66 个（danielmiessler 的仓库） · 按人气排序
Improve code, prompts, skills, or agent definitions through repeated changes and evaluation. Measure numerical targets such as latency or size, or use an LLM to judge pass-or-fail criteria, keeping changes that improve the result.
中文简介正在准备中。当前显示英语简介。
Examine articles, reports, or pasted text for bias in the data, the producing organization's interests, and the reporting. It seeks cited studies and returns a structured report separating supported findings from editorial interpretation.
中文简介正在准备中。当前显示英语简介。
Create and maintain LifeOS skills, from initial file structure to validation and effectiveness testing. Update workflows, improve instructions, and refine descriptions so skills activate for appropriate requests, while checking naming conventions and handling of personal data.
中文简介正在准备中。当前显示英语简介。
Explore one problem through several distinct perspectives to uncover hidden requirements and edge cases. Turn the findings into testable success criteria, refinements, and failure conditions, stopping when additional perspectives no longer produce new requirements.
中文简介正在准备中。当前显示英语简介。
Map sensitive data across the systems you manage, explore what a compromised asset could expose, and maintain a risk register. Record likelihood, impact, owners, mitigations, and review dates to support ongoing security planning.
中文简介正在准备中。当前显示英语简介。
Analyze a problem by separating fundamental facts from policies and untested assumptions. The skill produces a component breakdown, a constraint table, and a rebuilt solution, helping explain which inherited assumptions may be limiting the available options.
中文简介正在准备中。当前显示英语简介。
Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.
中文简介正在准备中。当前显示英语简介。
Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.
中文简介正在准备中。当前显示英语简介。
Use cmux on macOS to organize visible teams of AI agents, send prompts, inspect terminal output, and monitor completion. Set up role-based teams or have several agents investigate the same problem; live operation remains unproven in the supplied material.
中文简介正在准备中。当前显示英语简介。
Explore explanations for poorly understood phenomena through repeated hypothesis generation and selection. Compare causal mechanisms, test what happens when components change, and retain distinct candidates with predictions, rival comparisons, and clearly stated unresolved questions.
中文简介正在准备中。当前显示英语简介。
Evaluate AI agent outputs with code checks and model-based grading. Run repeated trials to measure reliability, compare prompts or models, and check whether changes reduce quality, with saved transcripts for reviewing the results.
中文简介正在准备中。当前显示英语简介。
Review stored LifeOS goals and personal context against available records such as sleep, app usage, work, and expenses. The skill prioritizes stale information and contradictions, proposes corrections for approval, and reviews the gap between current and ideal states.
中文简介正在准备中。当前显示英语简介。
Investigate incidents and recurring defects with structured methods such as Five Whys and Fishbone cause maps. Identify multiple contributing conditions, build a blame-free account of what happened, and propose practical changes to prevent similar failures.
中文简介正在准备中。当前显示英语简介。
Structure problem solving around clear goals, competing explanations, experiments, and measurable results. Use the cycle to diagnose bugs, validate features, compare prompts, or evaluate an early product, then choose the next step based on evidence.
中文简介正在准备中。当前显示英语简介。
Install LifeOS into an existing AI agent environment, then use a guided interview to capture current circumstances and goals for the Pulse dashboard. The skill also handles installation checks, updates, and removal.
中文简介正在准备中。当前显示英语简介。
Import existing notes and agent instructions into LifeOS by splitting content into sections and proposing destinations. Review uncertain classifications, approve selected groups, and retain source information alongside the imported material.
中文简介正在准备中。当前显示英语简介。
Turn an unclear idea into a specification with testable completion criteria. The skill supports discovery interviews, drafts from existing code, completeness checks, and records of decisions and verification in a shared project document.
中文简介正在准备中。当前显示英语简介。
Extract useful ideas from videos, podcasts, interviews, and articles, organized into sections tailored to the content. Choose from five depth levels, preserving surprising claims and, at fuller levels, getting essential takeaways and references to explore.
中文简介正在准备中。当前显示英语简介。
Create explainer clips, short videos, and animated overlays with React code. Define scenes and motion by frame number, then render an MP4 that can be regenerated after changes to the content, timing, or visual design.
中文简介正在准备中。当前显示英语简介。
Gather local news, building permits, elections, legislation, and other civic information for a configured US hometown. The skill combines available sources into a daily JSON digest that Pulse can display in its LOCAL tab.
中文简介正在准备中。当前显示英语简介。
Organize knowledge notes with links that explain their relationships, search saved information, review conflicting claims, and prepare weekly digests. Retrieve earlier work sessions and conversations by topic or date to recover context before continuing a task.
中文简介正在准备中。当前显示英语简介。
Operate Chrome or Brave using signed-in browser sessions to verify deployed pages, reproduce bugs, inspect page structure, and examine errors or network traffic. An optional macOS bridge extends control to native applications and operating system input.
中文简介正在准备中。当前显示英语简介。
Create and improve prompts for agents, workflows, and AI evaluations. Reusable Handlebars templates, which insert data into a fixed structure, help generate consistent instructions from YAML or JSON inputs for use in other tasks.
中文简介正在准备中。当前显示英语简介。
Clean spoken recordings by transcribing words, identifying filler and false starts, and joining cuts with short audio fades. Preview proposed edits, reduce breaths, repair noise-gate clicks, and optionally use Cleanvoice for additional cloud processing.
中文简介正在准备中。当前显示英语简介。