Explore

Generate an ATS-optimized resume tailored to a specific job posting. Creates clean HTML you can print to PDF. Works for any industry. Use when someone says 'tailor my resume', 'make me a resume', 'create a resume for', or 'update my resume for'.

See all available career-ops skills, what they do, and which one to use next based on where you are in your job search. Use when someone says 'help', 'what can you do', 'how does this work', or seems unsure what to do next.

Evaluate how well a job posting matches your background. Paste a JD or URL and get an honest A-F scored assessment with match analysis, compensation research, positioning strategy, and interview prep. Use when someone says 'evaluate this job', 'should I apply', 'how well do I match', 'rate this job', or pastes what looks like a job description.

Compare multiple job opportunities side by side. See scores, compensation, pros/cons, and a recommendation. Use when someone says 'compare my options', 'which job should I take', 'rank my opportunities', or 'compare these roles'.

Help fill out a job application form. Generates personalized answers for every field using your profile and evaluation. Never auto-submits. Use when someone says 'help me apply', 'fill out this application', or 'application for'.

Use when the user needs a GEO-friendly page blueprint for a specific product, topic, article, ranking, comparison, FAQ, knowledge-base, or case page, especially when the work must become implementable page structure rather than only copywriting.

Diagnose a website page or small page set for GEO readiness with authoritative public evidence, systematic page analysis, code/content/schema fixes, and four-format Chinese report delivery.

Use when a user asks for GEO 意图拓词、AI 搜索意图挖掘、AI 搜索问题集、问题簇、追问链路、查询重写、内容选题库、FAQ 题库、监测 Prompt 库, or AI Intent Miner.

当用户需要把 GEO 全景诊断、机会地图、AI 平台采样结论或品牌事实底座转成 30/60/90 天综合实施方案时使用，输出页面技术、内容矩阵、标题体系、知识库、外部证据、监测闭环、角色分工、验收指标和四格式报告；覆盖 DeepSeek、豆包、千问、Kimi、元宝；不用于从零做全景采样诊断或只写单篇内容。

通过抖音网页版搜索框采集下拉联想词，按词根→一级词→二级词扩展，逐词截图留证、记录位置与来源路径，按行业转化目标评商业价值并导出Excel采集包。用于抖音相关搜索词抓取、下拉词拓展与两层词库；视频内容、评论、账号、热榜和小红书采集另行路由。

当用户需要把已有 SEO 文章、公众号文章、官网文章、白皮书或产品页文案改造成 GEO 友好、AI 可引用、可核验、可扫描的内容时使用；输出原文 GEO 评分、改造版文章、改造前后差异、原子事实卡、FAQ、语义补强、真实数据获取与核验计划、证据缺口和 CMS 发布版 HTML 建议，并交付 Word、PDF、HTML、Markdown 四格式报告。

当用户需要生成 GEO 品牌对比内容、品牌替代方案、选型页、竞品对比页、FAQ 对比问答或“某品牌和其他方案怎么选”的内容包时使用，面向 DeepSeek、豆包、千问、Kimi、腾讯元宝生成中文简体、证据绑定、同口径、公平表达的品牌对比报告，并默认交付 Word、PDF、HTML、Markdown 四格式。

当用户需要把企业资料、官网、产品、客户案例、人物、地点、证据源和场景词整理成品牌实体知识图谱时使用；用于知识库升级、页面结构设计、监测纠偏、品牌百科化和 AI 内容一致性治理。

用浏览器逐个检索百度目标关键词，截图采集搜索框联想词与结果页底部“相关搜索”，按所属行业和转化目标给相关词评 1–10 分商业价值，生成带截图出处的 Excel。适用于百度关键词拓展、相关搜索词截图留证和行业化关键词评分；仅查普通搜索结果、热搜榜、指数或排名时不触发。

Use when a user needs repeated Doubao AI-search collection from web or Android Appium into compatible JSON plus Markdown/Excel/HTML GEO reports. Requires keywords/questions and repeat count; target entity/type are required only for target-vs-competitor diagnosis. Not for generic scraping, Doubao API chat, hidden API extraction, SEO writing, high-frequency automation, or one-off answers.

