Showing 9691–9720 of 10202 skills
Global one-shot evoskill skill library injection for gaia executor smoke and evaluation.
DANG-ai/SKILLER
Compact attachment-first router for GAIA-style tasks under a static ReAct loop with narrow evidence gathering, lightweight derivation, and strict answer-shape control.
DANG-ai/SKILLER
Compact attachment-first router for GAIA-style tasks under a static ReAct loop with narrow evidence gathering, lightweight derivation, and strict answer-shape control.
DANG-ai/SKILLER
Compact attachment-first router for GAIA-style tasks under a static ReAct loop with narrow evidence gathering, lightweight derivation, and strict answer-shape control.
DANG-ai/SKILLER
Compact attachment-first router for GAIA-style tasks under a static ReAct loop with narrow evidence gathering, lightweight derivation, and strict answer-shape control.
DANG-ai/SKILLER
bestdeejay-design/agent-skills
Use when <concrete trigger — when Lovable should load this skill>. Describe the boundaries too, meaning what this skill does NOT cover.
silvioventre/lovable-skills
Build a Logitech MX Keypad plugin for Claude Code and Codex on macOS with the Logi Actions SDK in C#, with live session keys that show which Claude Code and Codex sessions are working, waiting or finished, one-press voice dictation, area screenshots, Send and Discard keys, next-thread switching and usage limits on the keypad's nine LCD keys. Learns which coding agents, dictation app, screenshot tool and browser the user has, asks what they want, and adapts the keys to them. Covers project setup on the .NET version the Logi Plugin Service really runs, drawing every key yourself, press feedback, page navigation, opening an exact session, putting dictation and screenshots into the right text box, reading Claude and Codex usage limits, and the failures that cost the most time. Use this skill whenever someone mentions the MX Keypad, MX Creative Console, Loupedeck, Logi Options+ plugins, Logi Plugin Service, LogiPluginTool, .lplug4 files, or wants physical buttons or a macro pad for Claude Code, Codex or other coding agents, even if they do not name the SDK.
Shivak11/mx-keypad-claude-code-codex
Build a living, governed brand voice through the Brand Therapy discipline — an eight-stage process that treats a brand as the relational space between a company and its consumer. Use this skill whenever the user wants to create a brand voice, define a brand identity, build a brand persona, establish brand governance, or articulate what their brand actually sounds like. Also trigger when users say "brand voice", "brand identity", "who is my brand", "brand persona", "brand guidelines", "brand therapy", or ask for help making their brand feel coherent, consistent, or governed. This skill goes far beyond typical brand voice exercises — it builds a governed voice that can hold itself together under pressure, across channels, over time, and then turns it on.
jaimeschwarz/brandvoice
Agent assignment guidance, architecture patterns, and dependency ordering for fullstack-typescript plans.
LiorCohen/sdd
posteyai/skills
Build SKILL.md files for Claude Code, Codex, Amp, OpenCode. Production examples and patterns for skill structure, scripts, distribution, and making CLI tools AI-native.
gmickel/better-skill-builder
Explains which credential files a skill must never read.
ondrej-merkun/skill-audit
[FILL IN: what this skill does and exactly when to use it -- the phrases a user would actually type, not just the topic]
colomet/skill-boilerplate
国资公司投资项目合规自查。基于地方国资监管文件(市管国有企业投资监督管理办法 + 投资事项负面清单),对投资项目进行形式要件型合规初审:金额阈值判定、报告档级识别、14项负面清单核查、关联交易排查、决策程序齐备性、量化指标计算、高压线一票否决判定、八阶段时序错位防错。当用户提到"投资合规自查""项目合规""负面清单""F8/F10""报告程序""董事会程序""三级子公司股权投资""关联交易核查""1000万/3000万阈值""当前阶段"等关键词时触发。
jarodong/soe-investment-compliance-skill
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
FISCFED9/CLI
Plan a feature or bug fix and break it into well-formed, non-mixing Linear tasks — one parent issue per feature with ordered, dependency-linked sub-issues, each with a detailed plan, acceptance criteria, labels, and a branch name — ready for a coding agent to execute. Use when the user runs /plantask, or asks to plan and create Linear issues/tasks for a feature, bug, or piece of work.
Parsa-29/loop-config
Consult & operate against the Hyperliquid Names API. Use when your agent needs to resolve `.hl` names, reverse-resolve addresses, fetch HLN profiles or records, inspect owner or list queries, diagnose HLN API failures, prepare a mint-pass request, or guide HyperEVM dApp integration with HL Names.
HLnames/use-hln-api
识别和分析PUA(Pickup Artist)及情感操纵行为的专业心理分析工具。具备人格分析、心理侧写、情感分析能力,能够识别情感操纵、煤气灯操纵、虐待等有毒关系模式,评估人格特质(如黑暗三人格、脆弱型自恋等),预测对方行为并给出具体的相处建议。当用户需要:分析对方言行动机、识别PUA/情感操纵行为、评估NPD(自恋型人格障碍)倾向、识别操纵行为、预测对方未来行为、寻求健康关系建议、分析黑暗三人格或光明三人格时使用此skill。
marktantongco/promptc-os-ai-prompt-wiki
Top-level agent for USB logic analyzer work using the verified dslogic-cli/libsigrok4DSL native backend. Use for DSLogic/DSView environment setup, device connection, capture (stream+buffer), protocol decode (UART/SPI/I2C), and data interpretation. Use the dsview-logic MCP for hardware operations.
felixfinal/agent-dsviewer-logic-analyzer
Safe Captcha handling via Browser Agent or 2Captcha API.
kbarbel640-del/skills
A simple example skill for demonstration purposes
kbarbel640-del/skills
Join The Compact State — a shared autonomous agent network with on-chain identity, persistent memory, and collective governance.
Trompetilla/Skills
Revise an academic research paper draft (LaTeX) toward a specific target venue's conventions and a fluent, accepted-paper writing style. Use this whenever the user wants to prepare, tighten, restructure, or "clean up" a paper for submission — e.g. "get this ready for EMNLP", "make this read like an accepted ACL paper", "trim to the page limit", "remove the RQ/RO scaffolding", "add an algorithm/equation for the method", "why does this look like a student draft", "evaluate the novelty", "how did this line of work develop / what's the prior work / how is this different", or when they mention a venue (ACL, NAACL, EMNLP, AJCAI, NeurIPS, etc.) together with a manuscript. Trigger even if the user does not say the word "revise" — any request to make a paper draft match a venue or read more like a real published paper should use this skill. Accepts a target venue as input.
ZoeLinUTS/Academic-paper-revision
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.
diegosouzapw/awesome-omni-skill
Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization. Masters task decomposition, agent selection, and coordination strategies with focus on achieving optimal team performance and resource utilization.
diegosouzapw/awesome-omni-skill
Use fmail for agent-to-agent messaging with team conventions.
diegosouzapw/awesome-omni-skill
Expert competitive analyst specializing in competitor intelligence, strategic analysis, and market positioning. Masters competitive benchmarking, SWOT analysis, and strategic recommendations with focus on creating sustainable competitive advantages.
diegosouzapw/awesome-omni-skill
Expert C++ developer specializing in modern C++20/23, systems programming, and high-performance computing. Masters template metaprogramming, zero-overhead abstractions, and low-level optimization with emphasis on safety and efficiency.
diegosouzapw/awesome-omni-skill
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention, and automated recovery strategies across multi-agent systems with focus on minimizing impact and learning from failures.
diegosouzapw/awesome-omni-skill