본문으로 건너뛰기
cccskills
무료GitHub에 공개한국어 소개

release-openclaw-plugin-testing

OpenClaw 플러그인의 공개 전 설치·삭제, 설정 복구, 시작, SDK 호환성과 배포 패키지 동작을 검증하고 결과와 미검증 항목을 정리합니다.

원문원문 설명 보기

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.

연동 도구GitHubDocker
AI 평가80점/ 100설치 방법 보기

이럴 때 유용합니다

  • 공개 전 기본 제공 플러그인 설치·삭제 확인
  • 깨끗한 환경에서 베타 버전 검증
  • 설정 복구와 gateway 시작 확인
  • 외부 플러그인의 SDK 호환성 확인

한국어 소개

할 수 있는 일

OpenClaw 플러그인을 공개 전에 검증하여 배포 패키지로 정상 사용할 수 있는지 확인합니다. 설치, 활성화, 비활성화, 삭제와 함께 doctor를 통한 설정 복구, 설정 쓰기와 다시 읽기, gateway 시작, 외부 플러그인과 공개 SDK의 호환성을 다룹니다. 결과에는 실행 환경, 패키지 버전, 실패 내용, 검증을 건너뛴 이유를 기록합니다.

이럴 때 유용합니다

릴리스 후보나 베타 버전을 확인하고, 기본 제공 플러그인 전체를 점검하거나 공개 전에 부족한 테스트를 찾을 때 유용합니다. 기존 테스트를 먼저 확인한 뒤 추가할 검증과 실행 환경을 선택합니다.

사용 예시

  • “이 베타 버전의 플러그인 설치와 삭제를 깨끗한 환경에서 검증해 주세요.”
  • “설정 복구와 gateway 시작의 확인 계획을 세우고 미검증 항목을 정리해 주세요.”

주의 사항

OpenClaw 개발 및 검증 환경이 필요합니다. 검증 내용에 따라 pnpm, Docker, GitHub Actions, Testbox 등을 사용하며, 실행 환경 선택에는 openclaw-testing도 참고합니다. 실제 서비스는 인증 정보가 있을 때만 확인하며, 외부 사용자나 채널에 접촉하는 작업은 확인을 받아야 합니다.

이 소개문은 공개된 SKILL.md를 바탕으로 AI(OpenAI Codex)가 작성했습니다. 정확한 사양은 아래 원문을 확인하세요.

객관 평가

AI가 SKILL.md의 내용만을 근거로 4가지 관점에서 판정했습니다. 스타 수나 인기도는 판정에 넣지 않았습니다.

지시의 명확성언제 쓰고 무엇을 하는지 알 수 있는가
A양호공개 전 검증의 사용 상황과 설치, 설정 복구, SDK 호환성 등의 대상을 명시합니다.
절차의 구체성절차·입출력·예시가 구체적으로 적혀 있는가
A양호pnpm과 gh 명령 예시 및 결과, 실행 위치, 버전, 생략 사유의 기록 항목을 제공합니다.
안전성전송·삭제·명령 실행 등을 명시하고 있는가
B일부 부족실제 서비스 검증을 인증 정보가 있는 경우로 제한하지만 인증 정보 취급 절차는 제한적입니다.
도입의 용이성필요한 도구나 API 키가 적고 적혀 있는가
B일부 부족pnpm, Docker, GitHub Actions 등을 명시하지만 환경 준비는 다른 스킬을 참조합니다.

총점은 각 항목을 A=25점, B=15점, C=5점으로 더한 값입니다. 2026년 10월 19일 기준으로 AI(OpenAI Codex)가 판정했습니다. 참고용이므로 설치 전에 원문도 확인해 주세요.

평가가 다르다고 생각되면 재검토를 요청하기

어느 항목이 왜 다르다고 생각하는지 적어 주세요. 로그인은 필요 없습니다. SKILL.md와 대조해 평가를 다시 만들고 이곳에 반영합니다.

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

포함된 파일(2)

  • SKILL.md12.4 KB
  • agents/openai.yaml299 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

OpenClaw Pre-Release Plugin Testing

Use this skill when the user asks for plugin release confidence, plugin lifecycle sweeps, package-artifact plugin proof, or "what else should we test before release?" It complements openclaw-testing; use that skill too when choosing the cheapest safe runner or debugging a failing lane.

