Showing 9211–9240 of 10202 skills
Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.
diegosouzapw/awesome-omni-skill
Create custom Claude Code sub-agents with specialized expertise and tool access. Use when you need to build reusable agents for specific tasks like code review, debugging, data analysis, or domain-specific workflows.
diegosouzapw/awesome-omni-skill
Extract, plan, or propose implementation details at configurable depth levels (low/normal/extensive). Outputs to reference files for team discussion and handoff.
diegosouzapw/awesome-omni-skill
Optimize agent instruction files by extracting sections into separate files and referencing them. Reduces context size while preserving information.
diegosouzapw/awesome-omni-skill
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
diegosouzapw/awesome-omni-skill
Create, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operations, or JSON export.
diegosouzapw/awesome-omni-skill
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
diegosouzapw/awesome-omni-skill
Agent skill for release-swarm - invoke with $agent-release-swarm
diegosouzapw/awesome-omni-skill
Create new skills with guided prompts following best practices
DavidROliverBA/ArchitectKB
Voice-controlled Claude Code - speak commands, hear responses in Olivia voice
DavidROliverBA/ArchitectKB
TomLeeLive/openclaw-unreal-skill
Conceptual introduction to durable execution — what it is, why you'd want it, and the tradeoffs between rolling your own (just your DB) versus using a framework like Resonate. Read this BEFORE picking an implementation. For the Resonate SDK's concrete Context API (ctx.run, ctx.sleep, ctx.promise, structured concurrency), use the per-SDK skill for your language — resonate-basic-durable-world-usage-{typescript,python,rust,go}.
resonatehq/resonate-skills
Use when the user asks to generate or create a photorealistic photo or a photorealistic image, or any image that must look like a real camera captured it. Triggers include "photorealistic photo", "photorealistic image", "photo-realistic", "realistic photo", "generate a photo of", "make a photo", "hyperrealistic", "lifelike", "true to life", "cinematic still", "movie-style frame", "documentary shot", "product photo", "make it look real", "not AI-looking", "shot on", "film still". For illustrations, logos, diagrams, charts, or social media graphics, use the image skill instead.
olegspiridonovdev-spec/photoreal-image-skill
BizyAir 图片/视频/音频生成与 AI 应用执行。用户提到 BizyAir、要生成图片视频、发来 BizyAir 链接或 ID、要搜索 BizyAir 应用时调用。
siliconflow/bizyair-skill
Review any business decision, plan, or strategy through the minimalist entrepreneur lens. Use when someone wants a gut-check on a business decision, wants to simplify their approach, or needs to decide between options. Also use when the user mentions "review my plan," "gut check," "simplify this," "is this too complex," "minimalist approach," or "decision review." This skill references principles from all other skills in this pack.
scaccogatto/minimalist-entrepreneur
One or two sentences: what this skill does AND when to use it. Include the words a user would actually say ("review my essay", "ESP32 deep sleep"). The router matches on this text, so be specific.
Mohammed-051/AIVault
Capture a durable lesson, correction, or convention from this session as a reusable adept skill, then sync it to every harness. Apply when the user corrects you, when a fix generalizes, or when you say 'I'll remember that.'
itaywol/adeptability
Compose a loop — a scheduled system that discovers work, hands it to agents, verifies with an independent evaluator, persists state, and reschedules itself. Apply when the user wants automation that runs on a timer, a triage/babysitter routine, or asks about `adept loop add`.
itaywol/adeptability
Maintain an adept skill library (repo from `adept init --as-library`): published vs private skills, add --publish, syncing dev helpers to your harness. Apply in a library-layout project or when `adept skill list` shows a published/private source.
itaywol/adeptability
Use the `adept` CLI to author an AI skill once and render it into Claude Code, Cursor, Codex, Copilot, OpenCode, and 45+ agents. Apply when installing/syncing skills, editing SKILL.md, or touching .adeptability/.
itaywol/adeptability
Use this skill when writing or reviewing Python code in TTA.dev. Covers package manager, type hints, primitives usage, and anti-patterns.
theinterneti/TTA.dev
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"
theinterneti/TTA.dev
Multi-agent brainstorming: async opinion collision with expert personas. Mixed Codex/Claude Code engine. Use when multiple AI agents need to collaboratively discuss, debate, and converge on solutions through structured dialog. Triggers: brainstorm, multi-perspective discussion, opinion collision, expert debate, war room, collective intelligence, 头脑风暴, 多视角讨论, 集思广益.
northseadl/norix-skills
Task decomposition and multi-agent orchestration with retry, checkpoint recovery, and real-time monitoring. Mixed Codex/Claude Code engine. Parallel/sequential execution.
northseadl/norix-skills
A data-only example Skill used to verify explicit Agent Plugins bindings.
puristajs/harness
Describe what this skill does and the concrete situations in which an agent should use it.
sidiangongyuan/codex-skills-library
The full-lifecycle framework for building products people pay for - routes any product/business situation to the right stage and skill, and maintains persistent venture memory across sessions. Use when someone has a new product or business idea and asks where to start, when revenue or growth is stuck and the cause is unclear, when diagnosing "nobody is buying / signing up / staying", when asked "what should I focus on next" for a product or business, when reviewing progress on a venture this skill has touched before, or when choosing between working on marketing, product, pricing, or positioning. For a specific known problem (e.g. clearly a pricing question), go directly to the vertical skill.
lucasheriques/shipmate
Create or use lightweight persistent project memory for Codex. Use when the user wants Codex to remember decisions, naming, architecture rules, progress, experiment results, or prior debugging across sessions. Also use with memsearch-style markdown memory.
Arnie016/codex-prompt-templates
Use memsearch as an on-demand semantic index for project markdown memory (search → expand → optional deep drill). Use when the user asks to recall past decisions, prior debugging, or “have we seen this before?” and a `.memsearch/memory/` store exists (or the user wants to set one up). Skip when the question is only about current code state (use Read/Grep) or when the user explicitly does not want semantic indexing / installs.
Arnie016/codex-prompt-templates
Synthesize multiple local `sources/` clones into workflow families before creating skills, references, or scripts. Use when doing source-pattern synthesis, comparing several GitHub-derived repos, deciding which cloned patterns deserve durable Codex artifacts, or avoiding duplicate generated skills. Requires local source clones plus `source_pattern_matrix.py`. Skip when you only need a one-repo brief or a metadata-only source inventory.
Arnie016/codex-prompt-templates