Skills

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

Analyze historical downtrend durations and generate interactive HTML histograms showing typical correction lengths by sector and market cap.

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.

Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.

Cross-agent task routing — Codex auto-review, Kimi delegation by complexity score (iCPG + Claude reasoning), iCPG + Mnemos mandatory for all agents

Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. Use this for conceptual explanation, onboarding, and background reading. Route operational work to the specialized skills: debugging attention failures goes to context-degradation, token-efficiency work goes to context-optimization, conversation summarization goes to context-compression, and project-shape decisions go to project-development.

Mobile (Android + iOS) application penetration testing methodology. Covers static analysis (apktool/jadx for Android, class-dump/Hopper/IDA for iOS), dynamic instrumentation with Frida and Objection, SSL pinning bypass strategies, root/jailbreak detection bypass, deep-link / URL-scheme abuse, exported component attacks (Android activities, services, providers, receivers; iOS XPC, URL schemes, universal links), insecure data storage (SharedPrefs, KeyStore misuse, NSUserDefaults, Keychain ACL bypass), IPC / Intent redirection, WebView vulnerabilities (JavaScriptInterface, file:// access), Firebase/AWS/Azure misconfiguration leakage, mobile API testing, biometric/Face ID/Touch ID bypass, app-cloning and runtime patching, and mobile malware/RAT analysis primitives. Use for mobile pentest, bug bounty mobile triage, or app-store reconnaissance.

How an agent should operate as one mind inside a shared Company Brain built on MemClaw — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a MemClaw-connected team or fleet and your work should build on, and feed back into, what the organization already knows; it sets the operating posture. For the mechanics of individual memclaw_* tools, see the companion "memclaw" skill.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

Run and interpret repo diagnostic scripts (ratchets, validators, token stats). Use when measuring health. Do not use to run tests; use night-market-operations.

Capture professional-quality remote interviews using double-ender technique and dedicated recording platforms for podcasts, media, and content production. Use when: Setting up remote podcast interviews with guests; Recording media interviews across distances; Creating customer interview content; Producing expert interviews for thought leadership; Conducting research interviews with high audio quality

>

Gmail: Reply-all to a message (handles threading automatically).

Screens all Hyperliquid perps and surfaces top trading setups

Use when auditing a page for E-E-A-T signals. The agent reads the page and scores Experience, Expertise, Authoritativeness, and Trustworthiness — then tells you exactly what to add to each dimension.

AI crawler access analysis. Checks robots.txt, meta tags, and HTTP headers to determine which AI crawlers can access the site. Provides a complete access map and recommendations for maximizing AI visibility while maintaining appropriate control.

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.

Research a library and create comprehensive documentation in .claude/docs/libraries/.

Configure, extend, debug, or contribute to PicoClaw itself. Use when the task is about PicoClaw CLI commands, config.json, gateway, auth, models, skills, MCP servers, cron, routing, sessions, self-evolution, built-in slash commands, or repository internals. Use PicoClaw-native workflows, terminology, paths, and configuration.

This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.

钉钉群聊与消息。Use when 用户提到 发消息/单聊/群聊/建群/拉人进群/改群名/搜索群/群成员管理/@消息/撤回消息/机器人群发/Webhook通知/发图片或文件到群。Distinct from dingtalk-ding(紧急DING消息/短信/电话)、dingtalk-mail(邮件)、dingtalk-edu-group(班级群)。命令前缀：dws chat。

Design a feature architecture by analyzing existing codebase patterns and conventions, then provide a comprehensive implementation blueprint with specific files to create or modify, component designs, data flows, and a build sequence. Use this skill when the user asks for an architecture design, an implementation plan for a non-trivial feature, or when dispatched as a sub-task during feature-dev architecture phase.

When the user wants to track App Store chart rank changes, find top gainers and losers, detect breakout apps entering the top 100, or identify apps dropping out of charts. Also use when the user mentions "chart movers", "rank changes", "who's rising", "who's falling", "new chart entries", "top gainers", or "market shifts". For broader market overview, see market-pulse. For competitive keyword analysis, see competitor-analysis.

Expert guidance for developing with the tinystruct Java framework. Use when working on the tinystruct codebase or any project built on tinystruct — including creating Application classes, @Action-mapped routes, unit tests, ActionRegistry, HTTP/CLI dual-mode handling, the built-in HTTP server, the event system, JSON with Builder/Builders, database persistence with AbstractData, POJO generation, Server-Sent Events (SSE), file uploads, and outbound HTTP networking.

分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。

Academic manuscript writing with IMRAD structure, citation formatting, and reporting guidelines. Use when drafting or revising research papers.

Mobile, tablet, and desktop are different interaction paradigms — not the same layout scaled up or down. Sections can be hidden, repositioned, or made sticky on mobile. Navigation and primary actions move. Use when designing responsive layouts, adapting desktop UI for mobile, or deciding what to show on each breakpoint.

When the user wants to plan or optimize paid user acquisition campaigns. Also use when the user mentions "Apple Search Ads", "user acquisition", "paid ads", "UA", "ad campaign", "install campaign", "Facebook ads for apps", "TikTok ads", or "cost per install". For organic growth, see aso-audit. For launch-specific UA, see app-launch.

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

>

Unified team skill for brainstorming team. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team brainstorm".

Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.

Use when working directly with the `esm` Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.

AWS Aurora Serverless v2, RDS Proxy, Data API, connection pooling

用于搜索中文社交平台，包括 B站视频、知乎问答、小红书笔记、微博帖子和抖音视频。部分平台需要 cookie 认证。

Transform weak resume bullets into achievement-focused statements with metrics and impact

Diagnose IJFW integration health per platform. Trigger: 'doctor', 'check setup', /doctor

>

Autonomous multi-round research review loop. Repeatedly reviews via external reviewer backend (Codex or manual), implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.

Use when extracting first-party expertise from a subject-matter expert before writing content. Produces a knowledge document of contrarian takes, specific examples, and surprising outcomes that AI can't fabricate.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs/downloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.

Use after a session to promote useful episodic notes from logs/episodic/ into distilled, dated entries in MEMORY.md and memory/semantic/.

Python video composition with moviepy 2.x — overlaying deterministic text on AI-generated video (LTX-2, SadTalker), compositing clips, single-file build.py video projects. Use when adding labels/captions/lower-thirds to LTX-2 or SadTalker outputs, building short ad-style spots in pure Python without Remotion, or doing programmatic video composition. Triggers include text overlay on video, label LTX-2 clip, caption SadTalker output, lower third, build.py video, moviepy, Python video composition, sub-30s ad spot.