Cp Gate
devcodex-labs/devcodex
执行 CP1（需求确认）/ CP2（方案确认）与条件 CP3（实施计划确认）。CP1→CP2 强制按序，CP3 按工作流能力矩阵判定。
默认开发子类型规范 — 通用功能开发六阶段流程（CP1→PR-1自检→CP2→plan-review→CP3→执行→ECR执行闭环复审）
AGPL-3.0Auto-check passed
Install Dev Default
$ npx skills add devcodex-labs/devcodex --skill dev-default -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install devcodex-labs/devcodex dev-default --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/dev-default .claude/skills/dev-default && 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 "dev-default" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-default into .claude/skills/dev-default/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-default", 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/dev-defaultType 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 dev-default -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install devcodex-labs/devcodex dev-default --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/dev-default .agents/skills/dev-default && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dev-default" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-default into .agents/skills/dev-default/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-default", 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 dev-default -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install devcodex-labs/devcodex dev-default --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/dev-default .cursor/skills/dev-default && 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 "dev-default" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-default into .cursor/skills/dev-default/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-default", 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/dev-default--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 dev-default -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install devcodex-labs/devcodex dev-default --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/dev-default .gemini/skills/dev-default && 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 "dev-default" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-default into .gemini/skills/dev-default/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-default", 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 dev-defaultInstalls 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 dev-default -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/dev-default .github/skills/dev-default && 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 "dev-default" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-default into .github/skills/dev-default/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-default", 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 dev-default -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 dev-default --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/dev-default .opencode/skills/dev-default && 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 "dev-default" agent skill from https://github.com/devcodex-labs/devcodex/tree/main/content/skills/dev-default into .opencode/skills/dev-default/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev-default", 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
