金融
个人理财、预算与财务工具
rico-xhs-dense
ricoocuii-source
把长文章/Twitter/链接转化为高密度小红书图文系列。内容驱动分页，文案为主体（300-500字/页），视觉为辅（内容页≤25%）。10种布局模式 + 3种美学风格（手绘水彩/极简技术/现代SaaS）+ 30+ 具象隐喻物件库，按内容性质匹配。
worthless
oblangatas
Lock LLM API keys behind a local spend-cap proxy. Run worthless lock and OpenAI/Anthropic/OpenRouter traffic routes through the proxy — if the spend cap is hit, the real key never reconstructs.
記帳
itshanyu
在記帳討論串處理「金額 備註」格式的記帳訊息：AI 分類後寫入 Google Sheets。只在指定討論串生效。
timebox-evolver
VulcanusALex
Execute fixed-duration tasks with adaptive, non-mechanical autonomy under a hard time budget. Use for requests like "work for N minutes", timed research/coding/writing, or any long-chain task that must stay efficient, auditable, and stoppable with a clean handoff at time boundary.
draw-mermaid
handlename
Draw a mermaid diagram from a natural-language intent and return a syntax-validated mermaid source, verifying it with mermaid.parse() against a vendored, version-pinned mermaid.js driven by playwright-cli. Designed to be called from other skills (e.g. plan-to-issue, create-pr) through a subagent whose only return value is the validated mermaid on success or a failure reason on failure. Use whenever a mermaid diagram must be produced with a guarantee that it parses without syntax errors. Triggers include "mermaidで図を描いて構文チェックまでして", "draw a mermaid diagram and make sure it has no syntax errors", "syntax-checked mermaid".
playstore-submission-content
lukenguyen-me
Generate ready-to-paste Google Play Store text content for Android app submissions. Analyzes project context and produces all required text fields with Play Store character rules enforced.
product-architect
fogbound-bellringing777
Complete product development system with 31 specialized agents and 23 frameworks. Use when user asks to build a product, write a PRD, create a roadmap, plan an MVP, design an app, do a security audit, create a financial model, plan hiring, launch a product, set up operations, prepare for IPO, or write a compliance policy. Also triggers on help me plan, product strategy, go-to-market, fundraising, pitch deck, unit economics, competitive analysis, user personas, sprint planning, SOP, checklist for, or how do I start a company. Do NOT use for general knowledge questions, coding tutorials, or creative writing unrelated to product development.
hokkaido-project-instructions
CRYPTOKEYSAFE
Master project instructions for Anthony Potter's Hokkaido real estate investment and trip planning project. Covers investor profile, Otaru STR strategy, May 2026 trip bookings, trip financial tracking (paid vs owed), spring flower tour itinerary, property pipeline status, GK legal structure, management company research, and all confirmed facts as of March 21, 2026. Read this at the start of every conversation in this project.
financial-deep-research
ChaNg1o1
Conduct enterprise-grade financial research with multi-source synthesis, regulatory compliance tracking, verified market analysis, and forensic accounting investigation. Use when user needs comprehensive financial analysis requiring 10+ sources, verified claims, market comparisons, investment research, or forensic due diligence. Triggers include "financial research", "market analysis", "investment analysis", "due diligence", "financial deep dive", "compare stocks/funds", "analyze [company/sector]", "forensic accounting", "accounting fraud", "red flags", "SPV analysis", "revenue recognition", or "financial forensics". Do NOT use for simple stock quotes, basic company lookups, or questions answerable with 1-2 searches.
user-story-mapping
HMS091
Create a user story map that lays out activities, steps, tasks, and release slices. Use when planning a workflow, backlog, or MVP around the user journey.
cmev-run-experiment
RodelFMiguel
Run or reproduce a defined CLAIM-CMEV training, evaluation, calibration, or ablation experiment with versioned inputs and measured results. Use for model experiments and RQ1-RQ4 evidence, not routine unit tests or open-ended tuning.
goal-loop
MILTONADINA
Execute the spec-tests-implement-verify cycle for one atomic task at a time. Use after plan-decomposition has produced a task list. This is the workhorse loop - the agent implements, runs tests, reflects on failure, retries with bounded iteration. Halts mechanically when budget, iteration count, or scratchpad stasis ceilings hit. See constitution/LOOP.md for full protocol.
stripe-best-practices
EnterpriseBT
Guides Stripe integration decisions — API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, Treasury financial accounts, integration surfaces (Checkout, Payment Element), migrating from deprecated Stripe APIs, and security best practices (API key management, restricted keys, webhooks, OAuth). Use when building, modifying, or reviewing any Stripe integration — including accepting payments, building marketplaces, integrating Stripe, processing payments, setting up subscriptions, creating connected accounts, or implementing secure key handling.
frontier-orchestrator
alex-jordan547
"Frontier-models orchestrator mixing Claude and Codex (GPT) families: Claude Opus 4.8 as the orchestrator (coordinates, holds the plan, spawns workers), GPT-5.5 as the oracle (plans and validates with its own tools — cross-family so gates are never graded by the family that did the work), and Sonnet 5 / gpt-5.4 as skilled hands with Haiku 4.5 / gpt-5.4-mini / spark as cheap hands. Routes each task to the cheapest model whose context window can hold it. The orchestrator never writes code; it delegates pre-digested slices to workers. Optimizes for best result on hard tasks."
aws-cost-operations
saajunaid
This skill provides AWS cost optimization, monitoring, and operational best practices with integrated MCP servers for billing analysis, cost estimation, observability, and security assessment.
financial-disclosure-analysis
jiannanxiboy
Download, extract, verify, and analyze official financial disclosures from A-share and Hong Kong-listed companies, then write slide-ready presentation scripts with cell-level evidence. Use when the user needs source-traceable financial data from annual reports, interim reports, results announcements, or other filings, peer comparisons, period analysis, Excel workpapers, or per-page PPT scripts ready for review.
SKILL: Install IA BCC for a new client
jayclaudeai2026-spec
If anything looks wrong, halt and write a session_note to agent_memory describing what's blocking. Then notify the operator out-of-band.
otimizar-verba
sallzzbr
"Score campaign efficiency and propose a budget reallocation plan. Use when the user wants to redistribute ad spend, decide what to scale or cut, or check monthly pacing — otimizar verba, realocação de orçamento, efficiency score, pacing do mês, onde colocar o dinheiro."
backpass
YuukiFST
Train a project CLAUDE.md on its own session transcripts — one evidence-backed gradient step per run.
cost-report
Atrium-Hermes
Weekly API cost report — computes dollar costs from token usage, flags anomalies, forecasts burn, and prescribes concrete optimizations
crucible-meta-governance
terrylica
deciding whether to pivot or persist, whether to ship or hold, whether to scope-narrow a partial pass, how to manage.
fork-health-score
Atrium-Hermes
Weekly per-fork health tier synthesizing push recency + enabled skill count + 30d PR activity into ACTIVE/WARM/STALE/QUIET buckets; fleet health ratio + top-10 ACTIVE table; silent when nothing moves
expenses
benjamin-wo
Logging, finding, fixing, categorising and splitting expenses, category rules, and who owes what.
legends-and-lore
Tzeusy
Load design contracts (RFCs) to contextualize implementation work. The about/legends-and-lore/ directory contains numbered RFCs defining wire-level contracts, data models, state machines, and integration points. Consult relevant RFCs before implementing features, modifying protocols, designing state machines, or resolving cross-subsystem integration questions. Selectively load ONLY the RFCs relevant to your current task.