Community코딩 & 개발github.com

grahama1970/benchmark-models

표준 컴플라이언스 QRA 벤치마크를 후보 LLM에 대해 실행하여 정확도, 지연 시간, 비용을 평가합니다.

benchmark-models란 무엇인가요?

이 스킬은 후보 LLM(대규모 언어 모델)에 대해 표준화된 컴플라이언스 QRA(Quality Response Assessment) 테스트를 실행하여 정확도, 지연 시간, 비용을 평가합니다. 모델을 추론 파이프라인에 배포하기 전에 객관적인 성능 비교를 제공하여, 어떤 모델이 특정 컴플라이언스 요구사항(NIST 800-171, AS9100D, CMMC, ITAR, DFARS, DO-178C, MIL-STD 등)에 가장 적합한지 결정하는 데 도움을 줍니다. CLI 도구(`./run.sh`)를 통해 단일 모델 벤치마크 실행, 여러 모델 비교, 마지막 보고서 보기, 드라이 런(LLM 호출 없이 스캐폴드 출력) 등의 기능을 지원합니다. 벤치마크 결과는 `~/.embry/benchmark_results.json`에 저장되며, 테스트 케이스별 정확도, 지연 시간 백분위수(p50, p95), 예상 토큰 비용 등 상세 지표를 제공하여 모델 선택을 지원합니다.

지원 대상~Claude Code~Codex CLI~Cursor✓Antigravity
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/benchmark-models

Installed? Explore more 코딩 & 개발 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

benchmark-models은(는) 무엇을 하나요?

후보 LLM에 대해 표준화된 컴플라이언스 QRA 테스트를 실행하여 정확도, 지연 시간, 비용을 평가합니다. 추론 파이프라인에 배포하기 전에 모델 성능을 측정합니다.

사용법

단일 모델 벤치마크 실행

./run.sh run --model deepseek-v3 --suite compliance-basic

지정된 모델에 대해 /scillm을 통해 20개의 골드셋 컴플라이언스 QRA 질문을 실행합니다. TEST_CASE, EXPECTED, ACTUAL, MATCH, LATENCY_MS 열이 포함된 결과 테이블과 요약 메트릭(accuracy%, latency_p50, latency_p95, estimated_token_cost)을 출력합니다.

여러 모델 비교

./run.sh compare --models "deepseek-v3,llama-3.1-70b" --suite compliance-basic

각 모델에 대해 벤치마크를 실행하고 나란히 비교하는 테이블을 출력합니다.

마지막 보고서 보기

./run.sh report

가장 최근 벤치마크 결과를 ~/.embry/benchmark_results.json에서 읽어와 요약을 렌더링합니다.

드라이 런 (LLM 호출 없음)

./run.sh run --model deepseek-v3 --suite compliance-basic --dry-run
./run.sh compare --models "deepseek-v3,llama-3.1-70b" --dry-run

전체 벤치마크 스캐폴드와 20개 테스트 케이스 및 모의 결과를 출력합니다. LLM 호출은 이루어지지 않습니다.

스위트

  • compliance-basic: NIST 800-171, AS9100D, CMMC, ITAR, DFARS, DO-178C, MIL-STD 및 교차 프로그램 컴플라이언스 드리프트 탐지를 다루는 20개의 골드셋 QRA 질문입니다.

출력

결과는 ~/.embry/benchmark_results.json에 저장되고 표준 출력(stdout)으로 출력됩니다. 보고서에는 질문별 정확도와 모델 선택 결정을 위한 종합 메트릭이 포함됩니다.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

grahama1970/acceptance-contract

Turn a client brief, zip bundle, directory, or single requirements file into a typed acceptance-contract bundle with extracted requirements, acceptance checks, open questions, an immutable-goal draft, and a create-report-backed decision report. Use when users say acceptance contract, brief to requirements, freeze the goal, create immutable goal, amend immutable goal, build a Battle requirements bundle, or extract requirements from this bundle.

grahama1970/agent-ecosystem

Canonical map and shared contracts for the agent-governance ecosystem: the pi.receipt_envelope.v1 boundary envelope, the component graph, and the rules for which component owns which schema. Use when wiring a skill or extension into the shared receipt world, when asking how shame, triage-error, tau, ask, project-watchdog, ops-herdr, ponytail, and Memory fit together, or when validating an envelope.

grahama1970/agentic-evals

Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory validation, or readiness scoring for a skill workflow.

grahama1970/agent-inbox

File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.

grahama1970/agents-registry

Generate and query the centralized agent identity registry. Scans .pi/agents/*/AGENTS.md, parses frontmatter, outputs agents-registry.json and optionally syncs to /memory for semantic search.

grahama1970/agent-status

Artifact-driven status surfaces for long-running project-agent work. Maintains status.json, events.jsonl, proof manifests, and a stale-aware STATUS.html so humans can tell where the agent is, what passed, what is still unproven, and what decision or action is next — without dashboard theater.

grahama1970/align

Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow, high-stakes implementation, plan-iterate, project-infographic, or multi-review work.

grahama1970/analytics

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

grahama1970/analyze-chatterbox-emotions

Evaluate generated Chatterbox voice files as voice-quality artifacts: affect match, arousal/valence proxies, pause placement, intelligibility inputs, clipping, loudness, and discontinuity flags. Use when reviewing Chatterbox emotional tags, pauses, Turbo/base affect delivery, Persona Dream utterance renders, or whether generated speech matches an intended product-facing affect.

grahama1970/analyze-elf

Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled JS/TS source.

grahama1970/animation-vocabulary

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

grahama1970/anonymize-data

Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the oai-trial project. Use for anonymize data, pseudonymize exports, redact policy literals, or discover and explicitly approve fuzzy name aliases. The skill is a thin CLI/Docker interface, not another engine.

grahama1970/anvil

Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.

grahama1970/apple-design

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

grahama1970/argue

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

grahama1970/arxiv

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

grahama1970/ask

Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, ask Pi-native subagents from within Pi, run persona/deep-review workflows, generate image prompts, check OS/project health through composed skills, or run an ask DAG. This skill is the executable /ask runtime; do not replace it with an informal subagent, plain web search, or hand-written review; inside Pi, explicit Pi-native subagent targets are routed through the pi-subagents tool as an Ask target type.

grahama1970/assess

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment analysis. Offer to run after major changes (don't auto-run).

grahama1970/assistant

Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

grahama1970/assistant-lab

Self-improvement workbench for /assistant. All the tools needed to diagnose, train, evaluate, and promote models in a continuous loop. The "warm pond" where /assistant evolves its own inference stack.

관련 스킬