Official · CodexFreeSummary Review completed code changes against the original requirements, choosing review depth by behavioral risk. Coordinate independent reviewers, resolve actionable findings, and verify that the delivered changes match the content actually reviewed.
- Review completed changes before final verification
- Choose review depth based on behavioral risk
- Re-review fixes after actionable findings
openai/openai-agents-python☆ 30.2KUpdated Oct 20, 2026
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.
- Extract key insights from a YouTube interview
- Review a podcast at a chosen level of detail
- Organize useful ideas from an article
danielmiessler/LifeOS☆ 19.5KUpdated Sep 4, 2026
Compare a component's own design needs with the goals of the larger system through three structured passes. The result identifies conflicts, recommends an appropriate scope, and assesses whether the proposed design fits the whole.
- Choosing between a service, a library, and inline code
- Comparing feature requests with product goals
- Checking how new components fit an existing system
danielmiessler/LifeOS☆ 19.5KUpdated Sep 4, 2026
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.
- Finding overlooked requirements before starting work
- Reviewing a problem from stakeholders' perspectives
- Exploring failure modes and changes over time
danielmiessler/LifeOS☆ 19.5KUpdated Sep 4, 2026
Answer questions using a selected Obsidian vault, a collection of linked notes, without changing its files. Choose a search depth and receive answers with page references, clearly identified uncertainty, conflicting evidence, and any missing information.
- Find an answer in stored Obsidian notes
- Summarize knowledge in a vault
- Compare conflicting notes and their evidence
AgriciDaniel/claude-obsidian☆ 15.7KUpdated Oct 19, 2026
Places cameras, lidar, and other sensors in a running CARLA world, attached to vehicles or fixed in place. Configures mounting positions and sensor attributes, enables supported ROS 2 data publishing, and reports sensor IDs for later data reading.
- Mounting a dashcam on the ego vehicle
- Preparing a lidar for point cloud capture
- Adding GNSS or collision sensors
carla-simulator/carla☆ 14.5KUpdated Oct 21, 2026
Review code changed during a project phase for bugs, security vulnerabilities, and quality issues. Choose the review depth or specific files, receive findings grouped by severity, and optionally apply fixes followed by another review.
- Reviewing code changed during a phase
- Checking selected source files
- Examining interactions across files
open-gsd/gsd-core☆ 10.8KUpdated Oct 21, 2026
Assess GraphQL APIs during penetration tests, from finding endpoints and mapping data structures to checking access controls, query limits, subscriptions, and uploads. Includes example queries, guidance for testing tools, and defensive controls for interpreting findings.
- Map GraphQL endpoints and data structures
- Check access controls across users and roles
- Review query limits and subscription security
SnailSploit/Claude-Red☆ 7.7KUpdated Oct 13, 2026
Add a real 3D object to a web page using Three.js. Combine geometric depth, materials that respond to light, perspective, and subtle rotation or floating motion for hero sections and product visuals.
- Adding a faceted 3D object to a hero section
- Creating metal or ceramic-looking product visuals
- Adding subtle rotation and floating motion to web layouts
MengTo/Skills☆ 6.9KUpdated Oct 18, 2026
Shape a high-contrast interface with dark molded panels, inset shadows, and tactile controls that resemble physical objects. Apply a consistent visual system across page framing, cards, buttons, and small status displays, using one restrained accent color.
- Designing a dark interface with tactile depth
- Giving cards and controls a consistent material feel
- Using a brand color for status and active indicators
MengTo/Skills☆ 6.9KUpdated Oct 18, 2026
Build falling leaves or petals with visible front-and-back tumbling and sideways motion tied to rotation. Covers 2D canvas and 3D implementations, depth layers, particle density, rendering costs, and reduced-motion support.
- Add autumn leaves to a web page
- Animate drifting cherry blossom petals
- Create layered foliage in a 3D scene
MengTo/Skills☆ 6.9KUpdated Oct 18, 2026
Design a calm, dark workspace with frosted glass panels, multiple columns, and floating information cards. Coordinate navigation, framing, spacing, background depth, and subtle motion into a consistent interface that stacks cleanly on smaller screens.
- Designing a dark dashboard or workspace
- Arranging navigation and sidebars around a central view
- Unifying glass panels, buttons, and information cards
MengTo/Skills☆ 6.9KUpdated Oct 18, 2026
Create a WebGL background with a perspective grid, fading lines, and sparse floating particles. Add slow forward motion and gentle mouse-responsive camera movement, then tune density, color, and depth to support foreground content.
