lyndonkl/wc-decision-board
skills/wc-decision-board/SKILL.md
Renders the FIFA World Cup Fantasy decision board — the advisory output that surfaces 2-4 genuinely distinct, weighted options for the expert manager and ends on "your call." Takes the evolution engine's verified offspring (with fitness decomposition, genotype lineage, and specialist dissent) and formats each as an option with its concrete picks, EV/ownership-leverage/variance/progression decomposition, football reasoning, what it's betting on, the dissent, and an ownership read — then a trade-off axis, a recommended-but-overridable default tied to the rank objective, and a "what I need from you." Enforces options-not-commands, shows the working, surfaces dissent, never auto-commits. Use to present any squad/matchday/transfer/chip decision.
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude wc-decision-boardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 12, 2026, 7:33 AM210.4s1 file scanned
SKILL.md
- name:
- wc-decision-board
- description:
- Renders the FIFA World Cup Fantasy decision board — the advisory output that surfaces 2-4 genuinely distinct, weighted options for the expert manager and ends on "your call." Takes the evolution engine's verified offspring (with fitness decomposition, genotype lineage, and specialist dissent) and formats each as an option with its concrete picks, EV/ownership-leverage/variance/progression decomposition, football reasoning, what it's betting on, the dissent, and an ownership read — then a trade-off axis, a recommended-but-overridable default tied to the rank objective, and a "what I need from you." Enforces options-not-commands, shows the working, surfaces dissent, never auto-commits. Use to present any squad/matchday/transfer/chip decision.
wc-decision-board — render the advisory board
Implements footballfantasy/context/frameworks/decision-board-format.md. This is the system's product surface and the structural enforcement of "the agents feed me options, I decide." A board that reads like a command has failed even if its top option is right. The manager is the selection operator; this renders the choice for them.
Inputs
- The verified offspring (post-engine, post-specialist-verify): each with fitness decomposition, genotype lineage, repair log, and the specialists' dissent/annotations.
- The rank objective θ/k, the round/phase/deadline, mini-league standing, the diversity report.
Workflow
- [ ] 1. Select the 2–4 offspring to show (spanning the variance spectrum — at least one cover, one climb)
- [ ] 2. Render each as an OPTION (picks + decomposition + reasoning + bet + dissent + ownership read)
- [ ] 3. Write the TRADE-OFF axis (what actually separates them)
- [ ] 4. Write the RECOMMENDED DEFAULT (tied to θ, explicitly overridable)
- [ ] 5. Write WHAT I NEED FROM YOU (the inputs that would sharpen/change the board)
- [ ] 6. End on "your call." Write to boards/ and present. Do NOT proceed past this.
The rendered shape
═══════════════════════════════════════════════════════════════
[DECISION] — [round id] · [phase] · lock [deadline]
Objective: θ=[protect|gain|neutral] (k=[..]) — [one line why]
Mini-league: [standing] · [rounds left] Diversity: [wide|close]
═══════════════════════════════════════════════════════════════
CONTEXT
[2–4 lines: where we stand, what changed (eliminations, fixture swings,
the field's notable moves), the one tension this decision turns on.]
── OPTION A · "[handle]" ─────────────────────────────────────
Lineage: [A1 captain core + A4 clean-sheet stack + A2 differential pod]
Fitness: [n] · variance [band]
Decomp: xEV [n] · ownership-leverage [+/−n] · progression [n]
Picks: [squad/XI/captain/bench/chip — the concrete plan]
Strength: [2–3 lines, football reasoning the manager can interrogate]
Betting on: [the key assumption that must hold]
Dissent: [the strongest case against — from the critic / specialist verify]
Ownership: [template-covering | balanced | differential-leaning]
── OPTION B · "[handle]" ── [a genuinely different bet — different variance band] ──
…
[C, D as warranted; never more than 4]
THE TRADE-OFF
[1–3 lines naming the axis the manager is choosing on — variance vs floor,
template vs differential, this-round xEV vs progression carry.]
RECOMMENDED DEFAULT
"If you do nothing else, [Option X] — because [one line tied to θ].
If you'd rather [protect/gamble] instead, [Option Y]."
WHAT I NEED FROM YOU
• [the input(s) that would change the board — standing, appetite, non-negotiables, chip intent]
Your call — tell me which option (or your own variant) and I'll lock it and update state.
═══════════════════════════════════════════════════════════════
Rules (the contract)
- 2–4 options, genuinely distinct, spanning the variance spectrum (≥1 cover-leaning, ≥1 climb-leaning). Collapse near-duplicates.
- Always show the decomposition. Never a bare fitness number — the manager re-weights by their own read.
- Football register, expert. Reasoning the manager can interrogate, not "the model likes it."
- Surface the dissent on every option. A board that only sells hides risk.
- Recommend, don't command. The default is overridable and tied to θ, with the opposite-posture alternative named.
- Ask for what would change the board. The "what I need from you" block is mandatory (or an explicit "no input needed").
- End on the manager's move, then stop. Rendering the board is the last thing this skill does — it does not lock, update state, or proceed.
Mini-boards
Sub-decisions (switch the armband now or bank the 7? fire the Shield or hold? transfer X or Y?) use the same shape compressed to 2 options + trade-off + default + your-call. Same contract at every scale.
Guardrails
- If only one offspring survived verification, do not manufacture filler options — present the one with its dissent and explicitly say the alternatives were ruled out and why (and offer to widen the search if the manager wants more choice).
- If a load-bearing fact is unconfirmed (predicted XI, a knock), flag the affected option "confirm before lock."
- Write the board to
boards/YYYY-MM-DD-<decision>.mdand return its path; the Director presents and waits.
Related Skills
lyndonkl/conf-theme-clustering
testing
VerifiedTrustedCommunity
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-schedule-optimization
development
VerifiedTrustedCommunity
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-program-extraction
development
VerifiedTrustedCommunity
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-preference-elicitation
development
VerifiedTrustedCommunity
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.
127SKILL.mdUpdated Jun 28, 2026