Explore

Find agent skills by outcome

2,187 skills indexed with the new KISS metadata standard.

Showing 24 of 2,187Categories: Productivity, Research, Data, Creative, Communication
Data
PromptBeginner5 minmarkdown

quit-weed

Take a tolerance break or quit cannabis with streak tracking and craving support

0
Data
PromptBeginner5 minmarkdown

FORMAL REVIEW: CAM-BS2025-AEON-006-SCH-03

Salience Delegation & Latent Horizon Preservation

0
Data
PromptBeginner5 minmarkdown

Backend Source

- **Integration tests using a real database must clean up after themselves** — tests run against shared Neon branches. Always delete created rows in `afterAll` so other test suites aren't affected by leftover data. Tests using mock repositories (`createMockContainer`) do not need cleanup.

0
Creative
PromptBeginner5 minmarkdown

RNN Models - CLAUDE.md

This module provides architecture guidance for recurrent neural networks in PHM-Vibench. For available models and configuration, see [@README.md].

0
Creative
PromptBeginner5 minmarkdown

Sponsor Hall of Fame

Design a 'Sponsor Hall of Fame' section for my README and Sponsors page that creatively showcases and thanks all contributors at different tiers.

0
Productivity
PromptBeginner5 minmarkdown

Prompt: Initial Ruleset Generation

Generate initial causal rules \(R_0\) from clustering context.

0
Creative
PromptBeginner5 minmarkdown

```

На основе текста из истории, создай детальное описание одной сцены на английском, а затем иллюстрацию на основе описания. Используй нейтральные обозначения для людей и животных, не имена, например, "мальчик" вместо "Ваня", "женщина" вместо "Анна", "собака" вместо "Жучка", и т.п. Если в тексте больше

0
Data
PromptBeginner5 minmarkdown

Prompt tuning

A core intuition and opinion baked into the design of VLM Caption is that multi-turn conversation can help extract superior information by allowing different questions to be asked, then bring them together with a final summary request. Other VLM scripts or apps are likely just trying to "one shot"

0
Data
PromptBeginner5 minmarkdown

{{base}}

====================================================

0
Productivity
PromptBeginner5 minmarkdown

Role

You are an intelligent agent that completes multi-step tasks.

0
Productivity
PromptBeginner5 minmarkdown

Warning Prompts

generic skill

2
Productivity
PromptBeginner5 minmarkdown

With Skill Evidence for google-flow--google-flow

Agent is prompted to [task description] with this skill loaded.

0
Productivity
PromptBeginner5 minmarkdown

Workflow Engine Guidance

The workflow engine persistence schema is duplicated in RivetKit for inspector transport.

0
Productivity
PromptBeginner5 minmarkdown

pool_value

Generic sync.Pool wrappers with automatic reset functionality.

0
Data
PromptBeginner5 minmarkdown

dux-lite

Dux Lite 项目开发规则模板(基于 dux-php-admin 规范去重整理)。

0
Productivity
PromptBeginner5 minmarkdown

pool_value

Generic sync.Pool wrappers with automatic reset functionality.

0
Data
PromptBeginner5 minmarkdown

DOCS

We keep all important docs in .agent folder and keep updating them, structure like below

0
Data
PromptBeginner5 minmarkdown

- Suggested follow-up actions (prototype scope

data prep

0
Data
PromptBeginner5 minmarkdown

- **Llama 4 / Llama 405B variants (Meta)** — Best open-source frontier performance

excellent for self-hosting

0
Creative
PromptBeginner5 minmarkdown

- Generate a simple

practical starter prompt

0
Productivity
PromptBeginner5 minmarkdown

- **GPT-5 / o3 family (OpenAI)** — Deepest reasoning on very complex structured tasks

best at following extremely long/complex instructions

0
Data
PromptBeginner5 minmarkdown

- **Grok 3 / Grok 4 (xAI)** — Excellent reasoning

real-time knowledge via X

0
Data
PromptBeginner5 minmarkdown

| Data quality | 3 | Mostly clean

some inconsistency |

0
Data
PromptBeginner5 minmarkdown

| **4 – High Feasibility** | Clear logic

consistent data

0