LC

lyndonkl/claude

Developer tools
147 stars 品質 40 トレンド 40

A production-ready library of and for Claude Code — covering thinking frameworks, research, writing, design, data/ML, corporate finance, game theory, fantasy baseball, an evolutionary 10-agent FIFA...

概要

A production-ready library of and for Claude Code — covering thinking frameworks, research, writing, design, data/ML, corporate finance, game theory, fantasy baseball, an evolutionary 10-agent FIFA...

README

Claude Code Skills Collection

A production-ready library of 262 skills and 75 orchestrating agents for Claude Code — covering thinking frameworks, research, writing, design, data/ML, corporate finance, game theory, fantasy baseball, an evolutionary 10-agent FIFA World Cup fantasy backroom, household personal finance, a 9-agent team for growing a Substack publication, and a 9-agent learning studio for becoming a contributor to ML-driven crop genetics / genomic selection. Also included: five reusable primitives for gated, verifiable research pipelines, and a 3-agent narrative team that turns researched evidence into structured long-form nonfiction.

Install in 30 seconds:

/plugin marketplace add lyndonkl/claude
/plugin install thinking-frameworks-skills

Note: Two skills need something installed separately: markdown-to-pdf needs pandoc and a LaTeX engine, and readability-check needs the textstat Python package. See Optional dependencies below. Every other skill works out of the box.


I want to…

Pick the fastest entry point for what you’re trying to do. Most users start with an agent (which orchestrates many skills); power users invoke skills directly.

I want to… Start here
Value a company / analyze an M&A target / plan an IPO company-analyst, acquisition-analyst, ipo-strategist, special-situations-analyst
Research a thematic macro trend cluster (AI compute cycle, demographic shift, climate transition, etc.) macroeconomic-analyst
Reverse-engineer a real product’s vision / strategy / tactics / ML and system architecture from public material product-strategist
Decide how to allocate capital (debt / dividends / projects) capital-allocation-strategist
Manage my Yahoo Fantasy Baseball team mlb-fantasy-coach + 6 MLB specialists
Run my FIFA World Cup Fantasy squad (evolutionary boards — agents propose, you decide) wc-director + 9 team agents
Run my household finances from PDF statements (drop in, briefing + dashboard out) household-cfo + 8 household specialists
Write a paper / grant / recommendation letter scientific-writing-editor
Improve any piece of writing (blog, memo, essay) writing-assistant
Turn a pile of research into structured long-form nonfiction (find the shape, then write it) narrative-architect → scenewright, with writing-assistant
Make a calibrated forecast or probability estimate superforecaster
Design a dashboard, viz, or UI grounded in cognition cognitive-design-architect
Build a GraphRAG / knowledge-graph retrieval system graphrag-specialist
Design equivariant / symmetry-aware neural networks geometric-deep-learning-architect
Build geometric intuition for ML math (attention, PCA, eigenvectors, high-dim spaces) math-intuition-coach
Get a weekly digest of new bioRxiv / medRxiv / PubMed / arXiv papers (life sciences + CS / ML) against my keyword watchlist literature-scan-coach → paper-synthesizer
Grow my Substack / publish intuition-first ML & systems essays librarian, intuition-builder, editor + 6 more
Learn ML-driven crop genetics / genomic selection (experiential study → notes → publish in public) biostat-tutor, biostat-assessor, biostat-editor + 6 more
Build a personalized schedule for a conference (ingest the program → cluster themes → a few grounded questions → optimized plan) conf-director + 5 specialists
Run a gated research pipeline where every number is sourced, attacked, and verified before anything is built on it market-era-historian, series-archaeologist, mechanism-analyst, claim-verifier, stage-auditor
Use just one tool (no agent) Browse the Skills Index below

