pragmatic-programmer
Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices",…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Agents & models
26,336 results
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…
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…
finetuning-method-selection
Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any…
grpo-rlvr-training
Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically…
hermes-tweet
Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and approval-gated private or state-changing…
langchain-architecture
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI…
lora-qlora-recipes
Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration,…
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…
prompt-engineering-patterns
This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug…
quantized-export
Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes…
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI,…
recsys-pipeline-architect
Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by…
session-guard
Use when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts ignoring rules it followed earlier, when…
team-communication-protocols
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid.…
agnes-ai-generation
Call Agnes AI / Sapiens AI generation APIs for text, image, and video. Use when the user asks to use Agnes models, Agnes Image, Agnes Video, Agnes 2.0 Flash,…
agent-orchestration
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous…
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search,…
agent-email-cli
Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the…
cc-use
Delegate longer coding, troubleshooting, testing, or interactive CLI work to the inner command-line coding Agent in tmux, while the current outer Agent is responsible for breaking down the task, reading stable screen snapshots, correcting direction, performing final acceptance, and destroying the inner session after this task ends. Applicable when the user explicitly requests using cc-use, wants to delegate long implementation work to the inner Agent, needs to do real…
self-improving-agent
Use after a failure, user correction, repeated workflow problem, or validated success reveals a reusable lesson. Captures bounded redacted candidates, runs…
ziniao-role
Ziniao role management: querying, creating, modifying, and assigning roles, and viewing permissions. Used when users need to view the role list, create/modify roles, assign roles to employees, or view role members.
ziniao-skill-maker
Create a custom Skill for ziniao-cli. Use when the user needs to encapsulate ziniao API operations into a reusable Skill (wrapping atomic APIs or orchestrating multi-step workflows).
ziniao-store
Use when a request concerns the local Ziniao/ZClaw browser, a store name or ID, listing/resolving/opening/reusing/closing a store browser, or a store-scoped task…