Browse Skills — Page 139
21,758 public skills · showing 13,801–13,900
- 100/100
opencode-mirror
different-ai/openwork
Maintain the local OpenCode mirror for self-reference
- 100/100
opencode-primitives
different-ai/openwork
Reference OpenCode docs when implementing skills, plugins, MCPs, or config-driven behavior.
- 100/100
opencv
TerminalSkills/skills
>-
- 100/100
opendataloader-pdf
TerminalSkills/skills
>-
- 100/100
opendeviation-eval-metrics
terrylica/cc-skills
evaluating open deviation bar signal quality, computing Sharpe ratios with non-IID bars, running PSR/DSR/MinTRL statistical tests, or assessing.
- 100/100
openenv-cli
huggingface/OpenEnv
OpenEnv CLI (`openenv`) for scaffolding, validating, building, and pushing OpenEnv environments.
- 100/100
opener-critique
lyndonkl/claude
Evaluates the first 1-3 sentences of a substacker draft against the writer's signature opener patterns — confession / "I hadn't done X" / reframe / small concrete admission. Classifies opener as confession | reframe | admission | news-hook | generic-opener and flags news-hook/generic as tier-1. The opener sets the voice contract for the essay. Use on every draft. Trigger keywords: opener, hook, first sentence, opening, confession opener, news hook, generic opener.
- 100/100
opengraph-io-automation
ComposioHQ/awesome-claude-skills
"Automate Opengraph IO tasks via Rube MCP (Composio). Always search tools first for current schemas."
- 100/100
openhr
aAAaqwq/AGI-Super-Team
Boss直聘全流程AI自动化招聘智能体。自动登录、筛选候选人、个性化打招呼、智能聊天跟进、简历解析、飞书同步。触发词:启动招聘、自动打招呼、boss greet、openhr、简历解析、上传飞书。
- 100/100
openhue
openclaw/openclaw
Control Philips Hue lights and scenes via the OpenHue CLI.
- 100/100
openmed
mkurman/zorai
Production-ready medical NLP toolkit (maziyarpanahi/openmed). Entity extraction, assertion detection, PII de-identification, batch processing, REST API, and multilingual support. Covers installation, all model families, configuration, and deployment.
- 100/100
openocd
zhinkgit/embeddedskills
>-
- 100/100
openperplex-automation
ComposioHQ/awesome-claude-skills
"Automate Openperplex tasks via Rube MCP (Composio). Always search tools first for current schemas."
- 85/100
openrlhf-training
Orchestra-Research/AI-Research-SKILLs
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
- 100/100
openrouter
TerminalSkills/skills
>-
- 100/100
openrouter-automation
ComposioHQ/awesome-claude-skills
"Automate Openrouter tasks via Rube MCP (Composio). Always search tools first for current schemas."
- 100/100
openrouter-usage
aAAaqwq/AGI-Super-Team
Track OpenRouter API spending — credit balance, per-model cost breakdown,
- 100/100
openscreen
TerminalSkills/skills
>-
- 80/100
opensea
BankrBot/skills
Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base. Covers the full OpenSea developer surface across CLI, MCP server, shell scripts, and SDK. Pick the right sub-skill using the routing table below, then read that sub-skill's SKILL.md for operational detail.
- 95/100
opensea-api
BankrBot/skills
API key for all OpenSea services (REST API, CLI, SDK, and MCP server)
- 100/100
opensea-marketplace
BankrBot/skills
API key for all OpenSea services
- 100/100
opensea-swaps
BankrBot/skills
API key for all OpenSea services
- 20/100
opensea-tool-sdk
BankrBot/skills
RPC URL for Base mainnet (default https://mainnet.base.org)
- 70/100
opensea-wallet
BankrBot/skills
Bankr API key for HTTP-based agent wallet signing
- 100/100
opensource-guide-coach
xixu-me/skills
Use when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding, community health, maintainer burnout, code of conduct, metrics, legal basics, or open source project adoption.
- 100/100
opensource-pipeline
affaan-m/ECC
Open-source pipeline: fork, sanitize, and package private projects for safe public release. Chains 3 agents (forker, sanitizer, packager). Triggers: '/opensource', 'open source this', 'make this public', 'prepare for open source'.
