Index brand photo library using AI vision. Use when: setting up assets, adding new photos, or refreshing the index.
Generates project-libs skill from all project dependencies automatically. Use when creating documentation skills for all libraries in a project, or when the user wants to set up…
Update or refresh an existing search collection when source files have changed. Re-reads documents from their original source, re-chunks changed content, and rebuilds the FAISS…
Use when the human references a GitHub issue, pastes an issue link, or says fix issue N. Full resolution pipeline with diagnosis, planning, skeptical review, implementation, and…
Four-stage pipeline that takes a corpus of seed content (your existing notes), clusters by semantic similarity, proposes a vault taxonomy via LLM, renders a user-reviewable import…
Configure kgateway v2.0+ as L1 and Bifrost v1.x or LiteLLM v1.60+ as L2 for a 2-Tier Inference Gateway on EKS.
Checks for information leakage across module boundaries. Use when the user asks to check information hiding, when modules seem to change together, when implementation details leak…
Ingest a source into an LLM Wiki vault. Detects source type (URL, PDF, YouTube, tweet, gist, text, session), extracts content, creates wiki pages, updates index and log.
Use when user wants to ingest a development-skills feedback report and apply fixes, or runs /ingest-feedback.
Pulls recent activity (merged PRs, issues, commits) from a GitHub repository into the vault as queryable markdown.
Load a shared context-handoff from a URL (handoff service link, gist, paste.rs, or any link to a handoff markdown doc) and resume the work it describes.
Pulls recent pages or database entries from Notion into the vault as queryable markdown. Use when the user says /ingest-notion [--depth N], or asks to ingest,…
Analyze an uploaded image (screenshot of a design, website, app) and extract design tokens to use as a starting point.
Configure this machine for AI Session Tracker. Sets up hooks-based tracking for Claude Code or Copilot CLI with certificate or user authentication.
Start the Vibe Innovation Framework. Runs entry diagnostic, session planning, ICD initialization, and phase dispatch from the user's current uncertainty level (TRL -2 to 4).
Manage the Innovation Canvas Document (ICD). Initialize, validate against the JSON schema, render a Markdown view, diff against a previous version, or save.
Run a specific phase (0 through 5) of the Vibe Innovation Framework. Reads the current ICD, executes the full phase prompt, writes the structured output back to the ICD.
Request clarification when input is ambiguous. Use when user request has missing parameters, conflicting interpretations, or insufficient constraints for reliable execution.
Use this skill when inserting urgent work as a decimal phase between existing phases, adding mid-milestone work, or creating intermediate phases.
洞察生成 — 从业务/财务数据中提取洞察，识别模式、异常和机会， 转化为可落地的业务建议。 适用情形：用户要求"生成洞察"、"提炼 insights"、"从数据中找机会"时执行。 核心：数据模式识别 + 置信度评估 + 洞察到建议的转化链路。
洞察验证 — 验证已生成洞察的数据准确性、逻辑合理性和业务可操作性， 确保洞察质量并分级管理。 适用情形：洞察生成后进行验证，或用户要求"验证洞察"、"核实 insights"时执行。 核心：数据核实 + 逻辑检验 + 可操作性评估。
Skill de FALLBACK pra configurar o MCP server do FIN App. A partir da v0.2.0, o plugin já declara o fin-app-mcp via .mcp.json e pede a API key automaticamente no install…
Configure and customize skills for your workspace by asking questions and updating skill files with your preferences.
Build a BenAI-branded HTML page in the neo-brutalist instant-ui design language (cream background, near-black ink, 3px hard borders, 6px zero-blur shadows, a blue/green/amber…
Cluster related instincts by trigger family and lexical similarity, identify skill-creation candidates
Extract instincts from the current session — corrections, confirmations, and tool-usage patterns
Score existing instincts, execute status transitions, prune stale candidates, write scorecard
Review, promote, or remove learned instincts extracted from past sessions (`.claude/instincts/*.md`).
Создание новой инструкции (standard/validation/create/modify) с frontmatter, секциями и регистрацией в README. Используй при добавлении нового процесса, стандарта или воркфлоу.
Обновление содержания, деактивация или миграция инструкции. Используй при изменении процесса, переименовании файла, обновлении standard-version или выводе инструкции из…
Use when: auditing AI instruction artifacts, prompts, prompt templates, LLM task prompts, agent instructions, skill files, SKILL.md artifacts, prompt-packaged workflows, custom…
Проверка инструкции на соответствие стандарту — frontmatter, обязательные секции, ссылки, чек-лист. Используй после создания или изменения инструкции, при code review или перед…
分析insurance license advisor相关互联网金融合规问题。 覆盖：监管框架、资质要求、合规要点、违规风险。 适用情形：用户提及insurance license advisor相关事项。
Analyzes the user's business problem and recommends the right backend integration approach — Web API, Server Logic, Cloud Flows, or a combination — for a Power Pages site, then…
Manage codemap integration — 'check' audits installation health (scan-query reachable, index fresh, injection present), 'init' onboards codemap by discovering skills/agents,…
Publish or fetch learned patterns across projects via IPFS (Pinata) -- the cross-project pattern transfer that hooks_transfer enables
AUTO-TRIGGER: Apply this skill when the user is working with intent data signals from ZoomInfo, Bombora, G2, 6sense, Demandbase, or any similar platform, and needs to…
Check and manage drug interactions including drug-drug, drug-disease, drug-dosage, and drug-food interactions with 5-level severity classification.
