Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review".

Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly, skill, workflow, run skill, create skill, automation, pipeline. Requires: @refly/cli installed and authenticated.

Regenerate Python + TypeScript gRPC stubs after editing proto files. Use when proto/*.proto changes, imports from bindu.grpc.generated fail, CI reports generated-code drift, or HandleMessages calls fail with proto mismatch.

当用户想复盘或升级已启用的 sales-cs 时使用。扫描 sales-cs 的 feedback/ 聚合客户 反馈，结合用户意见提出升级建议（调整 MEMORY 客服手册 / 话术 / IDENTITY 称呼 / DECLARED_SKILLS 等），确认后由 main agent 直接改 sales-cs workspace 文件。 sales-cs 是对外 crew，不自行升级，所有调整经本技能由 main agent 落地。

国家趋势与顺势而为分析助手。围绕国家最新五年规划、重大政策文件与近期重大新闻，做"势—道—术"三层推演，面向投资、创业方向、商业思路、产品思路、就业择业、学习规划六大场景输出图文并茂的分析报告。Use this skill when the user asks to "分析国家政策"、"顺着国家走"、"势头上赚钱"、"五年规划解读"、"国家趋势分析"、"顺势而为"、"国势分析"、"国家导向分析"、"国家战略解读"、"政策红利分析"、"产业政策机会"、或任何希望结合国家政策与趋势做投资/创业/职业/学习决策的场景。默认聚焦中国（可配置为其他国家），输入用户特点（擅长的领域、特长、爱好等），未输入则按普通人处理，输出 markdown 报告到当前项目的 markdown 目录，图文并茂。

Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication, authorization, rate-limit, and CI/CD testing.

Search watched registries for community legal skills, showing matches with descriptions and offering to show the full SKILL.md before install. Use when the user says "browse", "search skills", "find a skill for", "what's out there for", or wants to add a new registry to the watchlist.

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit the fold.

Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions. Use for think this through, deep think, architecture review, postmortem, tradeoff analysis, or challenges to assumptions. This is a reasoning review, not a deterministic vault health check or repair workflow.

Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find everything about, research and file, go research, build a wiki on.

Use this skill whenever editing `*.rs` files in the `rust/` SDK in order to write idiomatic, efficient, well-structured Rust code

Investigate and fix model conversion issues in OpenVINO Frontends (ONNX, PyTorch) — triage, debugging, accuracy comparison, and pre-submission verification.

IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida_* modules (50+), idautils iterators, and common patterns.

Use only when a focused Sales workflow has selected a connected HubSpot CRM, or the user explicitly asks for HubSpot guidance, reads, drafts, notes, or reviewed record changes. Do not use when another CRM is authoritative.

Use this skill whenever a PDF file is being produced, opened, transformed, filled, or read. That includes: extracting text or tables from an existing PDF; combining, carving, rotating, cropping, or watermarking pages; composing a fresh PDF (report, invoice, certificate); filling AcroForm fields or overlaying text onto a non-fillable scanned form; encrypting or unlocking a PDF; running OCR over a scanned document; rendering pages to PNG/JPEG for visual analysis. Trigger on mentions of 'PDF', a filename ending in .pdf, requests like 'turn this into a PDF report', or references to AcroForm / form fields.

Route broad Data Analytics requests to the appropriate quantitative analysis, visualization, dashboard, report, notebook, KPI, market-sizing, validation, or semantic-layer workflow.

Design, build, verify, and publish production-grade TypeScript SDKs as npm packages inside a pnpm monorepo. Covers workspace layout, public API and module boundaries, plugin extension points, branded types and library-tuned tsconfig, tsdown bundling (vs tsup/tsc-only/unbuild), package.json exports with dual ESM+CJS and isomorphic conditions (browser/workers/RN/deno), Turborepo pipelines, publint and @arethetypeswrong/cli verification, changesets pre-release mode, npm dist-tags (latest/next/beta/rc/canary), and the alpha→beta→rc→stable release lifecycle. Triggers on: build a TS SDK, extract core library, package.json exports, dual ESM CJS, tsdown config, tsup vs tsdown, publint, attw, changesets prerelease, npm dist-tag, beta to rc, canary release, pnpm workspace SDK, isomorphic SDK, tsconfig library, npm provenance, shipping a TypeScript library.

Generate personalized music playlists by analyzing the user's music taste and generation feedback history. Triggers on any request involving playlist generation, music taste profiling, or personalized music recommendations. Supports multilingual triggers — match equivalent phrases in any language.

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax API resources from the terminal.

Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.