lyndonkl/wc-decision-logger
skills/wc-decision-logger/SKILL.md
Appends FIFA World Cup Fantasy decisions to tracker/decisions-log.md — logging not just what the manager chose but the full OPTION SET they chose from, which option the board recommended, whether the manager overrode it, and the manager's stated reasoning. Also archives the full generation (population → offspring → board → pick) to generations/, and updates the archetype scoreboard (which genotypes' blocks were chosen/won) and the manager's revealed preferences. Append-only; never overwrites. The override rows are the system's most valuable learning signal. Use after the manager picks an option off a board.
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude wc-decision-loggerInstall 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, 7:34 AM230.1s1 file scanned
SKILL.md
- name:
- wc-decision-logger
- description:
- Appends FIFA World Cup Fantasy decisions to tracker/decisions-log.md — logging not just what the manager chose but the full OPTION SET they chose from, which option the board recommended, whether the manager overrode it, and the manager's stated reasoning. Also archives the full generation (population → offspring → board → pick) to generations/, and updates the archetype scoreboard (which genotypes' blocks were chosen/won) and the manager's revealed preferences. Append-only; never overwrites. The override rows are the system's most valuable learning signal. Use after the manager picks an option off a board.
wc-decision-logger — log the choice, the option set, and the why
Implements footballfantasy/context/frameworks/decision-log-format.md. The key difference from a normal decision log: here we record a choice among presented options, including the recommendation, the override, and the manager's reasoning — because three learning loops feed on exactly that (archetype scoreboard, revealed preferences, specialist calibration). A bare "chose B" teaches nothing.
Inputs (from the Director, after the manager picks)
- The board (option set with lineage + fitness + variance + dissent), the recommended default.
- The manager's pick, any modification, their stated reasoning, the objective θ/k in force.
Workflow
- [ ] 1. Build the log entry (schema below) — capture the full option set + pick + reasoning + override flag
- [ ] 2. Append atomically to tracker/decisions-log.md (never overwrite)
- [ ] 3. Archive the generation to generations/<round>/ (population, fitnesses, offspring lineage, board, pick)
- [ ] 4. Update tracker/archetype-scoreboard.md (which genotype's blocks were chosen)
- [ ] 5. On override/modification, append a revealed-preference note to manager-profile.md
- [ ] 6. Return the decision_id
Entry schema (per decision-log-format.md)
### {iso8601} | {decision_type} | round {round_id}
- decision_id: {round_id}-{decision_type}-{NN}
- objective: θ={..}, k={..}
- board_options: [ A "{handle}" — lineage — fitness — variance ; B … ; C … ]
- recommended_default: {option}
- manager_pick: {A | modified A | own plan}
- manager_modification: {what they changed}
- manager_reasoning: {their stated why — verbatim/close; this is gold}
- override?: {yes/no}
- key_assumptions: {what the pick bets on}
- dissent_carried: {strongest case against the pick}
- confidence: {0–1}
- will_verify_on: {round id}
- outcome: {filled by round-review}
- outcome_recorded_on: {filled later}
- what_we_learned: {filled later}
decision_type ∈ squad-build | matchday | transfer | captain | chip | ad-hoc.
Generation archive (the evolutionary trail)
Write generations/<round>/<decision_type>.md capturing the whole search: the population (each archetype's candidate + self-dissent), the fitness table with decompositions, the offspring with lineage + repair logs, the diversity report, the board, and the manager's pick. This is how the search is audited and how memetic learning reconstructs which genotypes produced winning blocks.
Scoreboard + revealed-preference updates
- Archetype scoreboard: increment the count of "blocks chosen" for each genotype whose block appears in the picked candidate. After the round (via round-review) attach the points outcome so the scoreboard reflects which genotypes win, not just which get picked.
- Revealed preferences: when the manager overrides or modifies, append a one-line note to
manager-profile.mddescribing the tilt (e.g. "took the differential captain but refused the second punt → will gamble the armband, not the whole squad"). These become soft fitness terms.
Guardrails
- Append-only. Never overwrite a prior entry. Outcomes are filled in later by round-review, in place.
- Log the option set and the reasoning, always — not just the pick. The override rows are the highest-value training signal; capture the manager's words.
- One entry per decision; one generation archive per decision. Keep
decision_ids unique and chronological.
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