菜单
Template for creating a new Agent Skill. Copy this folder, rename it to your skill's kebab-case name, and fill in every section. Use this as the starting point whenever you author a new skill for the AgentSkills library.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Designs and analyzes A/B tests end-to-end — frames a sharp hypothesis, computes required sample size and test duration, runs significance tests (two-proportion z-test, Welch's t-test, chi-square), reports confidence intervals and lift, and flags common pitfalls like peeking, multiple comparisons, and Simpson's paradox. Use this skill when the user mentions A/B testing, split testing, experiment design, conversion-rate experiments, statistical significance, p-values, sample size or power calculations, "did this experiment win", minimum detectable effect (MDE), or asks to interpret experiment results honestly. Includes a runnable stats script (scripts/abtest.py).
Authors Architecture Decision Records (ADRs) that capture context, considered options with trade-offs, the chosen decision, and its consequences. Use this skill when the user wants to write, draft, document, or revise an architecture decision, an ADR, a design decision record, a technical decision log, or asks "why did we choose X" / "we need to record this decision" / "document this trade-off" for things like database choice, framework selection, API style, build vs. buy, or deprecating a component.
Designs clean, consistent REST and GraphQL APIs covering resource modeling, URL structure, versioning, pagination, filtering, error formats (RFC 9457 Problem Details), idempotency, authentication, rate limiting, and machine-readable contracts (OpenAPI 3.1 / GraphQL SDL). Use this skill when designing a new API or endpoint, reviewing an API design, choosing REST vs GraphQL, deciding on versioning or pagination strategy, defining error responses, adding idempotency keys, writing or critiquing an OpenAPI/GraphQL schema, or establishing API style guidelines and naming conventions.
Writes precise, complete reference documentation for HTTP/REST APIs and authors valid OpenAPI 3.1 specifications, including endpoint pages, request/response schemas, parameter tables, authentication, pagination, code samples, and error tables. Use this skill when the user asks to "document an API", "write API reference docs", "create an OpenAPI/Swagger spec", "document these endpoints", "write a REST API reference", "add request/response examples", "document error codes", "describe API parameters", or convert code/routes into API documentation.
Systematically reduces AWS cloud spend by right-sizing over-provisioned compute, finding and eliminating idle or orphaned resources, committing to Savings Plans and Reserved Instances, and enforcing cost-allocation tagging. Use this skill when the user asks to "reduce AWS bill", "optimize cloud costs", "find idle EC2/RDS/EBS", "right-size instances", "should I buy a Savings Plan or Reserved Instance", "set up cost allocation tags", "why is my AWS bill so high", or wants a structured FinOps cost-reduction plan.
Writes robust, safe, shellcheck-clean Bash scripts using strict mode, defensive quoting, error traps, safe temp files, and signal handling. Use this skill when authoring or reviewing shell/Bash scripts, when asked to "harden a bash script", "add strict mode", "fix shellcheck warnings", "make this script safe", debug silent failures, unquoted-variable bugs, word-splitting/globbing issues, or to add cleanup traps and error handling.
| name | 0-template |
| description | Template for creating a new Agent Skill. Copy this folder, rename it to your skill's kebab-case name, and fill in every section. Use this as the starting point whenever you author a new skill for the AgentSkills library. |
| license | MIT |
Copy this folder to a new top-level
<your-skill-name>/folder in the repo root, rename it, and replace this content. Delete this blockquote when done.
One short paragraph: what this skill does and the situations it applies to.
Keywords: comma, separated, discovery, terms
Use a table or bullet heuristics to help the agent choose between options.
| If… | Then… |
|---|---|
| condition A | action A |
| condition B | action B |
Show a concrete input and the expected output. See examples/sample.md for a fuller example.
references/guide.md — deep reference material (loaded only when needed).scripts/run.py — runnable helper.examples/sample.md — worked example.