dev-default- GitHub stars
- 439
- Token cost
- ~2.2k tokens
- SKILL.md length
- 555 words
- Files
- 2
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
默认开发子类型规范 — 通用功能开发六阶段流程（CP1→PR-1自检→CP2→plan-review→CP3→执行→ECR执行闭环复审）
- SKILL.md covers 触发条件, 六阶段执行, 关键规则 and 豁免项
- Calls npm
What it does
Dev Default is an agent skill from devcodex-labs/devcodex. 默认开发子类型规范 — 通用功能开发六阶段流程（CP1→PR-1自检→CP2→plan-review→CP3→执行→ECR执行闭环复审）
Its SKILL.md is about 2.2k 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
- “/dev-default”
Requirements
- Node.js
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:
npm
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
Dev Default loads about 2.2k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 555 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). 555 words, ~2,237 tokens.
Download SKILL.mdSave it as
.claude/skills/dev-default/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- dev-default
- description
- 默认开发子类型规范 — 通用功能开发六阶段流程（CP1→PR-1自检→CP2→plan-review→CP3→执行→ECR执行闭环复审）
Dev Default Skill
触发条件
dev 工作流未匹配其他子类型时的默认路径，适用于：新功能开发、接口实现、业务逻辑变更。
六阶段执行
| 阶段 | 动作 | CP 关卡 |
|---|---|---|
| N1 需求确认 | 先判定入口类型：纯新需求且无产品角色时独立保留 00-需求概况.md / 原始附件，生成并确认 01-需求确认.md；有产品角色并由产品直接提供完整需求时，以 01-产品需求.md 为 CP1 真相源，产品模板正文只给产品填写完整 PRD，AI / 研发缺口 / 冲突检查记录在 CP1 摘要、02-技术方案.md 或报告中，不生成或重写产品需求；需求变更独立保留 00-需求变更概况.md，生成 01-需求变更确认.md 并回写目标需求真相源；Bug 转 fix | CP1 确认 |
| N2 技术方案 | 架构设计、接口定义、数据流 → PR-1 内部自检（需求完整性），不通过则修正后重检；契约驱动型需求须显式引用目标文档路径/模式/契约范围 | 自检通过后 → CP2 确认 |
| N3 方案验证 | 调用 dev-plan-review Skill（PR-2~PR-7）；PR-5② 触发则继续 impact-review | 🔴 阻断时回 CP2 |
| N4 实施计划 | 任务拆分、顺序、依赖、验证与回滚 | CP3 确认 |
| N5 执行 | ExecutionContract/TestRoute 对照 → 编码实现 → 接口变更时 api-verification → document-sync | — |
| N6 ECR 执行闭环复审 | 对照 §2 核心设计、关键产物、报告、记忆、SUMMARY、diff/commit 与验证证据做执行后正式复审；默认 reviewClass=R2，控制面等高风险升 R3+清单，禁止「永远轻量」口径 | 发现阻断问题须回退修正 |
N5 执行阶段补充规则
读取前置（F-18）：修改已有文件前须先 view 当前内容，确认最新状态；同会话内已读且无并行修改的文件可跳过重复 view。
执行中变更处理（F-10）：执行阶段发现方案调整需求时，立即暂停，按 10-dev.instructions.md §变更管理 变更分级走对应流程，产物文件须在代码落地前更新。
在途缺陷绑定（F-10A）：实施前或实施中复现与当前需求相关的缺陷时，必须执行 spec-governance#InFlightIssueRequirementBindingGate；PI/PF 只做治理追踪，不能替代当前需求修订。阻断项先写回需求并提醒纳入决定；用户已明确要求一并处理或优先修复时，记录该授权后直接同步方案、验收和测试并先修复。
执行期 CP3 回退（F-26）：若 N5 执行过程中实际修改范围扩展到 CP3 门槛（文件数从 <5 增至 ≥5、临时引入高风险操作，或命中控制面/模板/validate/部署副本联动），必须暂停 source mutation，回到 N4 / CP3 补做实施计划确认后再继续。
回归扫描（F-19）：修改已有文件时，完成后须对该文件涉及的调用路径执行最小范围 grep 确认无残留引用问题；纯新增文件不触发。
统一联查矩阵（F-25）：命中控制面规则、模板、接口契约/验证产物、工作区真相源/部署副本、发布口径等高联动场景时，默认升为 L2 标准联查；若同时涉及多真相源同步或模板-示例-校验链，升级为 L3 强联查并追加交叉验证。
最小实现守门（F-27）：执行阶段必须按 CP1/CP2/CP3 的 WorkflowPlanDecisionV1.designDepth 与复杂度预算落地；minimal 只做满足已确认产品事实源和技术验证项的局部最小实现，standard 必须有真实消费者、公共契约、迁移/恢复或演进边界证据。ceremonyTier 与 assuranceLevel 不得反向扩大实现；禁止无计划新增抽象、通用配置、预留扩展点或未确认防御分支。若确需超出预算，先暂停并回 CP2/CP3。旧复杂度字段只读兼容，不得新写入。
