Performance
Performance profiling and optimization
MoltApp — Open AI Trading Benchmark
by patruff
eval.yaml: https://github.com/patruff/moltapp/blob/main/eval.yaml
code-review
by IHKREDDY
Performs comprehensive code reviews following industry best practices. Use when reviewing pull requests, code changes, or when asked to analyze code quality, security, performance, or maintainability. Checks for common bugs, security vulnerabilities, code smells, and adherence to coding standards.
補習班招生宣傳技能
by Jaosnwings
所有品牌相關資訊皆儲存於 /home/ubuntu/cram-school-brand-assets/brand_profile.md。
redis
by kprsnt2
Redis best practices including data modeling, caching patterns, and performance optimization.
rust
by kprsnt2
Best practices for Rust development including ownership, error handling, and async patterns.
mechanism-development
by tonyflo79
Develop the unique mechanism that explains HOW the product solves the root cause. Use after root cause framing (Skill 03) is complete and you need to create the proprietary explanation of how the solution works. The mechanism is the named, ownable process or ingredient that differentiates the product from everything else the audience has tried. Produces the mechanism package with named mechanism, explanation narrative, and naming anchoring score. Trigger when users mention mechanism, unique mechanism, how it works, proprietary process, named ingredient, or differentiating explanation. Requires root cause package from Skill 03.
commit-helper
by Olino3
Forge is a marketplace for a Claude Code Plugins
collabute-mcp
by collabute
Use Collabute MCP for organization-specific context retrieval and proposal-safe actions. Trigger when users ask about meetings, memory, Linear, Slack, or Vercel data from their Collabute workspace, or ask to create tasks from meeting context.
domain-ml
by lywa1998
"Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理"
agent-guard
by astecka-m
Real-time prompt injection detection and sanitization for AI agents. Protects against Clinejection-style attacks, command injection, and malicious prompt manipulation. Works as both OpenClaw skill and Claude MCP server.
deep-research
by ljchg12-hue
Expert deep research including multi-source verification, fact-checking, and comprehensive analysis
promise-calibration
by tonyflo79
Craft the calibrated promise — the specific, believable outcome the product delivers. Use after mechanism development (Skill 04) is complete and you need to define what the audience can expect. The promise must be bold enough to compel action but calibrated enough to maintain credibility. Produces the promise package with core promise, promise ceiling, specificity markers, and believability anchors. Trigger when users mention promise, core promise, what we are promising, outcome claims, benefit statements, or calibrating the main claim. Requires mechanism package from Skill 04.
auto-evolution
by squirrel289
"Memory-driven self-evolution layer for Agent Skills. Captures usage patterns, learns from errors, and automatically generates reusable knowledge. Use when you want your agent to learn from experience, track skill effectiveness, or generate improvement suggestions."
mobile-lead-soul
by Envy-7z
Mobile tech-lead operating mode for Android and Flutter delivery. Use when making architecture decisions, reviewing team PRs, guiding junior engineers, gating merges/releases, or balancing speed vs stability with token-efficient communication.
stage-execute
by cxyliuy
Execute an approved engineering plan exactly as specified. Implement an MVP and tests without expanding scope or changing constraints.
clawdbot-sync
by YPYT1
"Synchronize memory, preferences, and skills between multiple Clawdbot instances. Supports bi-directional sync via SSH/rsync over Tailscale. Use when asked to sync with another Clawdbot, share memory between instances, or keep multiple agents in sync. Triggers: /sync, 'sync with mac', 'update other clawdbot', 'share this with my other bot'."
film-echo
by sonicpic
Guide a user from a film title, scattered feelings, difficult-to-explain reactions, or messy notes to a coherent first-person Chinese reflection, movie review, or film essay. Use when Codex needs to help someone think through or understand a movie after watching it by asking staged, interview-led questions, drilling into scene-level details, extracting user-owned viewpoints, pressure-testing interpretations, and drafting polished prose instead of generic plot-summary content. Especially useful for art-house, ambiguous, or hard-to-parse films where the user needs patient guidance before writing or before arriving at any stable interpretation.
analyzing-requirements
by jyasuu
Helps the user define, refine, and document requirements for new software features or projects. Use this when a user says "I want to build...", "I need a feature...", or "How should I implement...".
debugging-expert
by Olino3
Forge is a marketplace for a Claude Code Plugins
database-optimizer
by Olino3
Forge is a marketplace for a Claude Code Plugins
system-info
by naohainezha
Get system information — OS version, disk usage, memory, running processes, network status. Use when users ask about their computer status or system health.
vercel-react-best-practices
by Lium-7768
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
workspace-standard
by marcus-qen
"Set up and maintain a structured OpenClaw workspace with project boundaries, role-based file taxonomy, and memory budgets. Use when: (1) bootstrapping a new workspace, (2) migrating from a flat docs/ structure, (3) adding a new project, (4) unsure where to write something, (5) running workspace maintenance, (6) auditing workspace health. Provides the directory layout, ROLE front-matter spec, MEMORY.md budget rules, and maintenance procedures."
code-improvement
by simplerick0
Suggest improvements to existing code including refactoring opportunities, performance optimizations, and modernization. Use for identifying technical debt, suggesting refactors, improving code architecture, and modernizing legacy patterns.