Use when a user provides ChatGPT web AI-search keywords, repeat count, target entity, entity type, OpenCLI profile, and crawl interval preference, then needs repeated crawls aggregated into JSON plus a Kami HTML GEO report. Not for generic crawling, ChatGPT API chat, SEO writing, or one-off answers.

Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draft_content.json, draft_info.json, or cutting videos — in English or Chinese (剪映, 字幕, 草稿, 剪辑, 切片, 视频编辑).

Search and recommend public DeepSeek Harness plugins when the user describes a capability they need, asks which plugin can perform a task, or wants popular alternatives before installing anything.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Prove model-disabled skills stay outside the model catalog.

Exercise project skill discovery and loading in snapshot tests.

Prove user-disabled skills remain available to the model.

把已经讨论清楚的产品需求综合为本地可追踪规格，不重新访谈用户，也不依赖外部 Issue 系统。

通过用户可观察的公开 seam 严格执行一个失败测试、最小实现、同一测试转绿的纵向开发循环。

在开发前用决策树逐轮澄清产品方向、用户选择和范围边界，直到双方确认共同理解。

Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.

Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider, then define, run, repair, or roll back the Plugin.

Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.

Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.

Use when writing, reviewing, restoring, trimming, or auditing prose in the deepseek-harness repo, including deciding where documentation or comments are required across Markdown, JSDoc, code and test comments, prompts, descriptions, diagnostics, and CLI or UI strings.

Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository suite.

Use when landing a stack of dependent GitHub PRs (A ← B ← C, where each bases on the one below) onto master, merging a PR whose base is another open PR's branch, or whenever a request mentions "stacked PRs", "PR stack", "dependent PRs", or merging several related PRs in sequence. Requires every same-repository dependency chain to use GitHub's official stacked-PR feature before landing so GitHub owns stack-wide rules, CI, ordering, retargeting, and merge state.

Use when working in the deepseek-harness repo to find non-obvious simplification candidates, write proposed Agent Notes or inline TODO/FIXME/XXX notes, audit or coalesce superseded Agent Notes, or fold worthwhile simplification ideas from another PR; especially for dead, duplicated, speculative, over-built, added-then-removed, or hand-rolled-where-a-dependency-exists surfaces.

Use when writing, moving, reviewing, or auditing documentation in the deepseek-harness repo — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a verify-doc-budgets failure, or requests like "improve the docs", "audit the docs", "where should this be documented", or "this doc is too long".

Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content changes.

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.

Use when the user wants to translate paper markdown, full papers, or batches into another language while preserving formulas, code blocks, and images.

Use when the user wants to install, configure, diagnose, or troubleshoot ScholarAIO, including setup check, dependency status, API keys, and bilingual setup flow.

Use when the user wants to find academic papers, search the local library, run keyword or semantic search, search by author, explore topics, or federate across library, explore databases, and arXiv.

Use when the user wants USPTO patent discovery, patent metadata lookup, application lookup, or downloadable patent candidates before ingest.

Use when the user wants to draft a literature review, survey a research area, summarize a field, organize workspace papers, identify gaps, or export review references.

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.

Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations.

Create or revise runnable Deer Workflow orchestration modules from a user's task description. Use this skill whenever the user asks to turn a repeatable multi-step task into a Workflow, generate a deer-workflow script, coordinate several Agent Loops with parallel or pipeline, or repair a Workflow that assumes APIs are globally injected.

Start a VibeAround Preview for either a running local web server or a Markdown file. Use after starting a dev server, after creating or updating Markdown, or when the user asks to preview a browsable artifact. Only available when the VibeAround MCP server is connected.

