본문으로 건너뛰기
cccskills
무료GitHub에 공개

harness-gepa

Inspect evolved prompt configurations, validate their structure, and view the system prompts they produce. You can also classify failures in run transcripts to support reviews before adopting or changing an agent policy.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome compiles to, or classify failure modes in a run transcript. The `gepaOptimize` loop itself is library-only (bring your own evaluator) and not surfaced here — use `harness-evolve` for sandbox-scored evolution. Degrades gracefully when @metaharness/darwin is absent.

ruvnet/ruflo
설치 방법 보기

이럴 때 유용합니다

  • Reviewing the system prompt before adopting an evolved policy
  • Validating prompt configuration changes in CI
  • Classifying failures in an agent run transcript

포함된 파일(1)

  • SKILL.md3.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Surfaces the GEPA (genetic-evolution prompt-adaptation) library exports from @metaharness/darwin/gepa. Unlike the other skills in this plugin there is no CLI binary behind this — the script dynamic-imports the library (local resolution first, versioned cache install as fallback) and calls the subprocess-safe subset.

When to use

  • Adopting an evolved policy: --op render shows the actual system prompt a genome compiles to — read THAT, not the raw JSON, before wiring a genome into a harness.
  • Auditing a promotion: --op genome loads + validates the shipped cand-6 genome (first holdout-confirmed cheap-tier promotion; provenance ships in the package) or any genome file you point at.
  • CI gate on genome edits: --op validate --alert-on-invalid exits 1 on structural errors.
  • Debugging a bad run: --op analyze --transcript run.json classifies failure modes (GEPA's failure-class taxonomy) from a transcript array.

What is deliberately NOT here

gepaOptimize — the optimization loop takes an in-process evaluate(candidate) callback ("bring your own evaluator") that cannot cross a subprocess boundary. Two supported paths instead:

  1. Library consumers: import { gepaOptimize, loadCand6Genome } from '@metaharness/darwin/gepa'
  2. Sandbox-scored evolution: harness-evolve (darwin CLI evolve), which pairs GEPA with its own sandbox evaluators.

Algorithm

Implementation: scripts/gepa.mjs.

  1. import('@metaharness/darwin/gepa'); on MODULE_NOT_FOUND fall back to a one-time npm install --prefix ~/.ruflo/darwin-cache-<pin> and import the cached dist/gepa/index.js (versioned dir → pin bumps invalidate).
  2. Dispatch --op:
    • genome → loadGenome(fs, path) or loadCand6Genome() + validateGenome
    • validate → validateGenome(rawJson) (raw parse so broken files reach the validator instead of throwing in the loader)
    • render → buildSystemFromGenome(genome, ext?, glob?)
    • analyze → analyzeTranscript(entries)
  3. Emit one JSON object; exit 0 (or 1 under --alert-on-invalid, 2 on bad input).

Examples

node scripts/gepa.mjs --op genome                          # cand-6 + validation
node scripts/gepa.mjs --op render | jq -r .system         # what does cand-6 SAY?
node scripts/gepa.mjs --op validate --path my-genome.json --alert-on-invalid
node scripts/gepa.mjs --op analyze --transcript run.json

Exit codes

  • 0 — op completed (or degraded — darwin not installable)
  • 1 — --alert-on-invalid and validation found errors
  • 2 — config error (unknown op, missing/broken input file)

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

add-model-descriptions

무료

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding newly available router models to chat-ui
  • Writing concise descriptions of model capabilities
  • Updating production and development model entries together
ruvnet/ruflo7.8만2026년 10월 20일 업데이트

adr-create

무료

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Record the reasoning behind adopting a technology
  • Start an ADR for an API or data model change
  • Document an infrastructure decision
ruvnet/ruflo7.8만2026년 10월 20일 업데이트

adr-index

무료

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Index ADRs imported from another project
  • Refresh a graph that differs from files on disk
  • Set up ADR tracking in an existing codebase
ruvnet/ruflo7.8만2026년 10월 20일 업데이트

adr-reindex

무료

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Rebuild the index after deleting an ADR file
  • Remove stale relationships after editing an ADR
  • Reconcile the ADR index on a schedule
ruvnet/ruflo7.8만2026년 10월 20일 업데이트

adr-review

무료

Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Check a pull request before merging
  • Review major code changes against agreed design decisions
  • Find references to superseded ADRs
ruvnet/ruflo7.8만2026년 10월 20일 업데이트

adr-verify

무료

Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Checking ADR integrity after import
  • Blocking CI when ADR issues are found
  • Reviewing ADR data before a release
ruvnet/ruflo7.8만2026년 10월 20일 업데이트

ruvnet의 스킬 모두 보기

이 스킬의 문제 신고