开发偏移守门（F-28A / DevelopmentDriftGate）：进入编码前必须对照 CP1/CP2/CP3、ExecutionContract、TestRoute、消费者同步和当前 dirty 边界做一次偏移检查。至少列出 allowedFirstBatch、blockedScope、noGoItems、driftTriggers、validationRoute 和 consumerSync；若实施中触达排除范围、扩大 package/API/配置/文档消费者、引入新依赖、改变验证路线或污染工作区，先暂停当前 mutation、重算结构化意图并回 CP2/CP3，不能把后续阶段能力直接并入当前批次。
必要注释守门（F-28）：非显然业务规则、状态转换、不变量、兼容约束、安全边界、外部契约映射或反直觉权衡必须保留短注释；JavaScript / Node.js 中命中必要注释的导出函数、核心业务函数、类、复杂对象契约、参数/返回/异常说明必须使用标准 JSDoc；禁止逐行解释、重复代码含义、临时 TODO 或调试注释。
通用工程吸纳守门（F-29）：CP1 起前置平台工程判断（消费者、共享契约、模块职责、维护成本、非目标）；provider/SDK 字段级合同；包工程层；依赖升级拆分业务 vs 依赖层；共享库根因优先修库；简单 service 不重复 route/model 校验。条件域审计（ExistingDomainContractAudit、ConfigOwnershipMatrix、ApiDocVerificationSync、DataMutationPlan、AbsorptionDecision、FullV1ScopeGuard、StartupPhaseTrace）按触发执行。跨项目/吸纳类守门只在本 Skill 判定触发并记录 gateGroup / ownerSkill / validationRoute / skipReason；执行正文与 legacy anchors 一律读 ../spec-governance/gate-registry.json + Owner Skill，禁止在此展开 Gate 百科。
验证卫生与串行边界（F-30） / 验证卫生与并发边界：按 ConcurrencyPolicy 执行：只读准备和隔离验证可在不共享输出目录时并行；release / pack / benchmark / codegen / package boundary 检查不得与会删除、重建或写入 dist 的命令并行；消费者验证异常时先核对 package.json / lockfile / node_modules / npm ls <关键依赖>；完成前检查并清理本轮或旧验证遗留的无关 dirty 文件。
多需求并行编排（F-30A）：N5 前若出现多个 requirement / bug / optimization / scenario-test、用户要求并行推进、子 Agent、子会话或 worktree，必须先调用 requirement-parallel-orchestration。RequirementIndependenceDecisionV1.status=independent 与 valid ParallelLaunchCardV1 只证明可规划；实际派发还必须取得当前宿主 direct collaboration capability、HostSubagentDispatchPlanV1.status=parallel-eligible 和逐项 AgentWorkLeaseV1。child 仅执行 read-only、独占 .tmp 验证或 separate-worktree patch，结果经根 Agent 校验、固定顺序汇合和重测后才可使用；timeout/cancel/late/invalid 自动隔离并由根 Agent 执行同 work graph 串行回退。weakly-coupled-lock 只允许并行准备 + 单写者检查点；serial-required 或无新鲜宿主证据禁止并行 source mutation，但不得阻断主任务。
技术路线对比门禁（F-31）：技术路线、架构优化、性能优化、框架能力设计或高维护成本方案，在 CP1 最终需求确认前执行对比调研；若存在同类产品/项目/框架/本仓库相似模块可比，必须记录证据范围和采纳/不采纳理由；不触发时写 N/A + skipReason。
需求方输入到产品需求链路（F-31A）：需求来自业务、运营、客户、老板、内部使用方、PRD、Word、原型、截图、会议纪要或用户补充消息时，CP1 必须先判定入口类型。无产品角色 / 研发兼产品时，纯新需求将需求方原始输入独立保留为 00-需求概况.md 或等价附件，且 00-需求概况.md 必须使用口语化问题收集“你希望系统帮你做到什么、现在你们怎么凑合处理、有哪些必须遵守的业务口径、给一个希望出现的例子、给一个不能接受的例子和相关材料”；需求方允许填写“没有 / 不知道 / 暂无 / 需要产品帮忙整理”。AI 再生成 01-需求确认.md 产品需求草稿，产品补充归一化后由需求方 + 产品双方确认。有产品角色并由产品直接提供完整需求时，使用独立 01-产品需求.md / product-requirement.prompt.md，产品模板正文只给产品填写完整 PRD，产品完整写清业务目标、流程图、文字步骤、节点解释、页面交互、字段描述、业务规则、示例 / 反例与不确定点；AI / 研发不生成或重写产品需求，缺口 / 冲突检查记录在 CP1 摘要、02-技术方案.md 或报告中，确认后直接进入技术方案。需求变更使用 00-需求变更概况.md + 01-需求变更确认.md，必须锚定原需求基线、变更前后差异、影响范围、不变内容和目标真相源，并在确认后回写目标需求文件；Bug / 异常 / 已承诺行为与实际不一致转 fix 的 00-问题概况.md / 01-问题确认.md，不得混入产品需求确认模板。技术方案只能承接双方确认后的产品需求、产品直接提供的完整需求或问题确认，不得直接把原始诉求当实现口径，也不得把需求方输入模板、产品完整需求模板和 AI 生成的产品确认模板混写。
条件 Gate 索引（F-32 / F-33 / F-33A / F-34）：N5 只做触发路由，完整字段与探针见 Owner Skill / gate-registry.json。未触发写聚合 N/A + skipReason。
| 触发面 | gateGroup（代表） | ownerSkill | 记录要求 |
|---|---|---|---|
| 前端 UI / 交互 / Figma / preview / i18n | frontend-runtime | audit-project · test-router · 前端相关 Owner | 设计来源、还原、状态、用户流、视觉验证纳入 CP2/CP3/TestRoute/ECR |
| 浏览器预算 / 用户自验 / finding 矩阵 / 数据迁移 / package 确认前证据等 | registry 对应组（finding-review、release、requirement-profile 等） | registry ownerSkills | gateGroup / ownerSkill / validationRoute / skipReason |