- 100/100
openspec-apply
partme-ai/full-stack-skills
Implement tasks from the change using `/opsx:apply`, working through the task list and checking off items. Use when the user says "implement", "apply the change", "/opsx:apply", or "start coding from tasks".
- 100/100
openspec-apply-change
Chorus-AIDLC/Chorus
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
- 100/100
openspec-archive
partme-ai/full-stack-skills
Archive a completed change with `/opsx:archive`, merging delta specs into main specs and preserving the change for history. Use when the user says "archive the change", "finish up", "/opsx:archive", or "mark this change as done".
- 100/100
openspec-archive-change
Chorus-AIDLC/Chorus
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
- 100/100
openspec-aware
Chorus-AIDLC/Chorus
Opt-in OpenSpec-mode authoring for Chorus PM workflows in Codex. Detects the local `openspec` CLI, scaffolds `openspec/changes/<slug>/` on disk, and mirrors Markdown files into Chorus document drafts via the `chorus-mcp-call.sh` wrapper. Required reading for the proposal, develop, and yolo skills whenever the user has the `openspec` CLI installed.
- 100/100
openspec-bulk-archive
partme-ai/full-stack-skills
Archive multiple completed changes at once with `/opsx:bulk-archive`, handling spec conflicts between changes. Use when the user says "archive all changes", "bulk archive", "/opsx:bulk-archive", or has multiple completed changes.
- 100/100
openspec-config
partme-ai/full-stack-skills
Configure OpenSpec project settings and global CLI configuration using `openspec/config.yaml` and `openspec config` commands. Use when the user says "configure OpenSpec", "project config", "add project context", or wants to set per-artifact rules.
- 100/100
openspec-continue
partme-ai/full-stack-skills
Create the next artifact in the dependency chain with `/opsx:continue`, building up a change incrementally. Use when the user says "continue the change", "create next artifact", "/opsx:continue", or wants step-by-step artifact creation.
- 100/100
openspec-explore
Chorus-AIDLC/Chorus
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
- 100/100
openspec-ff
partme-ai/full-stack-skills
Fast-forward through artifact creation with `/opsx:ff`, generating all planning artifacts (proposal, specs, design, tasks) at once. Use when the user says "fast forward", "create all artifacts", "/opsx:ff", or has a clear picture of what to build.
- 100/100
openspec-initial
partme-ai/full-stack-skills
Run `openspec init` to initialize OpenSpec in a project directory, creating the openspec/ folder structure and configuring AI tool integrations. Use when the user says "initialize OpenSpec", "openspec init", or "set up OpenSpec in this project".
- 100/100
openspec-install
partme-ai/full-stack-skills
Install the OpenSpec CLI globally via npm, pnpm, yarn, bun, or nix. Use when the user says "install OpenSpec", "set up OpenSpec", or "openspec command not found".
- 100/100
openspec-new
partme-ai/full-stack-skills
Start a new OpenSpec change with `/opsx:new`, creating a change folder with metadata and scaffolding. Use when the user says "start a new change", "new feature", "/opsx:new", or "create an OpenSpec change".
- 100/100
openspec-onboard
partme-ai/full-stack-skills
Guided onboarding through the complete OpenSpec workflow using `/opsx:onboard`, walking the user through a real change in their codebase. Use when the user says "onboard me", "tutorial", "/opsx:onboard", "how does OpenSpec work", or is new to OpenSpec.
- 100/100
openspec-propose
Chorus-AIDLC/Chorus
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
- 100/100
openspec-schema
partme-ai/full-stack-skills
Create and manage custom workflow schemas using `openspec schema init/fork/validate/which`. Use when the user says "create a custom workflow", "custom schema", "fork a schema", or wants to define their own artifact types and dependencies.
- 100/100
openspec-sync
partme-ai/full-stack-skills
Sync delta specs from a change into main specs using `/opsx:sync`, without archiving the change. Use when the user says "sync specs", "merge specs to main", "/opsx:sync", or needs to update main specs mid-change.
- 100/100
openspec-update
partme-ai/full-stack-skills
Run `openspec update` to regenerate AI tool instruction files after upgrading the OpenSpec CLI. Use when the user says "update OpenSpec", "openspec update", or "refresh OpenSpec skills/commands".
