OpenLogi Device Fixture Contribution
AprilNEA/OpenLogi
Guides recording, privacy review and offline verification of OpenLogi device fixtures with the fixture contribute and verify commands, without treating replay as proof of hardware behavior.
专家型产物质量门禁 — 当任务涉及代码、文档、示例、fixture、quick start、技术方案、报告或用户指出“不专业 / 像初级 / 示例误导 / 没有资深架构视角”时使用；要求区分生产推荐路径、框架原生能力、测试夹具边界、反模式与证据矩阵。
AGPL-3.0Auto-check passed
Install Expert Output Quality
$ npx skills add devcodex-labs/devcodex --skill expert-output-quality -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install devcodex-labs/devcodex expert-output-quality --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/expert-output-quality .claude/skills/expert-output-quality && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "expert-output-quality" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-quality into .claude/skills/expert-output-quality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-output-quality", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-qualityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add devcodex-labs/devcodex --skill expert-output-quality -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install devcodex-labs/devcodex expert-output-quality --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .agents/skills && cp -r skills-src/content/skills/expert-output-quality .agents/skills/expert-output-quality && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "expert-output-quality" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-quality into .agents/skills/expert-output-quality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-output-quality", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add devcodex-labs/devcodex --skill expert-output-quality -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install devcodex-labs/devcodex expert-output-quality --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/content/skills/expert-output-quality .cursor/skills/expert-output-quality && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "expert-output-quality" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-quality into .cursor/skills/expert-output-quality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-output-quality", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/devcodex-labs/devcodex.git --path content/skills/expert-output-quality--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add devcodex-labs/devcodex --skill expert-output-quality -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install devcodex-labs/devcodex expert-output-quality --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/content/skills/expert-output-quality .gemini/skills/expert-output-quality && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "expert-output-quality" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-quality into .gemini/skills/expert-output-quality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-output-quality", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install devcodex-labs/devcodex expert-output-qualityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add devcodex-labs/devcodex --skill expert-output-quality -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .github/skills && cp -r skills-src/content/skills/expert-output-quality .github/skills/expert-output-quality && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "expert-output-quality" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-quality into .github/skills/expert-output-quality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-output-quality", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add devcodex-labs/devcodex --skill expert-output-quality -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install devcodex-labs/devcodex expert-output-quality --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/content/skills/expert-output-quality .opencode/skills/expert-output-quality && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "expert-output-quality" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/expert-output-quality into .opencode/skills/expert-output-quality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-output-quality", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
expert-output-quality- GitHub stars
- 439
- Token cost
- ~1.4k tokens
- SKILL.md length
- 257 words
- Files
- 2
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
专家型产物质量门禁 — 当任务涉及代码、文档、示例、fixture、quick start、技术方案、报告或用户指出“不专业 / 像初级 / 示例误导 / 没有资深架构视角”时使用；要求区分生产推荐路径、框架原生能力、测试夹具边界、反模式与证据矩阵。
- Works in 3 steps: 判断产物类型和目标受众：用户、维护者、调用方、审核人或发布方。 → 选择角色基线：技术专家、资深架构师、领域专家或用户文档作者。 → 先反查项目和框架：已有…
- SKILL.md covers 定位, 触发条件, 核心门禁 and 执行步骤, plus 4 more sections
- Calls npm and node
What it does
Expert Output Quality is an agent skill from devcodex-labs/devcodex. 专家型产物质量门禁 — 当任务涉及代码、文档、示例、fixture、quick start、技术方案、报告或用户指出“不专业 / 像初级 / 示例误导 / 没有资深架构视角”时使用；要求区分生产推荐路径、框架原生能力、测试夹具边界、反模式与证据矩阵。
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `intent.json`).
The repository describes itself as: Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts. The licence is AGPL-3.0.