Goal

Prove the plugin system as a product surface, not just as source tests:

  • bundled plugin lifecycle: install, inspect, enable, disable, uninstall
  • package artifact behavior from a clean HOME
  • doctor/fix/config validation and idempotence
  • config discovery and config round-trip
  • status/log visibility and diagnostics
  • gateway startup/bootstrap with plugin metadata snapshots
  • public SDK compatibility for real external plugins
  • live-ish provider/channel probes only when safe credentials exist

First Checks

From the OpenClaw repo root:

pnpm docs:list
git status --short --branch
pnpm changed:lanes --json

Follow openclaw-testing for dependency ownership and the choice of local or remote proof.

Runner Choice

Prefer this order:

  1. GitHub Package Acceptance for installable-package product proof.
  2. Current dedicated Linux worker for trusted source/package/Docker proof when it has the required dependencies and capabilities.
  3. ci-build-artifacts-testbox.yml Testbox when Docker/package lanes need seeded dist, dist-runtime, and package caches.
  4. ci-check-testbox.yml Testbox for source checks, targeted Vitest, package-boundary checks, or focused Docker lanes.
  5. Workstation targeted commands only for small format/static/unit probes.

Avoid long package Docker runs from a stale sparse worktree. If Testbox sync reports hundreds of changed files or starts deleting package inputs, stop and warm a fresh box from current main, or switch to Package Acceptance.

Existing Baseline

Run or verify these before inventing new coverage:

OPENCLAW_TESTBOX=1 pnpm check:changed
pnpm run test:extensions:package-boundary:canary
pnpm run test:extensions:package-boundary:compile
pnpm test:docker:plugins
OPENCLAW_PLUGINS_E2E_CLAWHUB=0 pnpm test:docker:plugins
pnpm test:docker:plugin-update

For full bundled install/uninstall proof, shard the packaged sweep:

OPENCLAW_BUNDLED_PLUGIN_SWEEP_TOTAL=8 \
OPENCLAW_BUNDLED_PLUGIN_SWEEP_INDEX=<0-7> \
pnpm test:docker:bundled-plugin-install-uninstall

This example partitions the selected package's plugin inventory over shards 0-7. Private QA plugins are source-mode only unless a package explicitly includes them.

Confidence Matrix

Use this matrix for pre-release signoff. Record pass/fail, run URL/Testbox ID, package SHA/version, and skipped-live reason.

SurfaceProofPreferred runner
Package artifactPackage Acceptance suite_profile=package or custom lanesGitHub Actions
Bundled lifecycleSharded test:docker:bundled-plugin-install-uninstallTestbox or release Docker
External pluginstest:docker:plugins and plugins-offlineTestbox/package acceptance
Update no-optest:docker:plugin-updateTestbox/package acceptance
Doctor/fixseeded bad configs + doctor --fix --non-interactivenew Docker/Testbox harness
Config round-tripconfig set/get, inspect, doctor, reload, diff hashnew Docker/Testbox harness
Gateway bootstrapclean HOME, plugin groups enabled/disabled, status JSONnew Docker/Testbox harness
SDK compatibilitydirectory, tgz, and file: external plugins using SDK subpathstest:docker:plugins plus new smoke
Live-ishredacted provider/channel probes only for present envTestbox live lanes

Package Acceptance Plan

Full Release Validation owns final candidate qualification with Q=C and the exact publication tarballs. Use standalone Package Acceptance for diagnostics or postpublish confidence, not as a replacement candidate qualification:

gh workflow run package-acceptance.yml \
  --repo openclaw/openclaw \
  --ref main \
  -f workflow_ref=main \
  -f source=ref \
  -f package_ref=<branch-or-sha> \
  -f suite_profile=custom \
  -f docker_lanes='plugins-offline plugin-update doctor-switch update-channel-switch config-reload mcp-channels npm-onboard-channel-agent' \
  -f telegram_mode=mock-openai

Use source=npm -f package_spec=openclaw@beta for published beta proof. These standalone diagnostic/confidence runs may use trusted current harness code; candidate qualification must retain the frozen candidate's harness instead.

For extended-stable shared publication, require complete exact-target Full Release Validation from the admitted candidate-owned release-ci/* harness at Q=C, with trusted P admission and publication tooling separate. Direct canonical-branch or main producers do not satisfy the protected publisher. Package Acceptance is a post-publish selector smoke:

gh workflow run package-acceptance.yml \
  --repo openclaw/openclaw \
  --ref main \
  -f workflow_ref=main \
  -f source=npm \
  -f package_spec=openclaw@extended-stable \
  -f suite_profile=package \
  -f telegram_mode=mock-openai

Record the resolved version. Still verify every package and selector in the tag's all-publishable inventory; one smoke is not registry readback.