内部往来核算管理主流程 — 整合对账 + 转让定价 + 关联担保的综合管理。 适用情形：月末/季末关联交易管理报告时执行，整合 intercompany-reconciliation、 transfer-pricing-review 和 intercompany-guarantee-review，输出完整的关联交易管理报告。 核心：往来清晰 → 定价公允…
关联担保审核 — 核查 [ERP] 关联担保余额是否超限，评估被担保方财务风险。 适用情形：关联担保审核时执行，从 [ERP]/[CASH] 获取担保数据， 核查担保余额/担保比例/到期情况，评估担保风险，输出审核报告。 核心：担保余额核查 + 超限检查 + 被担保方风险 + 到期预警。
内部往来对账 — 核查 [ERP] 母公司与子公司往来余额一致性，识别差异并处理。 适用情形：月末内部往来对账时执行，从 [ERP] 获取双方账面数据， 核查往来余额是否一致，识别未达账项，输出对账报告。 核心：余额核对 + 差异识别 + 未达账处理 + 调平确认。
Use when: designing or auditing the contract of a boundary before implementation: API, service interface, module boundary, message schema, or webhook — operations, inputs and…
Interface Craft by Josh Puckett — a toolkit for building polished, animated interfaces in React. Includes Storyboard Animation (human-readable animation DSL with stage-driven…
Use when the user asks to reflect on recent sessions, analyze repeated mistakes, or review prompting and agent patterns for improvement.
内部审计管理主流程 — 整合年度审计计划/专项审计/审计发现整改全流程。 适用情形：审计总监/审计经理制定年度审计计划、启动专项审计、 管理审计发现整改时执行，整合 annual-audit-planning、 process-compliance-audit、audit-finding-tracking 和 fraud-investigation，…
Build an internal link plan from a sitemap or URL list — producing a hub-and-spoke topology, authority scores, and a prioritised link-recommendation table.
Interrogate code changes to surface decisions, alternatives, and confidence levels. Use when user asks to "interrogate", "what decisions", "hardest part", "alternatives", or wants…
Interview user to clarify any topic - exploring codebase, investigating issues, planning features, understanding requirements, or drilling into plans.
Create structured candidate assessment scorecards and competency interviews tailored for Indonesian workplaces.
Deep-dive spec interviewer. Reads a file or requirement, analyzes it against the codebase, then conducts a rigorous 1-on-1 interview using AskUserQuestion to produce a…
Extract structured insights from a qualitative interview or user test session. Creates interview snapshots following the Continuous Discovery Habits methodology.
Structure a raw invention idea into a formal invention disclosure. Use when user says \"构建发明\", \"structure invention\", \"发明构建\", \"invention disclosure\", or wants to formalize…
A股 ETF 结构化研究 — 指数估值/折溢价/AUM/跟踪质量/对冲覆盖，产出带来源追溯的研究备忘录。研究工具，非决策工具。共用数据层供 invest-a-journal ETF 路径调用。触发词：ETF/指数基金
交易日志 v2 — Claude 驱动四维评估（逻辑/盲点/仓位匹配/风险收益）+ 数据引擎；ETF 路径调用 invest-a-etf 共用模块。研究工具，非决策工具。触发词：交易日志/买入/卖出评估
A股多因子交叉验证的结构化投研助手 — 数据采集 + 学术级引用，产出带来源追溯的 Markdown 研究备忘录。研究工具，非决策工具。触发词：个股投研/估值/财报
Investigate a GitHub issue - fetch info, update labels, analyze code/reproduce, report findings, and optionally fix. Usage: /investigate-issue
Master orchestration — full end-to-end investigation of an unknown module using all ARC Probe capabilities together (strings, RTTI, functions, xrefs, structs, bookmarks, GUI…
投资合规检查 — 对投资决策和执行进行合规检查，确保投资符合公司投资政策、 监管要求和董事会授权。 适用情形：重大投资决策前、项目执行中，或用户要求"检查投资合规"时执行。 核心：政策核对 + 授权检查 + 风险合规 + 审批流程。
投资决策报告生成 — 整合 DCF 估值结果、敏感性分析、 战略价值评估和可比参照，生成结构化的投资决策包， 提交 CFO/IC/董事会审批。 适用情形：完成 npv-irr-calculation、real-options-analysis 和 comparable-company-internal 后，汇总生成正式审批文件。
投资项目评估 — 对潜在投资项目进行全面评估，包括财务回报测算、 风险分析和战略契合度分析，支持投资决策。 适用情形：资本支出预算编制前、项目审批前，或用户要求"评估投资项目"时执行。 核心：财务测算 + 风险分析 + 战略对齐 + 优先级排序。