Example prompts
- “不专业 / 像初级 / 示例误导 / 没有资深架构视角”
- “/expert-output-quality”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 判断产物类型和目标受众：用户、维护者、调用方、审核人或发布方。
- 选择角色基线：技术专家、资深架构师、领域专家或用户文档作者。
- 先反查项目和框架：已有 helper、middleware、plugin、types、schema、runtime dispatcher、配置系统、文档约定和官方 API。
What it can do on your machine
Read from SKILL.md and the folder at commit 1dd4525. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npmnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Expert Output Quality loads about 1.4k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 257 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from devcodex-labs/devcodex at commit 1dd4525, republished under its AGPL-3.0 licence (© devcodex-labs). 257 words, ~1,426 tokens.
Download SKILL.mdSave it as
.claude/skills/expert-output-quality/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- expert-output-quality
- description
- 专家型产物质量门禁 — 当任务涉及代码、文档、示例、fixture、quick start、技术方案、报告或用户指出“不专业 / 像初级 / 示例误导 / 没有资深架构视角”时使用；要求区分生产推荐路径、框架原生能力、测试夹具边界、反模式与证据矩阵。
Expert Output Quality Skill
定位
本 Skill 防止 AI 产物停留在“能跑示例”或“解释 fixture”的初级层面。它要求代码、文档、示例、方案和报告体现技术专家、资深架构师或领域专家视角：先给生产推荐路径，再说明测试夹具、演示代码、兼容路径和反模式的边界。
触发条件
| 场景 | 是否触发 |
|---|---|
| 代码、文档、示例、fixture、quick start、README、站点文档、技术方案、报告需要交付给用户或维护者 | 必须 |
| 用户指出“不专业”“像初级”“这不是推荐写法”“示例误导”“怎么又写成开发文档” | 必须 |
| 文档或报告需要解释测试 fixture、demo、mock、兼容路径、历史写法或反模式 | 必须 |
| 框架、SDK、库、运行时、权限、路由、中间件、鉴权、缓存、事务、队列、ORM、UI 组件等存在原生能力 | 必须 |
| 纯内部临时草稿、只读事实查询、无需产物沉淀的短问答 | N/A + skipReason |
核心门禁
| Gate | 要求 | 证据 |
|---|---|---|
ExpertOutputQualityGate | 输出必须体现对应角色的专业判断，不只复述代码或示例现象 | 角色定位、推荐路径、风险和取舍 |
ExpertRoleBaselineGate | 根据任务选择技术专家 / 资深架构师 / 领域专家 / 产品化文档作者视角 | 角色与受众说明 |
ProductionRecommendedPathGate | 先写生产推荐路径，再写测试、demo、fixture、兼容或历史路径 | recommendedPath / nonRecommendedPath |
FrameworkNativeCapabilityFirstGate | 先检查框架、SDK、平台或项目现有能力，避免手写重复机制 | official / repo-local / runtime evidence |
FixtureBoundaryDisclosureGate | fixture、mock、样例配置、硬编码单例必须标明不是生产主路径 | fixtureBoundary、allowedUse、forbiddenUse |
ExampleArchitectureFitnessGate | 示例要符合项目推荐架构，避免在 route、controller、UI 或测试里重复声明框架已承载的资源配置 | architectureFit、consumerImpact |
AntiPatternContrastGate | 必要时列出“错误写法 / 为什么错 / 正确写法”，但不把反模式放成主路径 | antiPattern、replacement |
ExpertEvidenceMatrixGate | 关键建议必须绑定代码、类型、官方文档、运行时、测试、构建或用户路径证据 | evidenceMatrix |
OperationExplanationContractV1 | 面向用户或维护者的操作说明必须写清目标、前置条件、输入、状态影响、结果形态、结果来源、失败语义、下一步和证据 | operationId、userGoal、resultSource、failureSemantics |
ResponseProvenanceClosureGate | 报告和最终回复中“已完成 / 已验证 / 推荐”的结论必须能追溯到文件、命令、测试、运行时或用户确认来源 | resultSource、evidence、freshness |