Drive a single workshop ticket through the inner SWE↔Tester loop. Resolves the ticket from `implement_yourself/tasks/`, creates an `implementing/from-scratch` branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), launches the software-engineer agent to implement it, then routes by archetype — Tester runs on logic tickets, orchestrator spot-checks the SWE's AC walk on glue/bootstrap tickets, fast-path file existence check on docs tickets (Tester HARD-OFF). Loops on FAIL up to 3 times, moves the file to `tasks/done/`, then commits directly with `git commit -m`. Stops after one ticket — the human reviews the commit, talks through it, then re-invokes for the next ticket. Trigger when the user types `/implement`, asks to "implement task NNN", says "pick up the next ticket", or otherwise wants to ship one workshop ticket under supervision.

Run deep research on any topic using the Deep Research MCP server. Use this skill whenever the user wants to research a topic, gather information, find sources, or create a research document. Triggers on: 'research this', 'find out about', 'gather information on', 'I need to understand', 'deep dive into', or any request that involves investigating a topic.

Conducts comprehensive web research, synthesizes data from multiple sources, and produces detailed reports.

Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.

Quick-score your pipeline of scan results. Ranks every role in your pipeline by fit and recommends which ones deserve a full evaluation. Use when someone says 'triage my pipeline', 'which scanned jobs should I apply to', 'rank my pipeline', or 'process my scan results'.

Scan company career pages for job openings that match your profile. Uses web search with site-scoped queries to find listings on Greenhouse, Lever, Ashby, SmartRecruiters, and other ATS platforms. Use when someone says 'scan for jobs', 'check careers page', 'find openings at', or 'search for roles'.

Research a company before applying or interviewing. Get an intelligence brief with culture, financials, recent news, team structure, key contacts, and smart interview questions. Use when someone says 'research this company', 'tell me about', 'what do you know about', or 'prep me for my interview at'.

Draft personalized outreach messages for LinkedIn connections, hiring managers, or recruiters. Creates targeted messages using a hook + proof + proposal structure. Under 300 characters for connection requests. Use when someone says 'draft outreach', 'message the recruiter', 'reach out to', or 'write a LinkedIn message'.

Predict RNA secondary structure, MFE folding, base-pair probabilities, RNA-RNA interactions via ViennaRNA Python bindings. Pipeline: sequence → MFE → partition function and pair-probability matrix → dot-bracket → duplex. Use for siRNA/sgRNA targeting, ribozyme design, RNA accessibility. Use RNAfold CLI for batch use without Python.

PyTorch Geometric (PyG) for graph neural networks: node/graph classification, link prediction with GCN, GAT, GraphSAGE, GIN. Message passing, mini-batches, heterogeneous graphs, neighbor sampling, explainability. Supports molecules (QM9, MoleculeNet), social/knowledge graphs, 3D point clouds. For non-graph DL use PyTorch; for classical graph algorithms use NetworkX.

Splice-aware RNA-seq aligner producing sorted BAM and splice junction tables. Builds genome index, runs two-pass alignment for better junctions. Outputs sorted BAM, junctions (SJ.out.tab), stats (Log.final.out), optional gene counts. Use Salmon for fast pseudoalignment; STAR when a BAM is needed for variant calling, IGV, or ENCODE pipelines.

Unified Python framework for extracellular electrophysiology. Load 20+ formats (SpikeGLX, OpenEphys, NWB, Intan, Maxwell, Blackrock), preprocess, run 10+ sorters (Kilosort4, SpykingCircus2, Tridesclous, MountainSort5) via one API, compute quality metrics (SNR, ISI, firing rate), compare sorters, export NWB/Phy. For format-agnostic multi-sorter workflows. For Neuropixels-specific PSTH/decoding use neuropixels.

Annotate and filter VCF variants with SnpEff and SnpSift. SnpEff predicts functional effects (HIGH/MODERATE/LOW/MODIFIER), genes, transcripts, AA changes, HGVS; SnpSift filters and adds ClinVar/dbSNP. Java CLI with Python subprocess integration. Use ANNOVAR for multi-database annotation; Ensembl VEP for REST API; SnpEff for fast CLI with pre-built genomes.