- 100/100
openspec-verify
partme-ai/full-stack-skills
Validate that implementation matches change artifacts using `/opsx:verify`, checking completeness, correctness, and coherence. Use when the user says "verify implementation", "check my work", "/opsx:verify", or wants quality validation before archiving.
- 100/100
opensrc
vercel-labs/opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs.
- 100/100
opentargets-disease-target
InternScience/scp
Retrieve disease-associated targets from Open Targets using disease EFO IDs to identify therapeutic targets.
- 100/100
opentargets-skill
openai/plugins
Submit compact Open Targets Platform GraphQL requests for target, disease, drug, variant, study, and search data, including associated-disease datasource heatmap matrices. Use when a user wants concise Open Targets summaries or per-datasource evidence context
- 95/100
opentofu
TerminalSkills/skills
>-
- 100/100
opentrons-integration
K-Dense-AI/scientific-agent-skills
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
- 100/100
opentype-js
TerminalSkills/skills
>-
- 100/100
openviking
TerminalSkills/skills
>-
- 100/100
openvpn
TerminalSkills/skills
>-
- 100/100
openweather-api-automation
ComposioHQ/awesome-claude-skills
"Automate Openweather API tasks via Rube MCP (Composio). Always search tools first for current schemas."
- 100/100
openwork-core
different-ai/openwork
Core context and guardrails for OpenWork native app
- 100/100
openwork-debug
different-ai/openwork
Debug OpenWork sidecars, config, and audit trail
- 100/100
openwork-orchestrator-npm-publish
different-ai/openwork
|
- 100/100
operationalization
yogsoth-ai/de-anthropocentric-research-engine
SOP: 将抽象概念操作化为可测量的指标和方法
- 95/100
operations
notque/vexjoy-agent
Business operations workflows — vendor management, runbooks, process documentation, risk assessment, capacity planning, change management, compliance tracking. Use when reviewing vendors, writing runbooks, documenting processes, assessing risk, planning capacity, or managing change.
- 100/100
operator-scorecard
aaronjmars/aeon
Weekly plain-language synthesis of agent health + community growth + economic activity — answers "was this week worth it?" in one notification
- 100/100
opponent-archetype-classifier
lyndonkl/claude
Classifies an opposing player, manager, or agent into one of a configurable archetype set using Bayesian inference over observed behavior (roster composition, transaction pattern, lineup moves, trade activity). Domain-neutral scaffold -- callers supply the archetype taxonomy (names, priors, characteristic feature distributions) and observed features; the skill returns a normalized posterior, MAP archetype, classification confidence, feature-contribution breakdown, and best-response hints. Use when modeling opponents, classifying player types, performing Bayesian archetype inference, producing opponent posteriors, or when user mentions opponent archetype, classify opponent, Bayesian archetype inference, player type classification, opponent modeling, or archetype posterior.
- 100/100
opportunity-solution-tree
deanpeters/Product-Manager-Skills
Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build.
- 80/100
ops-inspector
TencentCloudBase/CloudBase-MCP
AIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource health, inspect logs, or run a comprehensive health check across cloud functions, CloudRun services, databases, and other CloudBase resources.
- 55/100
opsgenie
TerminalSkills/skills
>-
- 100/100
optical-frequency-calculation
InternScience/scp
Calculate optical frequency and wavelength relationships for photonics and electromagnetic analysis.
- 100/100
optics_analysis
InternScience/scp
Optical System Analysis - Analyze optical system: calculate photon rate, frequency range, radiation pressure, and electron wavelength. Use this skill for optics tasks involving calculate incident photon rate calculate frequency range calculate radiation pressure electron wavelength. Combines 4 tools from 1 SCP server(s).
- 100/100
optimization-run
yogsoth-ai/de-anthropocentric-research-engine
Execute multi-objective optimization on candidates to produce a Pareto front of non-dominated solutions.
- 100/100
optimize
TheBushidoCollective/han
Optimize code for performance, readability, or efficiency
- 100/100
optimize-agentic-workflow
github/gh-aw
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.
- 100/100
optimize-for-gpu
K-Dense-AI/scientific-agent-skills
GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analysis, medical imaging, and sparse eigensolvers. Also use when you see CPU-bound Python code (loops, large arrays, ML pipelines, graph analytics, image processing) that would benefit from GPU acceleration, even if not explicitly requested.
