Operations and SOPs

A skill your agent uses to derive a deterministic reject/pass verdict from a draft@1 artifact's open-defect count, emitting a verdict@1 artifact for a branch to route on.

s0912758806p/agentic-sop-to-work

SOP 制定 Skill：帮助 Manager 与人类协作，从零设计一套任务执行 SOP. An agent skill from kid0317/crewai_mas_demo.

kid0317/crewai_mas_demo

Encrypt files and configs with Mozilla SOPS. An agent skill from sickn33/agentic-awesome-skills.

sickn33/agentic-awesome-skills

Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph…

agentsope/SkillAlchemy

标准 SOP：集群巡检 checkcluster/checklist 与 RCA 入口（rcarun/rcalist）。用户要健康检查、巡检时使用；RCA 场景映射与手动降级详见 obdiag-rca skill；与 observer-log-analysis、observer-sql-analysis、obproxy-log-analysis 分工明确。

oceanbase/obdiag

UiPath solution planner & designer. An agent skill from UiPath/skills.

UiPath/skills

업무 프로세스를 문서화하고 표준화합니다. An agent skill from modu-ai/moai-cowork.

modu-ai/moai-cowork

온라인 유료 커뮤니티 개설 전체 프로세스를 지원하는 에이전트 조직 스킬. An agent skill from bam-bam-2/solo-skills.

bam-bam-2/solo-skills

Atmos Secrets: declarative secrets.vars, !secret, cloud/Vault/1Password/SOPS backends, init/set/get/import/push/pull/shell/exec/validate, masking, and CI validation

cloudposse/atmos

审读用户提供的生命科学或生物医学论文、PDF、摘要、正文、figure、panel、caption 或截图，定位核心科学问题，逐图解释实验设计和证据链，审计机制、因果性、rescue、方法边界、正交验证与局限。材料缺失时请求补充或转介检索；不提供医疗建议、临床决策或可直接执行的湿实验 SOP。

xuzhougeng/wisp-science

Deployment workflows, pre-deploy validation, and smoke testing patterns.

bybren-llc/safe-agentic-workflow

Linear ticket management best practices. An agent skill from bybren-llc/safe-agentic-workflow.

bybren-llc/safe-agentic-workflow

Create Standard Operating Procedures after solving novel issues, establishing patterns, or documenting workflows.

qf-studio/navigator

Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval.

agentsope/SkillAlchemy

Re-ingest-correctness SOP for production RAG. An agent skill from agentsope/SkillAlchemy.

agentsope/SkillAlchemy

Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework.

agentsope/SkillAlchemy

Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a…

agentsope/SkillAlchemy

Security-first SOP for multi-tenant RAG systems. An agent skill from agentsope/SkillAlchemy.

agentsope/SkillAlchemy

Lifecycle SOP for per-model prompt artifacts — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset…

agentsope/SkillAlchemy

A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…

alirezarezvani/claude-skills

标准 SOP：多集群发现 listobdiagclusters、当前会话 showcurrentcluster、/use 切换与 clusterconfigpath 定向。多套 ~/.obdiag/.yml、切换默认集群、或一句话点名某集群时使用。

oceanbase/obdiag

Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft regardless of how routing reached it.

s0912758806p/agentic-sop-to-work

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer.

agentsope/SkillAlchemy

When the user needs to create SOPs, playbooks, runbooks, or other operational documentation that defines how a recurring process should be executed.

shawnpang/startup-founder-skills

A skill your agent uses when the user says 'create SOP', 'write SOP', 'standard operating procedure', 'document process', 'process documentation', 'runbook', 'playbook', or is creating step-by-step…

cwinvestments/memstack

经典交易策略参考范式指南：提供短线（唐奇安突破/RSI极值回归）、波段（EMA双均线/布林带下轨回归）、长线（200日均线基线/12月动量）6大策略原理、参数调优、8项回测指标研读与风险防范 SOP。

zhu1090093659/dsh-trading

Write GCP-compliant standard operating procedures for laboratory, clinical, or research workflows; use when a reproducible SOP with roles, steps, and control points is required.

aipoch/medical-research-skills

营销项目经理智能体，负责统筹营销创作流程，根据用户需求选择并加载对应的SOP，协调其他智能体完成营销内容创作. An agent skill from jeffstric/ZJT.

jeffstric/ZJT

Query project knowledge graph. An agent skill from qf-studio/navigator.

qf-studio/navigator

Audit and repair an internal knowledge base — staleness, ownership gaps, orphans, duplication, and findability.

borghei/Claude-Skills

Map, measure and improve business processes — SIPOC and swimlane capture, cycle-time and bottleneck analysis, handoff diagnosis, and a payback-ranked improvement backlog.

borghei/Claude-Skills

Cut software and services spend through seat-utilisation analysis, redundant-tool detection, and renewal-timing leverage.

borghei/Claude-Skills

Vendor lifecycle — weighted selection scorecards, risk tiering, renewal and notice-deadline tracking, spend concentration, and SLA credits.

borghei/Claude-Skills

Walks the documentation dependency web after a CLI code change and reports which downstream files (skills, SOPs, READMEs, plugin references) are out of sync.

ItamarZand88/CLI-Anything-WEB

写法律 Skill 前的前置对齐步骤——通过苏格拉底式提问把零散的法律经验/素材/直觉厘清为结构化 Brief（legal-skill-brief/v1），交给 skill-creator 编译。适用于律师想把文书经验、办案 SOP、咨询记录做成 Skill 的场景。不适用于非法律类 Skill 创建，也不适用于用户已提供完整可执行 Brief 且明确要求直接编译的情况。

cat-xierluo/legal-skills

Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work.

tobihagemann/turbo

A skill your agent uses when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether…

NVIDIA/skills

Construction law analysis covering FIDIC (2017 suite), PSSCOC, SIA Conditions, NEC4, and JCT.

LeoYeAI/openclaw-master-skills

VP of Engineering advisor on org design, productivity, quality, delivery, and capacity planning.

borghei/Claude-Skills

SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that a coder-agent reliably respects your codebase's…

agentsope/SkillAlchemy

Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic.

agentsope/SkillAlchemy

Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call.

agentsope/SkillAlchemy

Decomposed, multi-criteria metric design for LLM pipelines. An agent skill from agentsope/SkillAlchemy.

agentsope/SkillAlchemy

The compile-readiness gate for prompt auto-optimization. An agent skill from agentsope/SkillAlchemy.

agentsope/SkillAlchemy

Build a held-out eval set, run it on every prompt/model change, and block regressions in CI.

agentsope/SkillAlchemy

Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API?

agentsope/SkillAlchemy

Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the backend, not just wiring a typing animation in the UI.

agentsope/SkillAlchemy

Analyze a repository and generate comprehensive architecture and workflow documentation.

mikeyobrien/rho