How the pieces fit together

flowchart LR
    U([What do you need?]) --> D{Task}
    D -->|Analyze a company| CA[company-analystacquisition-analystipo-strategist]
    D -->|Analyze a product| PS[product-strategist]
    D -->|Write something| WA[writing-assistantscientific-writing-editor]
    D -->|Structure + write research| NA[narrative-architectscenewright]
    D -->|Forecast / decide| SF[superforecaster]
    D -->|Design / visualize| CD[cognitive-design-architect]
    D -->|Fantasy baseball| MLB[mlb-fantasy-coach+ 6 specialists]
    D -->|World Cup fantasy| WC[wc-director+ 9 team agents]
    D -->|Household finances| HF[household-cfo+ 8 specialists]
    D -->|Knowledge retrieval| GR[graphrag-specialist]
    D -->|Symmetry-aware ML| GDL[geometric-deep-learning-architect]
    D -->|Math intuition| MI[math-intuition-coach]
    D -->|Weekly paper digest| LSC[literature-scan-coach→ paper-synthesizer]
    D -->|Learn crop genomics| BIO[biostat-tutor+ 8 specialists]
    D -->|Plan a conference| CONF[conf-director+ 5 specialists]
    D -->|Gated research pipeline| RP[market-era-historianseries-archaeologistmechanism-analystclaim-verifierstage-auditor]
    D -->|One-off tool| SK[Skills Index ▾]
    CA & PS & WA & NA & SF & CD & MLB & WC & HF & GR & GDL & MI & LSC & BIO & CONF & RP --> S[(262 skills)]
    SK --> S

Orchestrating Agents

Agents detect your need and route to the right skills. Each agent’s page documents the skills it orchestrates and the workflow it runs.

