Skip to main content

ChatGPT skills and prompts

ChatGPT and OpenAI GPT workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.

codingAgent skill

智汇AI 内容引擎 SKILL V6.0

Plan and produce Chinese WeChat articles and spoken-video scripts, from news-topic selection and drafting to HTML formatting, publishing steps, and updates to the workflow’s content records.

Content score 69/100 · provisional32
View skill
codingAgent skill

Add Model Provider

Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.

Content score 68/100 · provisional395k
View skill
codingAgent skill

Antigaslighter

Verify a named artifact, workflow, deployment, or script against observable evidence. Read-only by default, bounded to the requested target, and explicit when evidence is incomplete.

Content score 68/100 · provisional18
View skill
codingAgent skill

Cloudflare

Use Cloudflare API credentials bound in Nuphos to inspect or change Cloudflare account resources.

Content score 68/100 · provisional710
View skill
codingAgent skill

Contribute To Asi

Hill-climb the benchmarks in elizaOS/asi, a JAX continual-reinforcement-learning framework, with optional public payout registration. Use when an agent is asked to improve a measured result, port a method from the literature, fix something that corrupts measurement, decisively close a research direction with paired evidence, or register a public Solana payout address.

Content score 68/100 · provisional129
View skill
codingAgent skill

F Comply

Measure whether a Topping Out rule actually binds, by tempting it at three prompt strictness levels in a throwaway working directory and grading what the session executed, deterministically. Use for /f-comply, "does this rule actually work", "test the NEVERs", "is RULES.md being followed", before trusting a new builder, or before promoting a rule to a hook. Measures existing rules: not for writing them (f-distill promotes a card into the constitution). Not a code gate.

Content score 68/100 · provisional14
View skill
codingAgent skill

Openai Whisper Api

OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.

Content score 68/100 · provisional394k
View skill
codingAgent skill

Openclaw Qa Testing

Run, watch, debug, extend, or explain OpenClaw qa-lab and qa-channel scenarios, artifacts, and live lanes.

Content score 68/100 · provisional395k
View skill
codingAgent skill

Penguin Config

Manage model API keys, default models and per-agent vault secrets with the penguin CLI.

Content score 68/100 · provisional3.2k
View skill
codingAgent skill

Pr Body

分析当前分支的全部变更,自动生成或更新 PR 标题和正文。聚焦内容质量:解释 why、归纳 what、标注测试方式,遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述,或已有 PR 需要更新描述。

Content score 68/100 · provisional659
View skill
codingAgent skill

Security Triage

Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Content score 68/100 · provisional395k
View skill
productivityAgent skill

Knowledge Ops

Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.

Content score 67/100 · provisional301k
View skill
codingAgent skill

Code Review Evaluator

How to run the adversarial code-review evaluator once local tests pass, before the PR opens

Content score 65/100 · provisional12
View skill
productivityAgent skill

Checkpoint Promotion

Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.

Content score 63/100 · provisional43k
View skill
codingAgent skill

Eval Harness First

Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.

Content score 63/100 · provisional43k
View skill
creativityAgent skill

Grpo Rlvr Training

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.

Content score 63/100 · provisional43k
View skill
codingAgent skill

Preference Optimization

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.

Content score 63/100 · provisional43k
View skill
codingAgent skill

Trace To Training Data

Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.

Content score 63/100 · provisional43k
View skill
creativityAgent skill

Vision Sft

Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.

Content score 63/100 · provisional43k
View skill
otherPrompt template

Act as a lawyer and judicial advisor with 25 years of experience in drafting defense memoranda in Saudi courts only, with the condition of adhering to the legal provisions currently in force.

A reusable prompt for asking an AI assistant to work as Act as a lawyer and judicial advisor with 25 years of experience in drafting defense memoranda in Saudi courts only, with the condition of adhering to the legal provisions currently in force..

Content score 60/100 · provisional177k