Showing 8161–8190 of 10204 skills
Deterministically validates the bundled fixture payload and returns its token.
hellogxp/skill-runtime-intelligence
Use after a batch of Webflow MCP writes (data_whtml_builder, data_element_builder, data_element_tool, data_element_settings_tool, data_style_tool, data_cms_tool, data_component_tool, data_component_props_tool, data_component_variants_tool, data_variable_tool, data_scripts_tool, asset_tool, data_sites_tool publish) to verify the writes actually landed — catching silently-dropped classes, Webflow-injected style defaults, bindings that only look broken, and stale live-page state. A PostToolUse hook shipped with the flowy plugin reminds the agent to invoke this skill.
yaroshidi/flowy
Proves a plugin from AGENT_DISTRO_PLUGINS reached the harness.
juspay/agent-distro
chatfuel-lab/wizard
The gh CLI is GitHub's official command line tool for interacting with GitHub repositories, issues, pull requests, and more. When needs to interact with GitHub repositories, issues, pull requests, and more, use this skill.
DANG-ai/SKILLER
Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.
DANG-ai/SKILLER
You are an expert requirements gatherer and agent builder. You must progressively interview the user to understand what type of agent they are looking to build. You should ask one question at a time w
ranbot-ai/awesome-skills
Initializes and configures Harness in a project — CI, memory, duo workflow, Codex. Use when setting up a new project or adding Harness configuration.
tim-hub/powerball-harness
VIZIER — the multi-horizon trading brain of the Scout/Valet/Vizier stack. Use whenever the user wants market research, a portfolio review or health check, a thesis on a stock/ETF/crypto, or to actually buy/sell across US equities & ETFs (Interactive Brokers) and crypto spot (CCXT). It orchestrates the Scout (data) and Valet (execution) MCP servers, decides with conviction-sized risk discipline, remembers theses between sessions, and executes only under explicit intent — confirmation by default, autonomy strictly opt-in. Triggers on: "research/analyze X", "what's happening in the market", "analyze the market and bring me recommendations" / "find the best opportunities" (→ manager breadth sweep), "is my portfolio healthy", "buy/sell $N of X", "invest $N across N ideas", an empty/vague call (→ read-only market sweep), or "should I buy/sell X".
pedrobraiti/vizier-trading-skill
dovudhusan/viral-hook-reels-skill
面向 AI 内容生产场景的 skill 集合,覆盖图片、视频、声音、数字人等内容生产能力。
shotfun-ai/shotfun-creator
Executes the declared deterministic boundary probe and returns its exact JSON result.
hellogxp/skill-runtime-intelligence
Persist gotchas, preferences, or a repeated workflow from recorded agent history into AGENTS.md or a new skill.
akunzai/agent-skills
สอน skill หรือ concept ใหม่ให้ผู้ใช้ ภายใน workspace นี้
Boom-Vitt/skills-thai
Coordinate Codex implementation with Astra planning and review and focused Luna native subagents. Use when the user requests Astra/Luna orchestration, bounded delegation, or this workflow for a coding task. Plain questions about models or pricing do not require delegation.
dante01yoon/astra-orchestrator
Improve and rewrite user prompts to reduce ambiguity and improve LLM output quality. Use when a user asks to optimize, refine, clarify, or rewrite a prompt for better results, or when the request is about prompt optimization or prompt rewriting.
proflead/codex-skills-library
Use when delegating or accepting cross-agent tasks (Codex, Antigravity, Copilot, OpenClaw, etc.), writing DISPATCH files, establishing file boundaries and ownership, or verifying dispatch completeness before starting work.
farhanhidayatulhaq-max/GAMUKIS
Use when handing off work, reporting results, or resuming another agent's work, writing progress and handoffs with verification evidence and reconciling stale status before editing.
farhanhidayatulhaq-max/GAMUKIS
Use for final review or integration of one or more agents' outputs, validating combined diffs against PRD requirements, contracts, auth and permissions, and regressions, then reporting an APPROVE or REQUEST_CHANGES verdict.
farhanhidayatulhaq-max/GAMUKIS
Claude Code only — a status line is a Claude Code concept and this skill does nothing on another CLI. Reads and changes what the MSU status line shows. Use when the user wants to turn a status-line segment on or off, change polling, title width, label, colours, icon, colour cycling or timestamp, or asks what their MSU status line is currently set to. Editing the settings file by hand is the same operation and belongs here too.
NEXPACE-Limited/msu-skills
Claude Code only — a status line is a Claude Code concept and this skill does nothing on another CLI. Puts the newest MSU Builder notice in the Claude Code status line, and repairs it. Use when the user asks to install, enable, set up, re-install or repair the MSU status line, wants MSU notices or announcements shown under the prompt or in the terminal, or reports that the MSU status line is blank, stale, or gone after an update. Wraps a status line that is already configured rather than replacing it. Taking it back out is `msu-statusline-uninstall`.
NEXPACE-Limited/msu-skills
Claude Code only — a status line is a Claude Code concept and this skill does nothing on another CLI. Takes the MSU status line back out, restores whatever status line was there before it, and uninstalls the plugin when that is what was asked for. Use when the user wants to remove, uninstall, delete, disable or get rid of the MSU status line or the msu-statusline plugin, wants their old status line back, or asks what the install left on their machine.
NEXPACE-Limited/msu-skills
This agent helps create new microagents in the `.openhands/microagents` directory by providing guidance and templates.
ranbot-ai/awesome-skills
Install, invoke, diagnose and distribute Funnel Engineering System skills across Codex, Claude Code, Cursor, Gemini CLI, GitHub Copilot and OpenCode, while preserving host-specific permission boundaries.
modassarislam37/funnel-engineering-system
Architecture skill for SynthKernel — TypeScript module composition via createContext. Use when building, extending, or refactoring a SynthKernel project.
hesprs/synthkernel
The foundational mindset for building with Resonate. Read this FIRST before any other Resonate skill. Teaches you to write simple, sequential code and avoid over-engineering.
resonatehq/resonate-skills
为人文社科报告进行可追溯的联网检索、优秀范例学习、政策与时效性事实核验、文献查找和引用整理。用户要求上网搜集、查最新信息、学习优秀范例、补充政策背景、查文献、核验出处或提供链接时使用。该 Skill 只负责外部资料的发现与证据控制,不替代报告统筹或 Word 排版。
xuedai-mayi/folio-desk
Use when asked to prove skill usage logging with Pathgrade by creating the marker file.
yang2020chen/skill-context-doctor
Use when engineering or selecting the best features for single-response classification or regression in MATLAB, whatever the data's modality — for non-tabular data it routes extraction to a domain skill, then selects, assesses, and delivers on the resulting table. Not for multi-response problems, model training, or raw data acquisition.
zrwangems/dsh-zrwang-plugin
Fit curves and surfaces interactively with the Curve Fitter app for a complete no-code fitting workflow. Invoke this skill when the Curve Fitter app, cftool, curveFitter, or "curve fitting tool/app" is mentioned in any way. Also use when exploring or comparing fit types (regression, interpolation, smoothing, splines, custom equations); excluding outliers interactively; iterating on a fitting workflow; help choosing a fit type; and exporting to a figure, generating MATLAB code, fits to the workspace, and to Simulink Lookup Tables.
zrwangems/dsh-zrwang-plugin