Agent Domain
writing-assistant Any writing task — structure, revision, stickiness, pre-publish gate
scientific-writing-editor Manuscripts, grants, letters, reviewer responses, career docs
narrative-architect Researched corpus → validated narrative architecture. Evidence ledger, form triage, designing principle, opposition web, beat map. Selects the structure (or reports that the material has none) and never drafts
scenewright Executes an architecture into prose. SCAM scenes, POV and distance, ladder of abstraction, number handling, Hart’s nine line passes. Source-bound, and escalates what it cannot fix at its own layer
superforecaster Forecasting and probability via 5-phase calibrated pipeline
cognitive-design-architect Cognitive design, information architecture, D3 viz, fallacy check
geometric-deep-learning-architect Symmetry discovery → group ID → equivariant architecture
math-intuition-coach 3Blue1Brown-style geometric intuition for any ML/data math (attention, PCA, gradients, high-dim spaces)
literature-scan-coach Single entry point for a weekly literature-scan project; routes weekly / catch-up / on-demand / re-synthesize intents and spawns paper-synthesizer per run with the right parameters
paper-synthesizer Worker for literature-scan-coach. One window, one digest. Fetches bioRxiv / medRxiv / PubMed / arXiv, filters, clusters by theme, writes the layered-reasoning synthesis with paper links
skill-creator Orchestrates Adler’s six-step methodology to transform a methodology document (PDF, markdown, paper, framework guide) into a properly structured Claude Code skill — SKILL.md + resources + rubric
graphrag-specialist Knowledge graph construction, embedding fusion, retrieval orchestration
company-analyst End-to-end company valuation → buy/sell/hold recommendation
special-situations-analyst Distressed / private / high-growth / financial-firm valuation
macroeconomic-analyst Deep thematic research on one trend cluster — sub-trends, value chains, beneficiary archetypes, pricing-in assessment, watch-indicators
product-strategist Outside-in layered analysis of a real product — vision, strategy, tactics, operational surface, system & ML architecture map, strategist synthesis
capital-allocation-strategist Financing mix, dividends/buybacks, project investment
acquisition-analyst M&A standalone + synergy + max bid
ipo-strategist Pre-IPO → post-IPO valuation and pricing range
mlb-fantasy-coach Primary Yahoo Fantasy Baseball orchestrator; morning briefs
mlb-lineup-optimizer Daily start/sit with advocate + critic variants
mlb-waiver-analyst Weekly add/drop and FAAB bid sizing
mlb-streaming-strategist Weekly pitching plan, two-start SPs, spot starts
mlb-trade-analyzer On-demand trade offer evaluation with always-counter ladder
mlb-category-strategist Weekly push/punt plan across the 10 H2H categories
mlb-playoff-planner July-onward positioning for weeks 21–23 playoff window
wc-director FIFA World Cup Fantasy main-thread orchestrator — runs the evolutionary generation loop, presents decision boards, the manager decides
wc-strategist Population member — one archetype genotype per parallel spawn, builds a complete candidate squad/plan
wc-evolution-engine Fitness, variance-clique selection, building-block crossover + repair, mutation, diversity guard
wc-synthesis Lens fan-in reconciler — integrates advocate/critic verdicts, preserves residual dissent, never argmaxes
wc-scout Player minutes/role/set-piece/fitness data spine via live web search
wc-fixture-analyst Fixture difficulty, progression odds (2026 best-thirds math), mismatches, swing calendar
wc-squad-architect Feasibility, value-per-million, transfers, Wildcard rebuild scoping, fragility scan
wc-matchday-tactician XI, captain ladder, bench order by kickoff, manual-sub triggers — the in-round 20–40 pts edge
wc-chip-strategist Times the five chips across the tournament horizon (deploy vs hold)
wc-ownership-analyst Effective ownership, template vs differential, field over-concentration, mini-league rival leverage
household-cfo Master orchestrator + synthesizer for the household finance team; runs per-drop, monthly, and ad-hoc chat
household-intake-classifier Per-PDF document classification + manifest + account matching
household-bookkeeper PDF → reconciled, deduplicated, categorized JSON store with append-only commit
household-spending-analyst Category trends, recurring detection, 60-day cash-flow forecast, seasonal calendar
household-bills-vigilance Missed bills, duplicate / fraud / anomaly / fee scans with severity-tagged alerts
household-savings-debt Goals, emergency fund, debt strategy, mortgage prepay math, rewards optimization
household-investment-retirement Portfolio drift, contribution optimization, TLH with wash-sale awareness, retirement projection
household-tax-compliance Document tracking, deduction tracker, HSA receipt vault, year-end packet for CPA
household-dashboard-designer Weekly static HTML dashboard with cognitive-design + storytelling + fallacy guard
librarian Ingest + tag + index a Substack writer’s corpus; topic ledger maintenance
intuition-builder 5 distinct framings (everyday / physical / contrarian / historical / counterfactual) per technical topic
editor Two-pass voice + structural review of drafts; voice gate before publish
distribution-translator Turn published essays into Substack Note / X thread / LinkedIn post / cross-post blurb
growth-analyst Weekly Substack CSV → rolling baseline → attribution → per-section report
trend-scout Weekly ML/systems signal digest from ~35 curated intuition-first sources
technical-reviewer Pre-publish claim check — simplified / wrong / contested / overclaim classification with primary sources
curator Every 4-6 weeks: section map maintenance; active + reactive; handles per-section voice overlays
growth-strategist Quarterly (rolling 13-week) strategic zoomout with uncomfortable questions and kill list
biostat-tutor Socratic experiential (Kolb) tutor for one learning module; never summarizes — draws the claim out and routes it to an evergreen note
biostat-assessor Closed-book Bloom-tagged probing; mastery banding; expanding-interval spaced-repetition scheduling
biostat-lab Lab + project mentor; designs and reviews experiential genomics projects; enforces cross-validation and predict-then-check
biostat-coach Curriculum coach; tracks phase/module progress and pacing; surfaces the spaced-repetition queue
biostat-scribe Generative vault-style note/post writer from the learner’s own evergreen claims (provenance-tracked)
biostat-editor Advisory-only editor for dictated essays — directs structure, flags grammar, suggests language; never rewrites unless told (read-only by design)
biostat-emergence Bottom-up clustering of evergreen notes into structure notes (4+ to form a cluster, >12 to split)
biostat-health Vault + curriculum health audit — orphans, duplicate claims, weak titles, status drift, overdue reviews
biostat-viz Interactive D3 genetics/genomics visualizations for the docs/ site; delegates design review to cognitive-design-architect
conf-director Conference-schedule pipeline orchestrator — runs ingest → cluster → elicit → schedule, gates on per-stage confidence, guards its invariants, surfaces conflicts, never auto-commits (reusable across conferences)
conf-program-ingestor Stage 1 — parses a conference program into confidence-scored event records + axes; fans out enrichment
conf-enrichment-researcher Isolated web-research sub-worker — thickens one thin abstract with provenance + confidence
conf-theme-cartographer Stage 2 — embed-then-label clustering into 6–8 themes + outlier bucket + soft multi-membership affinities
conf-preference-elicitor Stage 3 (interactive) — a few grounded, choice-based questions over an uncertainty region, with deliberate outlier probes; builds the preference profile
conf-schedule-optimizer Stage 4 — constraint optimization under user-owned weights; protects contiguous free time; surfaces unbreakable conflicts
market-era-historian Reconstructs how a market worked in one bounded period — fills a provided field schema with sourced, calibrated claims; built for parallel fan-out across periods
series-archaeologist Assembles decades-long datasets from incompatible sources — per-point provenance, a concordance of definitional breaks, documented bridges, no silent splices
mechanism-analyst Worked-number analysis of a market mechanism or deal economics vs named rivals — machine-checkable arithmetic plus a simulation-ready parameterization
claim-verifier Refute-first adversarial verification of a claim batch — independent re-sourcing, re-derivation, interval and grade challenge; confirmed / adjusted / rejected / unverified
stage-auditor The automated gate between pipeline stages — runs a contract’s deterministic checks, judges the rest, emits pass/fail plus a remediation payload; audits, never repairs

