fin-guru-quant-analysis
Perform quantitative analysis of returns, correlations, risk factors, and portfolio optimization. Statistical modeling with institutional-grade rigor.
fin-guru-research
Execute comprehensive market research workflows. Covers market intelligence gathering, sector analysis, security research, and competitive intelligence with temporal validation.
fin-guru-strategize
Develop comprehensive portfolio strategies from quantitative analysis. Integrates margin, dividend, and cash-flow tactics into actionable wealth-building plans.
margin-management
Monitor the margin-living strategy from the live DB snapshot. Refreshes the local database first, then reads margin balance, interest costs, dividend coverage ratio, and portfolio-to-margin thresholds. Triggers safety alerts for large draws and gives time-based scaling recommendations. Use when updating margin, balances, coverage ratio, or margin strategy analysis.
retirement-syncing
Parse and report retirement holdings from Vanguard and Fidelity CSV exports. CSV-only by design — the Vanguard IRAs and Fidelity 401k are not connected in SnapTrade, so there is no live/DB path yet and no persistent destination. Triggers on sync retirement, update retirement, vanguard sync, 401k update, IRA sync, or working with imports/retirement/ files.
finance-report
Generate institutional-quality PDF analysis reports for stocks and ETFs. USE WHEN user mentions generate report, create pdf, stock analysis, ticker report, watchlist analysis, OR regenerate reports. Includes VGT-style headers, embedded charts, portfolio sizing, and Perplexity sentiment integration.
monte-carlo
Run Monte Carlo simulations for Finance Guru portfolio strategy. USE WHEN user mentions monte carlo OR run simulation OR stress test portfolio OR probability analysis OR income projections OR margin safety analysis. Supports a 4-layer portfolio (Growth, Income, Hedge, GOOGL) with operator-supplied starting values.
portfolio-syncing
Refresh positions and balances from SnapTrade into family_office.db, then validate the snapshot. Reads live positions, cost basis, SPAXX, and margin from the DB (never a stale CSV). USE WHEN user mentions sync portfolio OR update positions OR portfolio-sync OR refresh positions OR downloaded from Fidelity.
transaction-syncing
Refresh investment activities and card/bank expenses into family_office.db, then review spending. Investment activities come from the DB transactions table (SnapTrade); debit-card and bank spending comes from the DB bank_transactions table (SimpleFIN), auto-categorized. Sync-first so nothing is stale. USE WHEN user mentions "sync transactions", "transaction history", "expense tracker", "categorize spending", OR "update expenses".
compliance-scan
Privacy and security compliance scanner for the Finance Guru repo. Catches API tokens, account numbers, dispatcher URLs, owner-name leaks, untracked sensitive files, and gitignore gaps before they reach GitHub. Use this skill whenever the user says "compliance scan", "is this safe to push", "scan for PII", "secrets check", "pre-commit security", "pre-push security", "check for leaks", "PRIVACY.md compliance", "audit privacy", "any leaks", "check before push", or wants a sanity check before `git push`. Also run it proactively after editing PRIVACY.md, after creating any new file under `.claude/skills/`, `notebooks/`, `fin-guru-private/`, or `scripts/qa/`, and any time the user adds a new credential, deploy URL, or webhook. Privacy and security are non-negotiable in this repo — when in doubt, run it.
instance-onboarding
Scaffold a private Finance Guru instance, complete its profile, add a broker CSV, and perform the first local database readout. Use after installing the finance-guru plugin.
codeagent
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.
codex
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.
gemini
Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks.
kiro-specs
Create a Kiro spec for a feature in .kiro/specs create/update feature spec/PRD/RFC—requirements, design doc, and implementation tasks checklist.Trigger on spec/specification/PRD/RFC/tech spec, requirements/user story/acceptance criteria/EARS, design doc/architecture, task breakdown/implementation plan/checklist; 需求/验收/设计/任务.
living-documentation
Sync spec files with code changes. Triggers when modifying code that affects .kiro/specs/*/requirements.md or .kiro/specs/*/design.md. Use after implementing features, fixing bugs, or refactoring that changes behavior documented in specs.
multi-agent-orchestration
Orchestrate multi-agent workflows from a Kiro spec using codex (code) + Gemini (UI), including dispatch/review/state sync via AGENT_STATE.json + PROJECT_PULSE.md; triggers on user says "Start orchestration from spec at <path>", "Run orchestration for <feature>", or mentions multi-agent execution.
sequential-orchestration
Execute spec tasks one at a time with tmux visibility. Python-based orchestrator with transparent serial execution. Triggers on: rate limit, overnight run, throttled execution, avoid quota exhaustion, sequential mode, slow execution, or user says 'Run sequential orchestration for <spec>'.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
debug-like-expert
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.
create-subagents
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
create-plans
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that Claude will execute. Produces Claude-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.
manage-skills
This skill should be used when the user asks to "create a skill", "build a new skill", "write a SKILL.md", "improve a skill", "update a skill", "audit a skill", "verify a skill", or mentions skill structure, skill best practices, or skill authoring. Provides expert guidance for creating, updating, auditing, and managing Claude Code Skills.
sqlalchemy-postgres
Expert guidance for SQLAlchemy 2.0 + Pydantic + PostgreSQL. Use when setting up database layers, defining models, creating migrations, or any database-related work. Automatically activated for DB tasks.
