations
- Day-one issues and the register's operational mitigants
- Credit agreement reporting and covenant test dates
Output format
- The bandwidth budget in executive-days, assumptions shown
- Three to five moves: owner, cost in days, success criterion, stop condition
- Week-one cadence: close date, pack, board calendar, cash and covenant reporting
- A dependency-ordered sequence by fortnight
- The cut list, each item with a reconsideration date, and the day-100 gate format
- Present the plan and all schedules in prose, never as markdown tables
Example
Thornbury Care Services (fictional, illustrative): six executives can each give one day a week over fourteen weeks, so the budget is 84 executive-days; holding back 18 as contingency leaves 66 to commit. Four moves fit exactly -- reporting rebuild 22 days, pricing review 18, rota and agency-spend review 14, top-ten customer programme 12. The pricing review carries 1.4 of the 8.0 EBITDA bridge from 12 at entry to 20 at exit, and its stop condition is explicit: if the March close still takes twenty working days, pricing is deferred, because a pricing decision on late data is worse than none. The ERP replacement, 40 executive-days alone, goes on the cut list with a reconsideration date at the year-one budget.
Signals
- GitHub stars
- 20
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
hundred-day-plan- Source
- github.com/andreworia/claude-finance-skills
github.com/andreworia/claude-finance-skills
Related picks
Skill · larksuite
The pick for Markdownmarkdown-mermaid-writing
Skill · k-dense-ai
The pick for Markdownagent-payment-x402
Skill · affaan-m
More in Commerce & financecustomer-billing-ops
Skill · affaan-m
More in Commerce & financereview
Skill · thedaviddias
More in Commerce & financechurn-prevention
Skill · coreyhaines31
More in Commerce & finance