Plugin npm Artifact Qualification

For a publication candidate, Full Release Validation owns plugin npm artifact qualification. Supply its publication selection at dispatch; the all-group parent invokes plugin-npm-release.yml in artifact-only mode against the exact Release SHA, requires successful tarball readback, and records the immutable aggregate descriptor in publicationArtifacts.pluginNpm. Release Prepare and publication must adopt that exact descriptor rather than repacking plugins.

Use a standalone trusted-workflow preflight only for a focused diagnostic or a selected-plugin repair that is outside a regular publication candidate:

release_sha="$(git rev-parse origin/release/2026.7.1)"
gh workflow run plugin-npm-release.yml \
  --repo openclaw/openclaw \
  --ref main \
  -f preflight_only=true \
  -f publish_scope=selected \
  -f plugins=@openclaw/meta-provider \
  -f ref="${release_sha}" \
  -f npm_dist_tag=default

Do not pass release_publish_run_id. Require the workflow to finish verify_plugin_npm_preflight successfully. Record the run URL, workflow SHA, and source SHA. The workflow first creates the staging/readback artifact plugin-npm-package-source-<source-sha>-<extension-id> containing npm-pack.json, preflight-manifest.json, and the tarball. It then uploads the final consumer artifact plugin-npm-package-<extension-id>-<version>-<route>-<run-id>-<attempt> containing the tarball and plugin-publication-manifest.json.

Record the final artifact name and digest separately. The manifest uses openclaw.plugin-publication-artifact/v1 and records the target SHA, package manifest hashes, publication route and policy, and tarball hashes and inventory. This standalone proof is validation-only; it does not authorize or stage publication and cannot replace Full Release Validation's manifest-bound descriptor. The artifact inventory, rather than the unpacked source tree, is the security and package-content boundary: source-only fixtures are irrelevant. Package-owned test and fixture paths outside shipped runtime and skill assets fail qualification; shipped runtime remains security-scanned. Bundled node_modules stays with dependency evidence rather than plugin-source policy. The separate trusted_publisher_preflight=true OIDC check requires a protected release-publish/<tooling-sha12>-<epoch> dispatch tag and runs in npm-publish. Real publication also requires that tooling tag; a direct human dispatch waits for its npm-release approval job before publishing. For an already-published version, require npm dist.integrity and dist.shasum to match the verified tarball. Treat only missing or provably older dist-tags as repairable; newer or incomparable selectors are a blocker.

New Testbox Harness Plan

If more certainty is needed, add or run a plugin-lifecycle-matrix Docker lane that uses one package tarball and sharded plugin lists. Per plugin:

  1. Start with a clean HOME.
  2. Capture plugins list --json.
  3. plugins install <id>.
  4. plugins inspect <id> --json.
  5. plugins disable <id>, then assert disabled visibility.
  6. plugins enable <id>, except config-required plugins without config.
  7. plugins registry --refresh.
  8. doctor --non-interactive.
  9. plugins uninstall <id> --force.
  10. Assert the plugin's plugins.entries value is exactly { enabled: false }, while its allow/deny entries, install record, managed directory, and bundled runtime load paths are gone. Use the existing harness's source-qualified uninstall expectations for historical targets.
  11. Assert diagnostics contain no level: "error" and output redacts secret-looking values.

Keep memory-lancedb special: it is config-required. First assert install does not enable it without embedding config, then run a second configured case.

Doctor/Fix Matrix

Seed bad states and require doctor --fix --non-interactive to repair them, then run doctor again and require idempotence:

  • stale plugins.allow
  • stale plugins.entries
  • stale channel config for missing channel plugin
  • invalid plugins.entries.<id>.config
  • packaged bundled path in plugins.load.paths
  • legacy plugins.installs
  • disabled channel/plugin config that must not stage runtime deps
  • root-owned global package tree that must remain unmodified

Gateway Bootstrap Matrix

Start packaged OpenClaw in Docker with clean state:

  • provider plugins enabled, no credentials: ready with warnings, no crash
  • channel plugins configured disabled: no runtime deps staged
  • startup-activation plugins enabled: ready and reflected in status
  • invalid single plugin config: bad plugin skipped/quarantined, others remain

