AI & ML

zpankz Bundle

BAIME-aligned refactoring protocol for Go hotspots (CLIs, services, MCP tooling) with automated metrics (e.g., metrics-cli, metrics-mcp) and documentation.

modbender Skill

Performs comprehensive due diligence on a cryptocurrency using CoinMarketCap MCP data. Use when users ask about a specific coin beyond just its price. This includes questions like "what is [coin]", "is [coin] legit", "analyze [coin]", tokenomics questions, holder distribution, or any request for deep information about a single cryptocurrency. Trigger: "research [coin]", "tell me about [coin]", "should I invest in [coin]", "DYOR [coin]", "is [coin] safe", "/crypto-research"

modbender Bundle

Lead Processing Agent

modbender Bundle

DEPRECATED — duplicate listing. Please use the canonical "openclaw-agent-optimize" skill instead.

modbender Skill

AI绘画提示词优化器 | 智能优化Midjourney/SD/DALL-E提示词。支持风格转换、批量生成。

modbender Bundle

s GPT, DALL-E, Stable Diffusion, Anthropic

modbender Bundle

!Version !Kite AI !Telegram

teng-bio Skill

USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.

modbender Bundle

Inter-Agent Communication Skill (OWASP ASI07)

modbender Skill

Human-Agent Trust Exploitation Skill (OWASP ASI09)

modbender Bundle

s create a conversational system that

teng-bio Bundle

Automatically orchestrates web search, raw web context, and deep research for requests to search, 查资料, 搜资料, 深度搜索, 调研, 文献综述, 找论文/资料/来源, look up, research, gather sources, compare current tools, or verify online claims. Use when the user asks for search/research without naming a specific search skill; it routes only through Brave spellcheck, autosuggest, web search, LLM context, and local report orchestration. 中文追加触发词：寻找参考文献、搜索文献、查参考文献、找相关论文、找几篇论文、文献搜索、论文搜索、参考文献怎么找、根据文献找来源。

modbender Bundle

System Prompt Leakage Test Skill

modbender Skill

Automates periodic Gmail management using OpenClaw cron jobs and heartbeat with gog CLI. Sets up scheduled email checks, spam cleanup, priority alerts, and weekly reports. Use when the user wants to automate email checking, set up recurring tasks, or run the email agent periodically in the background.

teng-bio Bundle

General repository-local research/project harness under `.project_os/` and first router for long-running, multi-step projects across domains. Use for research-project-os, project harness, 项目骨架, 通用项目工作台, 开工, 继续项目, 继续当前任务, 继续下一步, 大项目, 长期项目, 逐步推进, 当前进展, 恢复上下文, 制定计划, 拆解任务, plan out, break down, organize multi-step work, task_plan.md, findings.md, progress.md, 开始分析, 先跑, 先画, 绘图, 画图, 生成结果, 开始运行, 记录结果, 当前结果, run provenance, RESULTS_INDEX, DATA_ASSETS, current_task, result promotion, release workflow, 外置数据, 恢复检查. In any `.project_os/` project, also use before domain commands such as 系统发育, 发育树, 进化树, Newick, FASTA比对, PHYLIP, Nexus, alignment/tree/parsimony/treeness/RCV, ortholog, 同源基因, 分子进化, bootstrap, model training, 深度学习, R绘图, Python分析, and before 项目状态/写一个项目状态文档/更新项目状态文档/总结项目状态/记录当前项目进度/项目文档太大/拆分项目文档; establishes branch/task/run/result/assets first.

teng-bio Bundle

Narrow helper skill for README-first AI repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration. 中文触发词：论文代码仓库、复现仓库、README扫描、复现计划、仓库结构、推理/评估/训练命令提取、最小可信复现计划。

teng-bio Bundle

Trusted-lane execution and reporting skill for README-first AI repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, or end-to-end orchestration by itself.

modbender Skill

Smart LLM router — save 78% on inference costs. Routes every request to the cheapest capable model across 30+ models from OpenAI, Anthropic, Google, DeepSeek, and xAI.

modbender Bundle

Cut API costs 40-60% with intelligent model routing. Auto-routes simple tasks to cheaper models.

chrisblattman Bundle

Turn a rough request into a clear, structured prompt, show it, then run it. Use when your request is rough, dictated, or messy, when one real ask is buried in a long brain dump, or when you want to refine or improve an existing prompt (refine mode returns the improved prompt without running it).

teng-bio Bundle

Optional narrow helper skill for README-first AI repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.

