agentleFS
sebssebs/rewelo/.claude/skills/what-if/SKILL.md

what-if

Skill2 starsChanged 51 days agoMITView on GitHub

Simulate priority changes without modifying real data

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call simulate with no changes for the current ranking of the open tickets: it is the baseline each scenario is compared with.

    line 14
  2. Very specific:

    Use ticket_list for the tickets' scores, to name them in scenarios (ticket_list returns 100 tickets per call: page with offset until you …

    line 15
  3. Distinctive:

    Ask the user: "What scenario do you want to explore?"

    line 19
  4. Very specific:

    Call simulate with the hypothetical change: changes for new scores of existing tickets, add for new tickets, remove for dropped ones, …

    line 29
  5. Very specific:

    Don't recalculate priorities yourself: simulate returns the ranks and priorities before and after, and rankChange for every ticket that …

    line 30
  6. Distinctive:

    After showing results, ask:

    line 52

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

What-If Scenario Simulation

Explore prioritization scenarios for project $0 without changing real data.

Setup

  1. Call simulate with no changes for the current ranking of the open tickets: it is the baseline each scenario is compared with. Don't take it from calc_priority, which ranks done tickets too, while simulate ranks the open ones (not state:done)
  2. Use ticket_list for the tickets' scores, to name them in scenarios (ticket_list returns 100 tickets per call: page with offset until you have total of them)

Interactive loop

Ask the user: "What scenario do you want to explore?"

Examples:

  • "What if we drop the estimate on ticket X from 8 to 3?"
  • "What if the penalty on compliance doubles?"
  • "What if we remove ticket Y entirely?"
  • "What if we add a new ticket with B=13, P=8, E=5, R=3?"

For each scenario

  1. Call simulate with the hypothetical change: changes for new scores of existing tickets, add for new tickets, remove for dropped ones, weights for other weights. It writes nothing (do NOT call ticket_update).
  2. Don't recalculate priorities yourself: simulate returns the ranks and priorities before and after, and rankChange for every ticket that moved.
  3. For "what would it take for X to reach the top N?", call explain_priority with title and top: it shows the formula and the smallest single score change that gets there.

Output

Ranking diff

TicketBaseline RankScenario RankChangePriority Delta

Highlight:

  • Tickets that moved up or down by 2+ positions
  • The ticket(s) directly affected by the scenario
  • Any ticket that changed from "in sprint" to "out" or vice versa

Impact summary

  • "Reducing estimate on X from 8 to 3 moves it from #7 to #2, displacing Y and Z"
  • "Doubling penalty on compliance tickets reshuffles the top 5"

Continue or apply

After showing results, ask:

  • "Try another scenario?" → loop back
  • "Apply this change for real?" → only then use ticket_update
  • "Done" → show final baseline vs. all explored scenarios side by side

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.