General
PromptBeginner5 minmarkdownQuality: 72
Techniques to improve reliability
When GPT-3 fails on a task, what should you do?
15
Agent skill library
Skills that turn agents into dependable teammates.
Stop guessing. Use a tight standard for skills that are clear, testable, and valuable in under 60 seconds.
Writing & ContentCoding & DebuggingData & InsightsResearch & LearningOperations & WorkflowProduct & Growth
153586skills
16categories
Featured skills
View allGeneral5 min
OpenAI harmony response format
The [`gpt-oss` models](https://openai.com/open-models) were trained on the harmony response format for defining conversation structures, generating reasoning output and structuring function calls. If you are not using `gpt-oss` directly but through an API or a provider like Ollama, you will not have
General5 min
Techniques to improve reliability
When GPT-3 fails on a task, what should you do?
General5 min
User guide for gpt-oss-safeguard
ROOST and OpenAI have prepared a guide that explains how to write policy prompts that maximize [gpt-oss-safeguard's](https://github.com/openai/gpt-oss-safeguard) reasoning power, choose the right policy length for deep analysis, and integrate oss-safeguard's reasoning outputs into production Trust &
General5 min
> **Note:** This repository contains Anthropic's implementation of skills for Claude. For information about the Agent Skills standard, see [agentskills.io](http://agentskills.io).
[](https://skills.sh/anthropics/skills)
General5 min
Anthropic Computer Use Demo
> [!NOTE]
General5 min
Documentation
This directory contains the documentation source code for LlamaIndex, available at https://docs.llamaindex.ai.
Built for clarity
KISS content standard
Always expanding
Crawler + community
Skill formats
Four ways to package an agent skill
Prompt
Tight instructions that lock in tone, scope, and output shape.
Tool
Concrete actions, APIs, and schemas that your agent can call.
Workflow
Stepwise playbooks with decisions, checkpoints, and outputs.
Config
Settings and system prompts for reliable, repeatable behavior.
Popular skills
General
PromptBeginner5 minmarkdownQuality: 72
User guide for gpt-oss-safeguard
ROOST and OpenAI have prepared a guide that explains how to write policy prompts that maximize [gpt-oss-safeguard's](https://github.com/openai/gpt-oss-safeguard) reasoning power, choose the right policy length for deep analysis, and integrate oss-safeguard's reasoning outputs into production Trust &
15
General
PromptBeginner5 minmarkdownQuality: 72
OpenAI harmony response format
The [`gpt-oss` models](https://openai.com/open-models) were trained on the harmony response format for defining conversation structures, generating reasoning output and structuring function calls. If you are not using `gpt-oss` directly but through an API or a provider like Ollama, you will not have
14
General
PromptBeginner5 minmarkdownQuality: 70
Anthropic Computer Use Demo
> [!NOTE]
19
General
PromptBeginner5 minmarkdownQuality: 70
> **Note:** This repository contains Anthropic's implementation of skills for Claude. For information about the Agent Skills standard, see [agentskills.io](http://agentskills.io).
[](https://skills.sh/anthropics/skills)
12
General
PromptBeginner5 minmarkdownQuality: 69
Documentation
This directory contains the documentation source code for LlamaIndex, available at https://docs.llamaindex.ai.
13
Recently added
Business
PromptBeginner5 minmarkdownQuality: 31
Act as a Startup Co-Founder
Act as a Startup Co-Founder. You are an experienced entrepreneur with knowledge in business development and strategic planning. Your task is to support the founding team in launching a successful star...
5
General
PromptBeginner5 minmarkdownQuality: 31
- Use ${networkLibrary:Retrofit} or ${networkLibrary2:Ktor} to connect directly to the backend proxy endpoint (e.g.
${proxyEndpoint:https://albaroka.com/chat}).
5
General
PromptBeginner5 minmarkdown
Sync
Detect Spec to Code drift. Scan REQ/DESIGN/TASK specs for references to code that no longer exists, then report drift for review. Run after a hand-edit that moved or deleted code.
3
General
PromptBeginner5 minmarkdown
Retro
Fill an unfilled auto-retro skeleton for a date by running the retrospective skill
4
General
PromptBeginner5 minmarkdown
Checkpoint
Write a timestamped mid-session checkpoint snapshot of decisions, progress, and next actions to .agents/checkpoints/, then link it from the active session log.
4
General
PromptBeginner5 minmarkdown
interface:
display_name: "LLMInternSkill"
5
Browse by outcome
Categories with intent
Writing & Content
3889 skills
Coding & Debugging
9188 skills
Data & Insights
0 skills
Research & Learning
848 skills
Operations & Workflow
0 skills
Product & Growth
0 skills
General
115309 skills
Education
2222 skills
Marketing
1280 skills
Creative
7928 skills
Productivity
3523 skills
Communication
822 skills
Data
5862 skills
Business
2029 skills
Cursor-rules
206 skills
Openclaw
66 skills
Ship agent skills that users can trust.
Keep it simple, prove it fast, and build a library that compounds.