Optional native dependencies

A small number of skills wrap native command-line tools and only work if those tools are installed on the user’s machine. All such skills are optional. If a required tool is missing, the skill exits immediately with the exact install commands; nothing breaks silently and the rest of the library continues to work normally.

If you do not want to install the tools below, simply do not invoke the skills that need them. Every other skill in this repository, and every agent that does not include one of these skills in its pipeline, works without any additional native dependencies.

Skills with native dependencies

Skill Native dependency Why it’s needed Install (macOS) Install (Linux / Debian)
markdown-to-pdf pandoc and a LaTeX engine (xelatex) Renders a finished markdown report to an analyst-style PDF. The LaTeX engine produces the typography. Without these tools the skill cannot run; it has no fallback rendering path. brew install pandoc basictex``sudo tlmgr update --self``sudo tlmgr install xetex sudo apt install pandoc texlive-xetex texlive-fonts-recommended
readability-check textstat (Python package) Computes the five readability formulas. Without it the skill prints the exact install command and exits; it does not guess scores. python3 -m pip install --user textstat python3 -m pip install --user textstat

basictex on macOS is about 90 MB. Do not install mactex unless you specifically need the full LaTeX stack (~5 GB).

Agents that invoke these skills

Currently only one agent pipeline includes a dependency-requiring skill:

  • product-strategist calls markdown-to-pdf in its final step to render the finished strategist report.

If you run product-strategist without pandoc or xelatex installed, the agent still produces its primary markdown report; only the PDF rendering step is affected, and the agent will surface the install instructions in that case. You can install the tools later and re-render any past markdown report on demand.


Skills Index

262 skills across 8 super-categories. Every skill’s full methodology, templates, and evaluation rubric live in its SKILL.md — click any entry to drill in.


Installation

/plugin marketplace add lyndonkl/claude
/plugin install thinking-frameworks-skills

All 261 skills become available immediately. Claude invokes them automatically based on your request and each skill’s trigger description.


Using Skills

Skills activate automatically when you use matching trigger phrases — no manual invocation needed.

"Help me decide between three options..."      → decision-matrix
"I need to run user interviews..."              → discovery-interviews-surveys
"Value this company for acquisition..."         → acquisition-analyst (agent)
"What should I stream at pitcher this week?"    → mlb-streaming-strategist (agent)
"My chicken keeps coming out dry..."            → chef-assistant

Contributing

Fork, branch, and PR. Follow the skill structure above — SKILL.md under 300 lines, self-assess against the rubric (target ≥ 3.5), and include trigger phrases in the YAML description so Claude can auto-invoke.

Resources

License

Open source; use freely with Claude Code. Individual skills carry their own attributions.

Acknowledgments

Skills draw on established frameworks and practitioners:

  • Thinking: Bayesian reasoning, causal inference, dialectics, first principles
  • Research: Jobs-to-be-done (Christensen), design of experiments (Box, Taguchi), user research (Torres, Ulwick)
  • Decision-making: Multi-criteria analysis, expected value, risk analysis
  • Corporate finance: Damodaran’s valuation curriculum
  • Writing: Story structure (McKee, McPhee), clarity (Zinsser, Pinker, King), SUCCESs (Heath)
  • Culinary: Technique (Pépin, Child, López-Alt), food science (McGee, Sharma), cultural cooking (Bourdain, Chang, Ottolenghi)
View this README on GitHub

推奨ツール

別のキーワードを試すか、フィルタを外してください。

インストール

npx skillfish add lyndonkl/claude