manage-hooks
This skill should be used when the user asks to "create a hook", "add a PreToolUse hook", "debug a hook", "fix a hook", "hook not working", or mentions hook configuration, hook events, hook types, automating workflows, or understanding hooks. Provides expert guidance for creating, configuring, debugging, and managing Claude Code hooks.
damage-control
Install, configure, and manage Claude Code security hooks that block dangerous commands and protect sensitive files. Use when setting up security protection, blocking destructive commands (rm -rf, git reset --hard), protecting sensitive paths (.env, credentials), or managing PreToolUse hooks.
docs-master
Documentation creation and summarization. Use when the user asks to "write docs", "create documentation", "update README", "document this", "summarize code", "add docs", "write a changelog", "document the API", "explain this module", or mentions documentation, summarization, or README updates.
file-search
Fast file and text search across the codebase. Use when you need to find files by name, search code by content, locate definitions, find usages/imports, or explore project structure. Triggers on "find file", "search for", "where is", "grep for", "locate", "find definition", "find usage", "search codebase", "find all references".
generate-images
Generate and edit images using Nano Banana (Google Gemini image generation). Use whenever Claude Code needs to create new images, edit existing images, generate icons, diagrams, mockups, or any visual content.
generate-prd
Generates Product Requirements Documents for new features through guided discovery. Use when starting a new feature, creating specifications, or when user needs help defining requirements with clarifying questions.
manage-slash-commands
Expert guidance for creating and managing Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration. This skill should be used when the user asks to "create a slash command", "add a command", "manage commands", "build a command", or mentions slash commands, custom commands, or command configuration.
ralph-convert-prd
Converts Product Requirements Documents into prd.json format for the Ralph autonomous agent system. Use when preparing PRDs for Ralph execution, breaking down features into atomic user stories, or when the user mentions Ralph, prd.json, or autonomous agent workflows.
pytest-best-practices
Expert guidance for writing high-quality pytest tests. Use when writing tests, setting up fixtures, parametrizing, mocking, or reviewing test code.
git
Git operations for committing, pushing, and opening PRs using gh CLI. Use when performing version control tasks. This skill should be used when the user asks to "commit", "push", "create a PR", "ship code", "git status", or mentions git workflow, version control, or pull requests.
ralph-orchestrator
Orchestrates the full Ralph autonomous agent pipeline from requirements gathering to execution. Use when building new features, platforms, or complex tasks that need structured development through spec-interview, PRD generation, and autonomous implementation.
spec-interview
Interviews users to build comprehensive project specifications. Use when starting a new project, feature, or when user needs help defining requirements through guided discovery.
1k-bundle-release
Bundle release workflow — checkout, prepare, pr, diff-check, audit, publish, sync.
1k-trade-swap-market
Navigate OneKey App Swap, Bridge, Limit, and Stock/Market flows. Use for token selection, quotes, review/build/send, providers, cold start, and history/status; use the Perps skill for Hyperliquid.
1k-patch-package-workflow
Create or regenerate patch-package patches, including resolutions failures and build-artifact verification.
1k-retrospective
>
1k-debug-logging
Add or clean temporary OneKey debug console logs with consistent prefixes and safe stringify. Excludes analytics and permanent server logs.
1k-architecture
OneKey monorepo architecture, project structure, package relationships, and import hierarchy rules.
1k-ui-snapshot-cache
UI snapshot cache (display-only, main-thread) + unified startup timing schema — cold-start reads from snapshot namespaces (MMKV on native, IndexedDB on web) and the cross-platform `[StartupTiming]` log taxonomy. Use when adding or debugging a UI snapshot / SWR cache, debugging startup performance regressions, analyzing cold start timeline, or comparing iOS vs Android startup phases. Triggers on: ui snapshot cache, SnapshotCache, swr cache, usePromiseResult cache, cold start, startup optimization, 启动时间, SSR hydration, Balance displayed regression, contextAtomBase, flushColdStartCache, __ONEKEY_CTX_ATOM_SNAPSHOT__, StartupTiming, main_host.did_start, bg_runner.start.
1k-group-think
Spawns a team of 3 AI agents with different analytical perspectives to collaboratively analyze a problem, propose solutions, and debate trade-offs. Use when facing bugs, design decisions, architecture choices, or any task that benefits from multiple viewpoints. Agents discuss with each other, then present a comparison table for the user to decide. Triggers on "group think", "multi-agent", "team analysis", "3 agents", "collaborative analysis", "debate solutions".
1k-app-upgrade-test
Create test versions to verify app auto-update functionality and version migration.
1k-i18n
OneKey i18n and Lokalise workflow for module copy, full-language translation create/update, bilingual previews, confirmed upload, pull, and verification. Never edit generated translations.
1k-feature-guides
Feature development guides for OneKey. Use when adding new chains, socket events, notifications, pages, or routes. Covers blockchain integration, WebSocket subscriptions, push notifications, and navigation patterns.
1k-cross-platform
OneKey cross-platform patterns, platform files, platformEnv, and supported OS/SDK requirements.
1k-pr-daily-report
Generate a 24-hour PR activity report grouped by module with Chinese summaries. Use when the user asks for PR statistics, daily report, PR summary, or mentions "PR 统计", "每日报告", "PR 汇总", "日报".
Page 761 of 1652 · 82582 results