MeasuredVerificationStandard | 将探针/validate/测试标为已验证时，必须走生产入口命令（如 npm run test:core、node scripts/test-spec-governance.js）并记录 exitCode；隔离 harness 未复用 createCanonicalAwareReader 时只能标非权威实验，不得写成 V84/V# 成败 | command、exitCode、authorityPath、parityEvidence |
CodeTruthEvidenceMatrixGate | 重要需求、技术方案和修复结论必须绑定 repo path、符号/契约、当前行为、反证探针和差距，不能只靠文档自洽 | repoPath、symbol、currentBehavior、negativeProbe、gap |
SolutionFitAgainstRepoGate | 方案必须说明复用点、消费者、变更面、回滚和保持现状成本，避免凭空设计 | reusePoint、consumer、rollback、statusQuoCost |
ControlPlaneAdviceInventoryGate | 控制面/复审分级/Gate 体系/规范如何改等建议路径，在宣称最优或可实施前必须对 source-root 做 ExistingCapabilityInventory；禁止仅用 user-global 镜像或对话记忆；与 analyze-default 同名门禁同向（PI-176 / PF-181） | inventory 表、reusePoint、gap、禁平行声明 |
UniqueRecommendationBeforeConfirmGate | 多方案比较收敛后只能有一个推荐方案或一个明确组合推荐；任何用户须决策的路径建议（含完成态下一步）均适用 | recommended=1、alternatives、reason |
NoPreferenceMenuAfterConvergenceGate | 已由证据收敛且用户授予 auto 时，不再要求用户选择无意义偏好菜单 | auto evidence、decisionOwner |
UniqueNextStepRecommendationGate | 完成态 free-text「下一步/后续建议」仅 1 条主动作；禁止「或/或者」并列双可执行路径（PF-172） | single action、no or-fork、optional 不推荐 block |
执行步骤
- 判断产物类型和目标受众：用户、维护者、调用方、审核人或发布方。
- 选择角色基线：技术专家、资深架构师、领域专家或用户文档作者。
- 先反查项目和框架：已有 helper、middleware、plugin、types、schema、runtime dispatcher、配置系统、文档约定和官方 API。
3a. 若任务为控制面/复审等级/Gate 设计建议或「能否按 X 拆体系」：先执行
ControlPlaneAdviceInventoryGate（source-root inventory），再给推荐路径；未 inventory 不得写已验证最优。 - 给出生产推荐路径：职责边界、使用方式、扩展点、失败处理、验证路线和维护成本。
- 再标注非主路径：fixture / mock / demo / legacy / compat 的用途、风险和禁止外推范围。
- 对容易误导的示例追加反模式对比：错误写法、为何不推荐、正确替代、如何迁移。
- 建立
ExpertEvidenceMatrixGate：每个关键判断绑定至少一种事实证据；无法验证时写unknown / blocked / N/A + skipReason。 - 报告或复审中发现产物仍像初级解释时，先执行
ReviewEscapeRecordGate，说明此前清单为什么没有覆盖专业度维度，再补本 Skill 重跑。
输出字段
## ExpertOutputQualityGate
| 字段 | 内容 |
|------|------|
| roleBaseline | 技术专家 / 资深架构师 / 领域专家 / 用户文档作者 / N/A |
| productionRecommendedPath | 生产推荐写法、职责边界和使用入口 |
| frameworkNativeCapability | 框架 / SDK / 项目既有能力证据；无则写 N/A + skipReason |
| fixtureBoundary | fixture / mock / demo / hard-coded sample 的用途与禁止外推范围 |
| exampleArchitectureFitness | 示例是否符合推荐架构；不符合时给替代示例 |
| antiPatternContrast | 错误写法、风险、替代方案；不需要时写 N/A |
| evidenceMatrix | 判断 -> 代码/类型/官方文档/测试/运行时/用户路径证据 |
| operationExplanation | `OperationExplanationContractV1`，不涉及用户/维护者操作时写 N/A + skipReason |
| codeTruthEvidence | `CodeTruthEvidenceMatrixGate`，绑定 repo path / symbol / currentBehavior / negativeProbe / gap |
| solutionFitAndRecommendation | `SolutionFitAgainstRepoGate` + `UniqueRecommendationBeforeConfirmGate` / `NoPreferenceMenuAfterConvergenceGate` / `UniqueNextStepRecommendationGate` |