| data 台账吸纳 / 用户纠偏 / 仍需吸纳清单 | absorption-layering · confirmed-completeness | spec-absorption · spec-governance | LayeredAbsorptionDecision + layerChecks；禁止继续堆通用 guard 列表 |
全工作区 data/*.md 扫描 | （WorkspaceDataAbsorptionScope） | spec-absorption | 扫描 .devcodex/*/data/ 全部命名空间 + workspace；不得只扫 sticky 项目 |
错误处理验证（F-21）：实施完成后须验证边界/异常路径（如空值/权限拒绝/超时）均有处理，不得只验证正常路径。
调试清理（F-20）：执行完成后须检查并清除 console.log / 临时注释 / TODO 标注（业务 TODO 转为 issue 跟踪）。
Show full SKILL.md (223 more words)Show less
N6 偏离分级处理（F-04）
| 偏离类型 | 说明 | 处理方式 |
|---|---|---|
| 🟢 实现细节偏离 | 算法/结构调整，不影响接口/行为 | 记录偏离原因，继续 |
| 🟡 接口形式偏离 | 参数名/路径调整，行为不变 | 更新 api-verification，说明原因 |
| 🔴 行为/范围偏离 | 与已确认需求或技术方案功能差异 | 必须回 CP2/CP1 处理（见变更管理规则） |
长会话重锚定（F-24）：会话超过 10 轮后，N6 开始前须重新 view 01-需求确认.md / 01-产品需求.md（历史目录可用 01-需求概述.md）和 02-技术方案.md，确保复审基于最新文档而非记忆。
N6 ECR 最小清单
执行完成后、最终报告完成前必须执行 ECR（Execution Closure Review）：
| 项 | 检查对象 | 目的 |
|---|---|---|
| ECR-1 | CP1/CP2/CP3、报告、daily tasks、SUMMARY | 避免压缩后状态错配 |
| ECR-2 | 需求条款 / 问题 ID → diff/commit 文件 | 避免确认范围漏实现 |
| ECR-3 | CP3 步骤 → 测试/部署/验证证据 | 避免计划与执行漂移 |
| ECR-4 | 报告声明 → 测试/探针/官方文档 | 避免过度宣称 |
| ECR-5 | memory daily → SUMMARY | 避免 SUMMARY 早标绿 |
| ECR-6 | git dirty 边界 | 避免混入用户另案变更 |
| ECR-7 | 控制面任务追加 validate / direct replay / host-contract probe；涉及规范源、Skill、Hook、CLI、MCP、模板、部署副本、路径规则或 validate 语义时必须执行 SCV（spec-governance）；release/pack 任务追加 PackageBoundarySerialCheck 与无关残留清理证据 | 避免校验假绿、规范漂移与验证残留 |
关键规则
- 强制顺序（R12）：方案 → PR-1 自检 → 确认 CP2 → PR-2~PR-7 → CP3 → 编码。禁止跳过 PR-1 直接请确认 CP2（Stop gap
pr1-skipped/ R9）；禁止 CP2 未确认就改hooks//skills//instructions//host-projections/等控制面（R10 复用checkCpGate，strict deny / safety-only 披露cp2-unconfirmed-write）。 - 三个 CP 必须按序形成显式或 Auto 决定，禁止合并跳过；是否等待只由结构化 executionDecision 决定（C02）
- PR-1 在 CP2 前做 AI 内部自检，PR-2~PR-7 在 CP2→CP3 之间做详细验证（
dev-plan-review两阶段流程） - 执行阶段结束后触发：
api-verification（若涉及接口）→document-sync→ ECR 执行闭环复审（N6，内部包含方案一致性验证和 ECR-1~ECR-7） - Auto、控制面、多批次、预计 ≥10 文件或发布类任务，执行前必须调用
execution-contract；测试路线复杂或跨模块时调用test-router - dev 任务包含规范缺口、审查 finding、回归或其他修复目标时，调用
execution-contract的repair-collaboration：低风险可内联 lightweight，高风险必须 full + independent re-review；纯新增功能不触发，模型名称不参与分类 - 高联动场景不得只做单文件修改；至少要同步直接真相源与同层联动文件
impact-review仅由 PR-5②（跨模块架构依赖变更）触发，position：plan-review 之后、CP3 之前- N4 只确认实施计划，不重复技术方案中的架构决策、接口论证和兼容性主说明；
05-实施进度.md对小任务不是默认文书，但多批次、预计 ≥10 文件、跨轮次、阻塞、控制面联动或用户要求持续跟踪时必须启用 - 高风险控制面 / 多批次任务的 ExecutionContract 与 TestRoute 必须显式列出历史能力回归矩阵，至少写清“历史能力 → 受影响批次 → 必跑验证 → 失败回滚点”
- Node.js 项目默认运行时、CI、Profile 与 README 不低于
>=18；低于 v18 必须有业务理由、风险和验证证据 - 关键 Markdown 产物（需求 / 方案 / 实施计划 / 实施进度 / 阅读型文档 / README）必须包含
## 目录导航；.http / .cjs不适用 - 输出报告：
reports/requirements/目录，遵循reportSkill 命名规则 - 测试覆盖：实现完成后确认关键路径单测
豁免项
无特殊豁免，完整走 CP1→CP2→CP3 流程。