- Create a tech-style background with depth
- Add gentle mouse-responsive camera movement
- Tune fading grid lines and sparse particles
MengTo/Skills☆ 6.9KUpdated Oct 18, 2026
Apply layered, neutral shadows to cards, form controls, panels, and larger containers using Tailwind classes with custom values. Three prescribed shadow strengths help match visual depth to the size and purpose of each component.
- Adding subtle depth to form controls and compact cards
- Styling shadows for panels and popovers
- Giving hero media and modal-like containers stronger elevation
MengTo/Skills☆ 6.9KUpdated Oct 18, 2026
Learn programming concepts through a short definition, a minimal code example, and a practical use case. Explanations adapt to experience level, highlight common mistakes, and suggest related topics and a small practice exercise.
- Learning React hooks from small examples
- Understanding how async/await works
- Exploring SQL joins in depth
FlorianBruniaux/claude-code-ultimate-guide☆ 6.2KUpdated Oct 20, 2026
Start a presentation from a topic and optional documents, choose research depth and visual richness, and coordinate outline creation and production through companion skills. Saved task records also support resuming interrupted presentation work.
- Start a presentation from a topic and documents
- Choose research depth and visual richness
- Review an outline before slide production
OpenSenseNova/SenseNova-Skills☆ 5.8KUpdated Oct 9, 2026
Audit GraphQL APIs for exposed schemas, missing access checks, injection risks, and weak query limits. Combine automated tools with targeted checks to investigate data exposure, unauthorized operations, and resource exhaustion, then document findings with reproducible evidence.
- Discover GraphQL schemas and hidden fields
- Check object and field access permissions
- Test batching, query depth, and complexity limits
awarexone/Agentic-Bug-Hunter☆ 5.4KUpdated Oct 10, 2026
Draft an English referee report for an economics or finance paper, with a findings summary, specific numbered critiques, and a letter to the editor. Choose the recommendation, review depth, and three to eight comments.
- Drafting a referee report for an economics or finance paper
- Examining causal claims and robustness of research findings
- Choosing review depth and the number of comments
brycewang-stanford/Auto-Empirical-Research-Skills☆ 4.7KUpdated Oct 20, 2026
Manage long or multi-part agent tasks by defining observable completion criteria before work begins. Break work into deliverables, run approved checks, and verify recorded evidence again before reporting which requirements are met or still need attention.
- Defining completion criteria for long autonomous tasks
- Finding omissions in work returned half-finished
- Coordinating parallel deliverables and integration checks
Leonxlnx/unlazy☆ 4KUpdated Sep 3, 2026
Record function entry and exit in C/C++ programs, with separate logs for each thread. Convert those logs into a Perfetto timeline to inspect call depth, execution order, and activity across threads.
- Following function execution order
- Inspecting call depth in logs
- Viewing multiple threads on one timeline
gadievron/raptor☆ 3.9KUpdated Oct 20, 2026
Prepares Claude Code or OpenAI Codex for in-depth research with hyperresearch, then hands the request to a structured workflow for research reports, literature reviews, and analysis using multiple sources with verified citations.
- Preparing a research report with verified citations
- Reviewing literature on a specific topic
- Comparing evidence from multiple sources
jordan-gibbs/hyperresearch☆ 3.9KUpdated Oct 11, 2026
Create or update hierarchical AGENTS.md files that explain a project's structure, commands, and conventions. Analyze directory complexity to choose useful locations, then keep local guidance concise and avoid repeating parent instructions.
- Documenting project conventions for coding agents
- Adding guidance for complex directories
- Updating existing AGENTS.md files
code-yeongyu/lazycodex☆ 3.8KUpdated Oct 20, 2026
Prepare BOP datasets and run depth estimation, image segmentation, and FoundationPose to estimate object positions and orientations. Evaluate completed runs, compare accuracy and coverage, or change scoring settings without repeating inference.
- Adapt a BOP dataset and test a single scene
- Estimate object poses without ground-truth annotations
- Re-score a completed run while preserving its original report
NVIDIA/skills☆ 3.7KUpdated Oct 21, 2026
Analyze how liquid a stock is using Yahoo Finance data (yfinance): bid-ask spreads, volume and dollar volume (ADTV), top-of-book and options depth, square-root market impact and slippage estimates, turnover ratio, and Amihud illiquidity, rolled into a liquidity grade. Use this skill whenever the user asks about liquidity or trading costs — how easily a position can be entered or exited, what a large order would do to the price, spread or execution-cost estimates, order book depth, volume patterns, or liquidity comparisons — especially for small caps, penny stocks, and thinly traded names.
The English summary is being prepared. Showing the original description.
himself65/finance-skills☆ 3.4KUpdated Oct 19, 2026