菜单
Load tests API endpoints with progressive concurrency. Measures response times, error rates, throughput, and identifies breaking points. Generates a detailed report with latency percentiles, throughput curves, bottleneck analysis, and optimization recommendations.
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。
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
Use before starting a product, feature, MVP, agent, automation, or integration build to identify the main pre-build risk and choose the smallest validation step. Trigger when the user asks whether to build, scope, validate, prioritize, or sanity-check an idea before implementation.
Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.
Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.
基于 SOC 职业分类
| name | api-load-tester |
| description | Load tests API endpoints with progressive concurrency. Measures response times, error rates, throughput, and identifies breaking points. Generates a detailed report with latency percentiles, throughput curves, bottleneck analysis, and optimization recommendations. |
| tools | Bash, Read, Write, Glob, Grep |
| model | inherit |
Stress-test HTTP endpoints under increasing load, identify breaking points, and produce a report with actionable recommendations.
references/tool-commands.md -- tool invocations (hey/wrk/ab/curl), default concurrency stages, per-stage data to capture.references/metrics-interpretation.md -- latency, throughput, error, breaking-point, and bottleneck classification.references/output-template.md -- exact structure for api-load-report.md, including ASCII charts and scaling table.references/rules-and-examples.md -- safety rules, error handling, and example invocations.Collect from the user. Ask before proceeding if a required input is missing.
Required: endpoint URL(s) (with method, headers, body as needed); expected latency thresholds. Default thresholds if unspecified: p50 < 100ms, p95 < 300ms, p99 < 1000ms.
Optional: concurrent users or range (default ramp 1 to 100); authentication; request payloads; custom headers; test duration (default 10s per stage); ramp pattern (default step ramp, doubling each stage); success criteria (default 2xx); known rate limits; environment label (prod/staging/dev).
Follow these steps in order.
Select a tool. Check in priority order: which hey, which wrk, which ab, which curl. If none of hey/wrk/ab exist, install hey (brew install hey on macOS, go install github.com/rakyll/hey@latest on Linux with Go) or fall back to curl with bash background processes and wait. Verify with a single trivial request against a provided endpoint; diagnose connectivity or auth before continuing.
Validate endpoints. Send one request per endpoint with the specified method, headers, auth, and body. Confirm the status matches the success criteria and record baseline single-request latency. On failure, surface the error and ask whether to skip or fix.
Design the test plan. Build progressive concurrency stages (see references/tool-commands.md for the default progression), trimming or extending to the user's concurrency range. Define per-endpoint method, URL, headers, body, success codes, and timeout (default 30s). Print the plan for review before executing.
Execute stages. For each endpoint, run every concurrency stage sequentially with the selected tool, waiting 2 seconds between stages. Capture and store the per-stage metrics. See references/tool-commands.md for commands, request-count formula, and the metrics list.
Interpret metrics. Compute latency percentiles and profile, throughput curve and ceiling, error rates and onset, the breaking point, and the bottleneck classification. See references/metrics-interpretation.md.
Generate the report. Write api-load-report.md to the current working directory following references/output-template.md exactly, including ASCII throughput and latency charts.
Post-report actions. Print a 3-5 line summary to the console, state the report path, explicitly highlight any critical issues, and offer to re-run specific stages with different parameters.
Apply the safety rules, error handling, and example invocations in references/rules-and-examples.md. Key constraints: never load-test production without explicit confirmation, only test GET by default, mask auth tokens, respect 429 rate limits, count timeouts as failures, and never extrapolate beyond tested ranges.