- 100/100
optimize-prompt-token-efficiency
doodledood/manifest-dev
Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.
- 100/100
optimize-seo
MicrosoftDocs/cloud-adoption-framework
Validates SEO metadata quality — description length, title/H1 match, and ms.topic correctness. Use when asked to check SEO or metadata optimization.
- 100/100
optimize-simplicite-logs
github/awesome-copilot
capability to parse Simplicité logs from a raw `.txt` file, filter fields to reduce noise, and output the result as structured JSON.
- 100/100
optimizetests
openclaw/openclaw
Optimize OpenClaw slow tests, imports, misplaced coverage, and CI wall time without dropping coverage.
- 100/100
optimizing-attention-flash
NousResearch/hermes-agent
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
- 100/100
optimizing-performance
rileyhilliard/claude-essentials
Measure-first performance optimization that balances gains against complexity. Use when addressing slow code, profiling issues, or evaluating optimization trade-offs.
- 100/100
optimoroute-automation
ComposioHQ/awesome-claude-skills
"Automate Optimoroute tasks via Rube MCP (Composio). Always search tools first for current schemas."
- 100/100
option-vol-analysis
anthropics/financial-services
Analyze option volatility by combining vol surface data, option pricing with Greeks, and historical price data to assess implied vs realized volatility. Use when pricing options, analyzing volatility surfaces, computing Greeks, assessing vol premiums, or evaluating vol trading strategies.
- 100/100
options-advanced
HKUDS/Vibe-Trading
Advanced options strategies: volatility-surface modeling (SABR / Local Vol), dynamic Greeks rebalancing, calendar spreads, volatility arbitrage and skew trading, and option market-making basics.
- 100/100
options-flow-analyzer
diegosouzapw/awesome-omni-skills
Options Flow Analyzer workflow skill. Use this skill when the user needs Real vs lottery call separation for options P/C ratio analysis \u2014 prevents signal inversion from deep OTM noise and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
options-flow-analyzer-v2
diegosouzapw/awesome-omni-skills
Options Flow Analyzer workflow skill. Use this skill when the user needs Real vs lottery call separation for options P/C ratio analysis \u2014 prevents signal inversion from deep OTM noise and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
options-payoff
HKUDS/Vibe-Trading
Option P&L analysis methodology: payoff diagrams, breakeven calculation, multi-leg strategy visualization, and Greeks-based scenario analysis.
- 100/100
options-strategy
HKUDS/Vibe-Trading
Options strategy framework supporting Black-Scholes pricing, Greeks analysis, and multi-leg backtesting. Suitable for cryptocurrency and equity options.
- 100/100
optuna
mkurman/zorai
Hyperparameter optimization framework (Optuna). Define-by-run API with automatic search space construction, state-of-the-art samplers (TPE, CMA-ES, NSGA-II, GPSampler), efficient pruning (Median, Hyperband, ASHA), multi-objective optimization, constrained optimization, distributed parallel execution, and visualization dashboard. Integrates with PyTorch, PyTorch Lightning, TensorFlow, Keras, XGBoost, LightGBM, CatBoost, MLflow, W&B, and scikit-learn.
- 100/100
opus-review
SteelMorgan/1c-agent-based-dev-framework
Ревью через второй независимый инстанс Opus. Навык учит агента запускать независимое ревью артефактов через субагент Task с изолированным контекстом. Используй при вызове /review-opus, /review-all, или когда пользователь просит проверить план, спецификацию, код или архитектуру независимым взглядом той же модели.
- 100/100
ora
TerminalSkills/skills
>-
- 100/100
oracle
openclaw/openclaw
Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.
- 100/100
oracle-family-scan
Soul-Brews-Studio/arra-oracle-skills-cli
Oracle Family Registry — scan, query, welcome. 186+ Oracles indexed. Use when user says "family scan", "oracle registry", "welcome new oracles", or needs to check Oracle population.
- 100/100
oracle-manage
Soul-Brews-Studio/arra-oracle-skills-cli
Skill and profile management — prepare tools, switch profiles, enable/disable skills, feature modules. Use when user says "oracle manage", "oracle prepare", "oracle skills", "oracle profile".