Assert:

  • gateway reaches ready
  • openclaw status --json includes plugin diagnostics
  • openclaw plugins inspect --all --json is parseable
  • package tree is not mutated
  • logs contain no raw tokens

Config Round-Trip Representatives

Use representative plugin families instead of every plugin for deep config round-trip:

  • providers: openai, anthropic, mistral, openrouter
  • channels: telegram, discord, slack, whatsapp
  • memory: memory-lancedb
  • feature/runtime: browser, acpx, tokenjuice

For each representative:

  1. Write config through CLI when possible.
  2. Read it back through config get or JSON.
  3. Run plugins inspect.
  4. Run doctor --non-interactive.
  5. Trigger gateway config reload if applicable.
  6. Compare config hash before/after no-op commands.

External SDK Smoke

In a package Docker lane, create tiny external plugins and install them from:

  • local directory
  • .tgz
  • file: npm spec

Cover CJS and ESM shapes, plus at least one plugin importing focused openclaw/plugin-sdk/* subpaths. Assert plugins inspect sees its tool, gateway method, CLI command, or service.

Live-Ish Probe Rules

Before live-ish work, source allowed env in Testbox and generate a redacted availability matrix: present/missing only, never values.

Only run probes for credentials that exist. Prefer auth/catalog/status probes over sending user-visible messages. If a probe might contact an external user, channel, or workspace, stop and ask the user.

Reporting

Report in this shape:

package/ref:
tbx ids / run urls:
matrix:
  bundled lifecycle:
  package acceptance:
  doctor/fix:
  gateway bootstrap:
  config round-trip:
  sdk external:
  live-ish:
failures:
skips:
next highest-value gap:

Say clearly when a failure is Testbox sync/env damage rather than product behavior, and prove that with a clean rerun or current-main comparison.

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

1password

무료

Set up and authenticate the 1Password CLI, then supply stored passwords and API keys to commands or configuration. The skill covers desktop integration, service accounts, and interactive sign-in while keeping secrets out of chat and logs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Setting up the 1Password CLI
  • Supplying API keys to commands
  • Using service account authentication in CI
openclaw/openclaw39.2만2026년 10월 18일 업데이트

acp-router

무료요약 있음AI 평가 80점

OpenClaw에 전달한 자연어 요청을 Claude Code 같은 외부 코딩 에이전트로 연결합니다. ACP나 acpx로 작업을 시작하거나 이어가며 대화 맥락을 유지합니다.

  • 스레드에서 Claude Code 시작
  • 외부 에이전트의 기존 작업 계속
  • acpx로 직접 지시 전달
openclaw/openclaw39.2만2026년 10월 18일 업데이트

Add a model provider to OpenClaw and verify it with a real response. The skill validates configuration, keeps credentials in environment or file references, and reports test results and any default model changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding a model provider to OpenClaw
  • Configuring credentials through environment or file references
  • Checking whether a model returns a real response
openclaw/openclaw39.2만2026년 10월 18일 업데이트

Prepare an agent activity transcript for a GitHub pull request or issue. Extract relevant prompts, decisions, and results from local logs, remove sensitive material, and preview the edited record before separately authorized publication.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Preparing an agent activity record for a pull request
  • Extracting task-relevant prompts and results from local logs
  • Previewing a transcript with sensitive information removed
openclaw/openclaw39.2만2026년 10월 18일 업데이트

Manage Apple Notes on macOS through memo, a command-line tool. Create, browse, search, edit, delete, and move notes between folders, or export selected notes to HTML or Markdown for use outside the app.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Creating notes with titles
  • Finding notes by folder or approximate search
  • Editing notes and organizing them into folders
openclaw/openclaw39.2만2026년 10월 18일 업데이트

apple-reminders

무료요약 있음AI 평가 70점

Mac에서 Apple Reminders의 기한이 있는 할 일을 확인하고 추가·편집합니다. 목록 관리와 완료·삭제를 통해 iPhone이나 iPad에서 보는 작업을 정리합니다.

  • 오늘 할 일과 기한이 지난 작업 확인
  • 기한이 있는 개인 할 일 추가
  • iPhone과 iPad에서 보는 작업 정리
openclaw/openclaw39.2만2026년 10월 18일 업데이트

openclaw의 스킬 모두 보기

이 스킬의 문제 신고