Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

evolve

Start or monitor an evolutionary development loop

4.90k repo starsObserved in 1 repos
Agent Building

lossless-claw

Configure, diagnose, and use lossless-claw effectively in OpenClaw, with emphasis on key settings, summary health, and recall-tool usage.

4.88k repo starsObserved in 2 repos
Agent Building

building-with-zep

Guide for building, designing, reviewing, evaluating, and troubleshooting applications that use Zep — agent memory built on temporal Context Graphs, for use cases needing low-latency retrieval, one or many users and agents, multi-source ingestion, and governance. Use whenever you write or design code that integrates Zep — adding memory or long-term context to an agent or chatbot, ingesting chat/business/document/JSON data into a Context Graph, retrieving a Context Block or searching the graph, choosing between user graphs and standalone graphs, scoping graphs, defining a custom ontology or custom instructions, or deciding how to evaluate and tune Zep for a use case. Triggers on requests like "add memory to my agent", "integrate Zep", "store this in Zep", "search the Zep graph", "set up a Zep ontology", "how should I structure my Zep graphs", "why is Zep not returning the right context", "help me evaluate Zep", or "make my agent remember users".

4.77k repo starsObserved in 1 repos
Agent Building

zep-eval-harness

Run and manage the Zep eval harness pipeline — document chunking, user ingestion, document ingestion, evaluation, graph inspection, and results analysis. Use when the user asks to run eval harness scripts, use the Zep eval harness, get terminal commands for eval harness operations, chunk documents, ingest users or documents into Zep, run evaluations, inspect graphs, compare evaluation runs, analyze completeness/accuracy metrics, or work with the eval harness data/config/runs directories. Also triggers on "run the harness", "start ingestion", "run evaluation", "chunk the documents", "compare runs", "analyze results", or any reference to the eval harness pipeline.

4.77k repo starsObserved in 1 repos
Agent Building

prompt-token-efficiency

Rewrite prompts for minimal tokens, maximal clarity, and low ambiguity for LLM consumption.

4.76k repo starsObserved in 1 repos
Agent Building

vulnresearch-orchestrator

Five-stage modular vulnerability pipeline orchestrator. Delegates scan → detect → verify → patch → exploit through OPPLAN objectives. Load at orchestrator startup.

4.72k repo starsObserved in 2 repos
Agent Building

engagement-startup

Mandatory first-turn startup procedure — checks for existing engagements, resume/new selection, workspace initialization.

4.72k repo starsObserved in 1 repos
Agent Building

structured-questions

How to use ask_user_question — the single operator-input channel for every interview question, including free-form fields via allow_other=true.

4.72k repo starsObserved in 1 repos
Agent Building

sn-update

Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills", "更新 sensenova skills", "更新 sn skills", "刷新 sn-*", "升级 sn-* skills", or names a specific sn-* skill to update (e.g. "更新 sn-ppt-standard", "refresh sn-image-base"). Default scope is the whole sn-* bundle; if the user names specific skills, update ONLY those.

4.71k repo starsObserved in 3 repos
Agent Building

agent-goal

Create a slash-command `/goal` for long-running Codex or Claude Code work when the user explicitly asks for a `/goal`, agent goal, or completion condition. Outputs one goal line with the objective, starting context, validation evidence, and stop condition.

4.70k repo starsObserved in 1 repos
Agent Building