- 100/100
oracle-soul-sync-update
Soul-Brews-Studio/arra-oracle-skills-cli
Sync Oracle instruments with the family. Check and update skills to latest version. Use when user says "soul-sync", "sync", "calibrate", "update", or before /awaken.
- 100/100
oral-health-analyzer
diegosouzapw/awesome-omni-skills
\u53e3\u8154\u5065\u5eb7\u5206\u6790\u6280\u80fd workflow skill. Use this skill when the user needs \u5206\u6790\u53e3\u8154\u5065\u5eb7\u6570\u636e\u3001\u8bc6\u522b\u53e3\u8154\u95ee\u9898\u6a21\u5f0f\u3001\u8bc4\u4f30\u53e3\u8154\u5065\u5eb7\u72b6\u51b5\u3001\u63d0\u4f9b\u4e2a\u6027\u5316\u53e3\u8154\u5065\u5eb7\u5efa\u8bae\u3002\u652f\u6301\u4e0e\u8425\u517b\u3001\u6162\u6027\u75c5\u3001\u7528\u836f\u7b49\u5176\u4ed6\u5065\u5eb7\u6570\u636e\u7684\u5173\u8054\u5206\u6790\u3002 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
oral-health-analyzer-v2
diegosouzapw/awesome-omni-skills
\u53e3\u8154\u5065\u5eb7\u5206\u6790\u6280\u80fd workflow skill. Use this skill when the user needs \u5206\u6790\u53e3\u8154\u5065\u5eb7\u6570\u636e\u3001\u8bc6\u522b\u53e3\u8154\u95ee\u9898\u6a21\u5f0f\u3001\u8bc4\u4f30\u53e3\u8154\u5065\u5eb7\u72b6\u51b5\u3001\u63d0\u4f9b\u4e2a\u6027\u5316\u53e3\u8154\u5065\u5eb7\u5efa\u8bae\u3002\u652f\u6301\u4e0e\u8425\u517b\u3001\u6162\u6027\u75c5\u3001\u7528\u836f\u7b49\u5176\u4ed6\u5065\u5eb7\u6570\u636e\u7684\u5173\u8054\u5206\u6790\u3002 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
orama
TerminalSkills/skills
Expert guidance for Orama, the fast full-text and vector search engine that runs everywhere — browser, server, and edge. Helps developers implement search with typo tolerance, facets, filters, and hybrid (keyword + vector) search without external infrastructure.
- 100/100
orange-flaggen-katalog
Klotzkette/claude-fuer-deutsches-recht
Katalog schwacher positiver Formulierungen im Arbeitszeugnis, die auf Note 3 hindeuten. Umfasst alle Orange-Signale: fehlende Steigerungsadverbien, eingeschränkte Lobesformeln und strukturelle Abschwächungen mit Notentendenz Note 3.
- 100/100
orca
elophanto/EloPhanto
Complete guide for Orca - Solana's leading concentrated liquidity AMM (CLMM). Covers Whirlpools SDK for swaps, liquidity provision, pool creation, position management, and fee harvesting on Solana and Eclipse networks.
- 100/100
orchard
okooo5km/Skills4U
Use the local `orchard` CLI to interact with macOS Apple apps and services from Codex: Calendar, Reminders, Clock, Mail, Contacts, Notes, Music, Weather, Messages, and Location/Maps. Use when a task asks to read or manage local calendar events, reminders, Apple Mail, contacts, notes, iMessage/SMS, Apple Music playback/library, weather, current time/timezones, geocoding, routes, or current location.
- 100/100
orchestrate
Significant-Gravitas/AutoGPT
Meta-agent supervisor that manages a fleet of Claude Code agents running in tmux windows. Auto-discovers spare worktrees, spawns agents, monitors state, kicks idle agents, approves safe confirmations, and recycles worktrees when done. TRIGGER when user asks to supervise agents, run parallel tasks, manage worktrees, check agent status, or orchestrate parallel work.
- 100/100
orchestrate-batch-refactor
TerminalSkills/skills
>-
- 100/100
orchestrate-batch-refactor-v2
diegosouzapw/awesome-omni-skills
Orchestrate Batch Refactor workflow skill. Use this skill when the user needs Plan and execute large refactors with dependency-aware work packets and parallel analysis and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
- 100/100
orchestrating-agents
oaustegard/claude-skills
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.
Page 139 of 218