scoreboard
Skill1 starsChanged 16 days agoMITView on GitHub
Show the user's live ESPN fantasy football matchup scores across all their leagues in one view. A summary table with each side's score, top three scorers and projection, then each league's starters slot by slot with points and projections. Use for "how are my matchups", "scores", "scoreboard", "am I winning", "show all my games", or during and after game windows.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- joshuaporth/appsec-skilltheir own version, first seen May 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- joshuaporth/appsec-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- tradesSkill
- waiversSkill
- weekly-checkSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 49
Keep names short: last name without suffixes (Jr., Sr., III), or first initial plus last name if two players share one.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Scoreboard across leagues
Uses the espn-fantasy MCP tools. ESPN's app shows one matchup at a time; this puts every league on one screen. It's a status view, not advice: don't recommend moves unless the user asks.
1. Gather
get_scoreboard: every league's matchup in one call, for the current week unless the user named one. If the user named one league, useget_matchupfor just that league instead. A league inerrors(usually a bye week) gets a one-line note instead of a row.list_leaguesfor each league's display name, since the matchups carry only the alias.
From each matchup, use for both sides:
score(points so far) andprojected(ESPN's live projected final).winProbability: ESPN's chance that side wins (0–1). It's set for the current week only, and is null otherwise.- Each starter's
slot, name,actualPoints,projectedPoints,injuryStatus,lockedandgame(kickoff, opponent).
A player has played, or is playing, if locked is true. Show his points even if they're 0.0. A player who hasn't kicked off shows "—" for points. On a bye week (opponent is null), say so and show only the user's side.
2. Summary table
One row per league, with the most interesting game first: closest projected margin, then the rest.
| League | You | Opponent | Proj. (you – opp) | Win % | Status |
| League A | 90.8 · Smith 22.9, Jones 19.7, Lee 9.1 | 83.2 Team Name · Brown 27.4, Diaz 16.4, Cole 14.7 | 104.0 – 96.5 | 71% | Leading by 7.6 · 1 left vs 1 |
- You: your score, bold if you're ahead, then your top three scorers by actual points so far, as last names with points. Before any of your starters has played, show the top three by projection instead, marked "proj".
- Opponent: their score (bold if they're ahead), their team name, then their top three the same way.
- Proj.: the two
projectedtotals. - Win %: your
winProbabilityas a whole percentage (ESPN's number, not yours). Show "—" when it's null. - Status: leading or trailing, and by how much: "Narrow lead" if the margin is under about 10, then how many starters each side still has to play ("2 left vs 3"). Once every starter on both sides has played, say "Won" or "Lost".
Above the table, say in one line whether games are still in progress, and in which window ("4:25 PM games in progress, SNF and MNF still to come").
3. Per-league detail
A table per league, headed with the league name:
| Slot | You | Pts / Proj | Opponent | Pts / Proj |
| QB | Player A (SNF) | — / 16.3 | Player B | 16.5 / 20.3 |
- Pair starters by slot, in the league's slot order, both sides on one row.
- Points are actual / projected, with "—" for players who haven't played.
- Mark players who haven't kicked off with their window: (TNF), (SNF), (MNF), or the day and time for anything else. Mark injury tags after the name: Q, D, O.
- Keep names short: last name without suffixes (Jr., Sr., III), or first initial plus last name if two players share one. Team defenses keep their team name ("Broncos D/ST").
4. One line per league
After the tables, give each league one line on what's left: who still plays on each side, and what has to happen. For example: "Up 30 with Mahomes left; they have three Monday-night starters, so it isn't locked up." Keep it factual. No lineup advice unless the user asks.
Give times in the user's time zone (Eastern if unknown).
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
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.