<!-- auto-sync anchors -->前端体验质量门禁 · CodeTruthRequirementGate · ManualReviewEvidenceRetention · GovernanceGateRegistry · V2FormalSolutionPackage · ReviewFindingIntakeGate · FigmaHighFidelityRestorationGate · DatabaseRecordMigrationExportGate · FrontendBrowserVerificationBudgetGate · RequirementPreConfirmGate · PackageAdapterPreConfirmEvidenceGate · SkillFirstAbsorptionGate · CapabilityToSkillPromotionGate · SkillAbsorptionDecision · LayeredAbsorptionGate · ProactiveBetterAlternativeGate · commonInstruction · skill · promptTemplate · executionConsumer · validationProbe · publicDocs · deployCopy · ConfirmedAbsorptionCompletenessGates · EvolutionCapabilityControlPlaneGate · FrontendAsyncCacheRenderGate · RemoteCIParityPushGate
FigmaProductionAssetBudgetGate
© 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/dev-default of devcodex-labs/devcodex.
- SKILL.md
- intent.json
Open the folder on GitHubat commit 1dd4525
Compare with similar skills
Dev Default next to the 2 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 |
|---|---|---|---|---|---|---|
| Dev Default this skilldevcodex-labs/devcodex | 439 | — | ~2.2k | Automated safety check: Pass | AGPL-3.0 | |
| Cp Gatedevcodex-labs/devcodex | 439 | — | ~5.1k | Automated safety check: Pass | AGPL-3.0 | |
| Dev Plan Reviewdevcodex-labs/devcodex | 439 | — | ~3.3k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Dev Plan Review
devcodex-labs/devcodex
技术方案验证（两阶段质量门禁）— PR-1 CP2 前自检 + PR-2～PR-7 详细验证，阻断不合格方案进入编码. An agent skill from devcodex-labs/devcodex.
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 Dev Default
What does Dev Default do?
默认开发子类型规范 — 通用功能开发六阶段流程（CP1→PR-1自检→CP2→plan-review→CP3→执行→ECR执行闭环复审）. Dev Default is an agent skill from devcodex-labs/devcodex.
How do I install Dev Default in Claude Code?
Run `npx skills add devcodex-labs/devcodex --skill dev-default -a claude-code`. Or copy the skill folder (content/skills/dev-default in devcodex-labs/devcodex) into .claude/skills/dev-default in your project. Claude Code loads it when a task matches its description.
How do I install Dev Default in Codex?
Run `npx skills add devcodex-labs/devcodex --skill dev-default -a codex`. Or copy the skill folder (content/skills/dev-default in devcodex-labs/devcodex) into .agents/skills/dev-default in your project. Codex loads it when a task matches its description.
Can I use Dev Default 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 dev-default -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dev-default, .gemini/skills/dev-default, .github/skills/dev-default and .opencode/skills/dev-default in your project.
What does Dev Default need to run?
Going by SKILL.md and its folder, Dev Default needs the command-line tools its instructions call (npm). Our summary lists: Node.js.
Does Dev Default 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 Dev Default 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 Dev Default use?
Dev Default 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 Dev Default use?
About 2.2k tokens (SKILL.md is roughly 8.9k 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 Dev Default?
Skills that share tags, products or a category with Dev Default: Cp Gate (devcodex-labs/devcodex, 439 stars) and Dev Plan Review (devcodex-labs/devcodex, 439 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dev Default?
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.