| controlPlaneAdviceInventory | 触发时：ExistingCapabilityInventory 摘要；未触发写 N/A + skipReason |常见修正
| 初级产物问题 | 专家型改法 |
|---|---|
| “fixture 每个 route 都重复 middlewares，所以说明可用” | 说明 fixture 只证明底层 RouteOptions.auth 存在；生产推荐使用认证插件集中注册、资源 mapper 或 route group / preset helper，route 只保留最小业务声明 |
| 示例把硬编码单例当主路径 | 标为 smoke / demo，并给真实批量、配置化或生命周期完整的主路径 |
| 文档只解释内部实现字段 | 先写用户任务、配置选择、成功/失败路径，再把内部字段放到 developer / maintainer 章节 |
| 报告只说“已验证通过” | 写生产入口命令、输入、输出、exitCode、代码落点和残余风险（MeasuredVerificationStandard） |
| 用隔离脚本 40 错宣称 V84/core 红 | 先跑 npm run test:core；隔离须复用 createCanonicalAwareReader 才可谈 V# 等价 |
| 手写框架已有能力 | 先列框架原生能力和项目既有 helper；仅在有缺口时新增抽象 |
与其他 Skill 的关系
dev-docs/user-manual-authoring：文档和用户手册需要本 Skill 检查示例、推荐路径和内部实现边界。dev-plan-review：CP2 中涉及架构、框架能力、示例或 fixture 时，本 Skill 是 PR-2 阻断项。audit-project/audit-document/audit-readme/audit-user-manual：审查代码、文档、README 或用户手册时叠加本 Skill。test-router：把expertOutputQuality写入 TestRoute，并选择源码反查、类型检查、官方文档、运行时探针或人工证据。report：报告必须列ExpertOutputQualityGate结果；若未触发写N/A + skipReason。
禁止
- 禁止把 fixture、mock、硬编码样例、单例 smoke 或重复声明当成生产推荐路径。
- 禁止只说“不推荐”但不给框架原生能力、项目既有能力或推荐替代。
- 禁止只按审查报告、历史记忆或截图文字下结论；关键判断必须有本地或官方证据。
- 禁止为了“显得专业”过度设计；新增抽象仍需真实消费者、维护收益和项目边界依据。
© devcodex-labs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in content/skills/expert-output-quality of devcodex-labs/devcodex.
- SKILL.md
- intent.json
Open the folder on GitHubat commit 1dd4525
Compare with similar skills
Expert Output Quality next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Expert Output Quality this skilldevcodex-labs/devcodex | 439 | — | ~1.4k | Automated safety check: Pass | AGPL-3.0 | |
| OpenLogi Device Fixture ContributionAprilNEA/OpenLogi | 23k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Octopus Quicknyldn/claude-octopus | 4.2k | 1 repos | ~2.2k | Automated safety check: Pass | MIT | |
| GSD Quick Batchopen-gsd/gsd-core | 10k | — | ~1.4k | Automated safety check: Notes | MIT | |
| Quick Design SpecDonchitos/Claude-Code-Game-Studios | 26k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Fixture Generatorjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~556 | Automated safety check: Pass | MIT |
Similar skills
Octopus Quick
nyldn/claude-octopus
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
GSD Quick Batch
open-gsd/gsd-core
Runs several small /gsd-quick tasks as one batch, with a single coordinator that plans them, dispatches workers per item and owns all shared writes and worktree merges.
