金融
个人理财、预算与财务工具
autonomous-run
williamwue
"Run a bounded task until its completion condition is verified."
research-reporting
YuukiAS
Create repo-grounded research reports, milestone summaries, experiment reviews, technical notes, advisor/group-meeting reports, and result retrospectives from project evidence. Use for report semantics even when the final deliverable is a formal PDF; rendering mechanics belong to companion document skills.
context-budget
texugo7badger
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
architect
williamwue
"Design caller-first types and modules, compare alternatives, then implement within scope."
roadmap-architect
odysseythink
Turn a large multi-phase roadmap into an execution-ready plan by splitting oversized goals (so an AI executor never silently drops scope), ordering real source-level dependencies, judging what can run in parallel, and labelling each sub-task with the execution mode it should run in (normal / plan / design). Use this skill whenever the user wants to "拆分 roadmap", "细化路线图", "标注每个阶段用什么模式跑", "排依赖 / 看能不能并行", "防止 AI 执行时遗漏功能", or asks which sub-tasks are safe in normal mode vs need plan mode vs need design mode. The defining feature is ROI discipline: it does the high-leverage work once (one shared rubric, applied in a single batch pass over every phase) instead of re-deriving the same judgement phase-by-phase across many turns. Do NOT use this skill to actually execute a roadmap task — it only produces and refines the plan.
Beancount Accounting
ouachitalabs
This skill should be used when the user asks to "add a transaction", "create a beancount entry", "record an expense", "balance my accounts", "query my finances", "check account balances", "categorize spending", "write beancount", "edit .beancount files", "run a BQL query", "reconcile accounts", or mentions beancount, double-entry accounting, or ledger files. Provides comprehensive beancount syntax, directives, and query language expertise.
autonomous-run
williamwue
"Drive one bounded engineering task through evidence-based iterations to a fixed predicate without stopping for routine intermediate prompts."
to-tasklist
G-Eskayo
Convert a confirmed design/requirements doc into a persisted markdown task list with per-task status checkboxes, for projects that have no issue tracker (private/local-only repos). Use when a design doc has just been approved and the project has no GitHub issues (e.g. local-only git repos holding sensitive data), instead of to-issues/to-prd.
autopilot-stack
williamwue
"Build and review a linear change stack; leave landing to the operator."
data-throughput-accelerator
texugo7badger
Use when large data ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, or table synchronization needs to become much faster while preserving data correctness.
blast-area
crissmoldovan
"Map what a set of changes would affect before making it: callers, data contracts, jobs, UI, tests, build toolchains, deploy ordering, and second-order readers — with searched negatives and a list of what the map cannot see. Use when you need to know what a change would break."
manage-rag-default
DocAILab
Analyze a RAG task and produce guidance for choosing exactly one available Agentic RAG Skill using evidence dependencies, retrieval routes, corpus characteristics, and execution budget. Use as the first and only Skill loaded during the Manage selection stage.
resolve-problem-report
crissmoldovan
"Take a reported problem end to end: reproduce the claim, find the root cause, offer candidate fixes with trade-offs, spec the chosen one, and land it through review. Symptoms: a user reported X, this is broken in production, a flaky test is hiding something real, someone filed a bug or feature request, this keeps coming back. Use it when the report deserves more than a quick patch; for a one-line fix, just fix it."
frevana-s3
FinpeakInc
Upload any local file (images, videos, PDFs, documents, archives, data files) to S3 via Frevana's universal upload flow (POST /s3/custom-upload-url with scene_type=universal) and return its public URL, file key, and content ID. Use this skill whenever the user asks to upload, host, share, or store arbitrary files in Frevana S3 storage, or update previously uploaded files via file_key.
speed-it
ravidsrk
Bring declared user journeys within pre-declared performance budgets, proven by measurement. Controlled baseline (measure to a metric contract, not once) → profile the real bottleneck → fix PR-per-hotspot with a mandatory before/after → re-benchmark to the metric's statistical contract → add CI regression guards, looping until every journey is within budget or parked. Use when "the app is slow", "perf sweep", "Core Web Vitals", "get under budget", or an unattended perf-hardening run. Not for a per-diff perf opinion (review-it) or post-deploy watch alone (observe via ship-it).
idea-generator
odysseythink
Systematically generate startup idea candidates using 8 proven recipes adapted for the user's specific context (skills, industry exposure, connections, assets). Use this skill whenever the user is stuck in "don't know what to build" mode, says "I need ideas", "what should I work on", "help me brainstorm directions", "I'm not finding anything", or has been in open exploration for 2+ weeks without locking a direction. Also trigger when the user finishes a round of idea-evaluator scoring and all candidates scored ≤4, indicating the current idea pool is exhausted and needs replenishment. This skill outputs a ranked list of concrete idea candidates ready to be fed into idea-evaluator. It is a DIVERGENT tool (expand options) that pairs with idea-evaluator (CONVERGENT tool, narrow options). Do not use this skill if the user already has a clear direction — use idea-evaluator instead.
finance-data-toolkit
onewaymyway
金融数据抓取与分析全链路工具箱。覆盖股票基础数据、东方财富股吧帖子、财经新闻、研报等多源抓取，提供数据清洗、技术/基本面信号计算、舆情分析、研报自动生成功能。适用于量化选股、舆情监控、投研自动化、个人投研决策支持等场景。
cost-tracking
texugo7badger
Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.
arena
williamwue
"Compare independent candidates for the same artifact, cross-judge them, select a base, integrate stronger ideas, and verify the result."
cost-aware-llm-pipeline
texugo7badger
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
tiledbvcf
YuukiAS
Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.
isolated-change-validation
crissmoldovan
"Validate a change in a sandbox physically separate from the trusted tree, and earn a verdict a reader can check rather than a builder's claim: freeze the source identity in a hash manifest before the first edit, declare the path budget, watch one RED per behaviour, run the gates yourself, review on independent axes, classify every scan hit, and hand the run over as runnable state. Symptoms: prove this works before it goes anywhere near main, the agent says the tests pass, validate this in a sandbox, the scratch tree has no git, an overnight unattended run someone else picks up, keep the accepted candidate somewhere it cannot be lost, the sandbox must not be able to reach the real repository. For a change you are landing in the repository itself, use a delivery skill; this is for work that stays outside it until it is accepted."
setup-oh-my-stack
williamwue
"Preview and configure pstack-style per-workflow models, review panels, and reasoning budget from the current runtime inventory."
architect
williamwue
"Ground a nontrivial design, compare distinct caller-first type and module sketches, then implement within scope and redesign when evidence contradicts the shape."