finchipaiorg Skill

Multi-state privacy obligation extraction memos fail when the agent does not apply each statute's applicability threshold to the company's actual profile before extracting obligations and does not differentiate between obligations that are unique to one state and those that are shared across states.

teng-bio Bundle

Create, critique, or redesign high-quality scientific explanatory schematics for paper notes, project technical-route notes, mechanism/principle diagrams, graphical abstracts, Obsidian/PPT reading aids, and source Figure/Table explanations. Use when users ask to make, explain, judge, improve, redraw, or replace scientific schematics; decide whether to self-draw versus use original paper figures; or mention 技术路线图, 技术机制图, 机制图, 原理图, 技术原理说明图, 流程图, 工作流图, 方法路线图, 项目路线图, 研究框架图, 模型架构图, 证据链图, 混杂控制图, 补充图, 一图流, 图解, 示意图, 配图, 论文Figure讲解, 原文图讲解, Figure/Table拆解, 关键原文图插入, 重要图表讲解, 插图太丑/不好看, 重画/美化插图, 绘图质量, graphical abstract, workflow schematic, mechanism diagram, model architecture figure, figure quality. Prioritizes high-value original Figure/Table insertion and explanation, visual hierarchy, evidence boundaries, and optional-only schematics.

domenicrosati Bundle

Use when submitting, monitoring, throttling, or debugging jobs on a Slurm HPC/GPU cluster — writing sbatch scripts, requesting GPUs (whole, MIG fraction, or shard), array job throttling, email alerts, partitions, QoS, fairshare, logging, scancel/scontrol control, smoke tests with salloc/srun/--test-only, and agent-driven monitoring loops.

finchipaiorg Skill

Agents producing a buyer-side SPA markup for an insurance company acquisition should flag primary deviations and insurance-company-specific structural issues, including dividend covenant restrictions, managing general agent concentration risk, representation and warranty insurance cooperation clauses, and regulatory examination exposure.

finchipaiorg Skill

Cross-border data transfer agreement markups for clinical trial data fail when the agent applies generic negotiation positions rather than integrating the organisation's playbook, the applicable commercial agreement context, the due-diligence summary, and the internal email escalation positions into a coherent redline.

finchipaiorg Skill

Guides preparation of a buyer-side issues list for a draft escrow agreement, requiring cross-reference of each provision against the related acquisition agreement, flagging timing misalignments, claims deadline inconsistencies, governing law conflicts, and absent successor escrow agent provisions.

finchipaiorg Skill

Review fund formation materials including governing fund documents, offering materials, side letters, a fee workbook, a waterfall model, a prior-fund term sheet, and an investor commitment schedule to produce a full fund economics analysis covering consistency checks, side-letter economics, MFN cascade impact modeling, prior-fund comparison, and model error identification.

finchipaiorg Skill

Draft a beneficiary-oriented source code escrow agreement and a negotiation issues memo for a software-as-a-service license transaction, using the escrow agent's template and the deal documents as inputs.

finchipaiorg Skill

Redlining analysis loses discipline when the agent skips playbook hierarchy and fails to anchor each deviation to the governing transfer mechanism and transfer impact findings.

finchipaiorg Skill

Privacy policy updates for AI-powered health tools fail when the agent does not ground new disclosures in the product description and the privacy impact assessment, and does not separately memo the legal risks arising from the new product's data uses.

finchipaiorg Skill

External privacy notice drafts for digital health platforms fail when the agent does not anchor the notice's disclosures in the current data processing inventory and does not address additional jurisdiction-specific expansion and AI product integration obligations as distinct disclosure workstreams.

finchipaiorg Skill

Cross-border vendor transfer triage fails when the agent does not use the inventory baseline provided in the task materials, does not verify claimed transfer mechanisms against independent confirmation materials, and does not assess each vendor relationship against the transfer destinations and data categories evidenced by the record.

finchipaiorg Skill

Drafting an advance health care directive for a client with diminishing capacity requires reconciling potentially inconsistent agent designations across source materials, translating abstract treatment preferences into actionable clinical standards, and addressing companion document requirements and professional responsibility concerns.

finchipaiorg Skill

Privileged anti-corruption gap analysis for a newly acquired subsidiary's regional sales practices, assessing exposure across third-party agent relationships, gift and hospitality expenditures, government official hiring, and books-and-records compliance.

finchipaiorg Skill

GDPR enforcement guidance executive briefs fail when the agent summarizes the guidance generically rather than filtering its implications through the company's specific processing activities and compliance tracker to produce actionable, company-specific takeaways for cross-functional leadership.