Quick Design Spec
Donchitos/Claude-Code-Game-Studios
Writes a short design spec for small gameplay adjustments such as tuning, tweaks and minor additions, and redirects anything larger to a full design document.
Fixture Generator
jeremylongshore/tons-of-skills-marketplace
Generate fixture generator operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.
Quick
notque/vexjoy-agent
Tracked lightweight execution with composable rigor flags: --trivial, --discuss, --research, --full.
More from devcodex-labs/devcodex
All 70 skills in this repoAccessibility I18n
devcodex-labs/devcodex
无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用；要求把包容性体验和本地化验证绑定到真实用户路径。
AI Agent System Architecture
devcodex-labs/devcodex
AI Agent 系统架构专家 Owner — 当任务涉及 Agent 路由、工具调用、上下文管理、记忆、状态机、权限、人机协作、可观测性、回放验证或模型辅助治理时使用；要求把 Agent 行为设计成可解释、可恢复、可审计。
API Contract Architecture
devcodex-labs/devcodex
API 契约架构专家 Owner — 当任务涉及 public API、HTTP/SDK/CLI 契约、版本兼容、错误模型、分页过滤、幂等、Schema、类型、迁移或消费者影响时使用；要求先冻结消费者契约，再设计实现与验证。
Architecture Design
devcodex-labs/devcodex
架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用；要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。
Audit Common
devcodex-labs/devcodex
审查公共维度 G0~G5 + Profile Freshness Check — 所有 audit 子类型必先执行的基础维度层
Audit Session
devcodex-labs/devcodex
审计工作流的跨会话状态机 — 在 <audit-root/.audit-state/<session-id.json 持久化轮次/发现项/收敛状态，支持 Token 中断后精准恢复
Questions about Expert Output Quality
What does Expert Output Quality do?
专家型产物质量门禁 — 当任务涉及代码、文档、示例、fixture、quick start、技术方案、报告或用户指出“不专业 / 像初级 / 示例误导 / 没有资深架构视角”时使用；要求区分生产推荐路径、框架原生能力、测试夹具边界、反模式与证据矩阵。. Expert Output Quality is an agent skill from devcodex-labs/devcodex.
How do I install Expert Output Quality in Claude Code?
Run `npx skills add devcodex-labs/devcodex --skill expert-output-quality -a claude-code`. Or copy the skill folder (content/skills/expert-output-quality in devcodex-labs/devcodex) into .claude/skills/expert-output-quality in your project. Claude Code loads it when a task matches its description.
How do I install Expert Output Quality in Codex?
Run `npx skills add devcodex-labs/devcodex --skill expert-output-quality -a codex`. Or copy the skill folder (content/skills/expert-output-quality in devcodex-labs/devcodex) into .agents/skills/expert-output-quality in your project. Codex loads it when a task matches its description.
Can I use Expert Output Quality in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add devcodex-labs/devcodex --skill expert-output-quality -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/expert-output-quality, .gemini/skills/expert-output-quality, .github/skills/expert-output-quality and .opencode/skills/expert-output-quality in your project.
What does Expert Output Quality need to run?
Going by SKILL.md and its folder, Expert Output Quality needs the command-line tools its instructions call (npm and node).
Does Expert Output Quality access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Expert Output Quality safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Expert Output Quality use?
Expert Output Quality is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Expert Output Quality use?
About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Expert Output Quality?
Skills that share tags, products or a category with Expert Output Quality: OpenLogi Device Fixture Contribution (AprilNEA/OpenLogi, 23k stars), Octopus Quick (nyldn/claude-octopus, 4.2k stars), GSD Quick Batch (open-gsd/gsd-core, 10k stars) and Quick Design Spec (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Expert Output Quality?
devcodex-labs (a GitHub organization) maintains it in devcodex-labs/devcodex, which has 439 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on September 17, 2026.
Source: devcodex-labs/devcodex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.