Agent skill

Knowledge Engineering Quality And Delivery

by echoVic in echoVic/blade-code

覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环. An agent skill from echoVic/blade-code.

MITAuto-check passedTesting & QA

Install Knowledge Engineering Quality And Delivery

skills CLI
$ npx skills add echoVic/blade-code --skill knowledge-engineering-quality-and-delivery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install echoVic/blade-code knowledge-engineering-quality-and-delivery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.trae/knowledges/engineering-quality-and-delivery .claude/skills/knowledge-engineering-quality-and-delivery && rm -rf skills-src

Use ~/.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/

Facts

Skill name
knowledge-engineering-quality-and-delivery
GitHub stars
181
Token cost
~1.4k tokens
SKILL.md length
352 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环. An agent skill from echoVic/blade-code.

  • Tasks that involve Unit testing
  • SKILL.md covers Module Structure, Branching Table, Affected Scope and Gotchas, plus 6 more sections
  • Calls bun
  • Tasks that involve Changelog and release notes

What it does

Knowledge Engineering Quality And Delivery is an agent skill from echoVic/blade-code. 覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环。 Navigate when: 调整测试分层、CI 门禁、真实 API 准出、构建产物、npm 发布或文档同步。 Excludes: 具体运行时业务语义(转到对应功能域);各门禁实现细节继续进入本节点的四个子节点。 Keywords: quality gate, qualification, Vitest, real API, performance, security, snapshot, build, release, npm, GitHub Actions, Docsify, changelog.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Unit testing, Changelog and release notes and Quality gates. It works with npm, GitHub Actions and Vitest. The repository describes itself as: AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers. The licence is MIT.

When your agent uses it

  • Tasks that involve Unit testing
  • Tasks that involve Changelog and release notes
  • Tasks that involve Quality gates

Example prompts

  • “/knowledge-engineering-quality-and-delivery”

What it can do on your machine

Read from SKILL.md and the folder at commit 30f8684. 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:

    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Knowledge Engineering Quality And Delivery loads about 1.4k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 352 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 echoVic/blade-code at commit 30f8684, republished under its MIT licence (© echoVic). 352 words, ~1,435 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-engineering-quality-and-delivery/SKILL.md (or your agent's skills folder).
name
knowledge-engineering-quality-and-delivery
description
覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环。 Navigate when: 调整测试分层、CI 门禁、真实 API 准出、构建产物、npm 发布或文档同步。 Excludes: 具体运行时业务语义(转到对应功能域);各门禁实现细节继续进入本节点的四个子节点。 Keywords: quality gate, qualification, Vitest, real API, performance, security, snapshot, build, release, npm, GitHub Actions, Docsify, changelog.

Module Structure

该域不是单一模块,而是把确定性测试、付费模型轨迹、制品级门禁和 tag 驱动发布串成一条跨 CLI、Web、ACP、TUI 与文档的交付链。

Directory Layout
  • packages/cli/tests/ — CLI 核心的 unit、integration、CLI、E2E、real-api、performance、snapshot 与 security 测试
  • packages/cli/web/tests/ — Web 组件、Store、服务和 bundle 预算测试
  • packages/cli/scripts/ — 测试运行器、资格编排、构建、凭据加载与发布脚本
  • scripts/ — 仓库级发布辅助和独立基准脚本
  • .github/workflows/ — CI、tag 发布与 Docs Pages 部署
  • docs/ — 中文默认站点、英文镜像、设计规格和准出证据
  • package.json、packages/cli/package.json — 工作区命令、发布包边界与版本
  • biome.json、packages/cli/vitest.config.ts、packages/cli/web/vitest.config.ts — 静态检查与测试项目定义
Key Entry Points
  • createQualificationPlan() in packages/cli/scripts/qualification.ts — 定义本地 14 项和生产 16 项顺序门禁
  • testTypes in packages/cli/scripts/test-config.js — 定义各 Vitest 项目、超时、环境和发布阻断文件白名单
  • packages/cli/scripts/build.ts — 构建 CLI ESM 产物并把 Web 输出到同一发布目录
  • .github/workflows/ci.yml — 聚合确定性 CI 作业
  • .github/workflows/publish.yml — 校验 tag/包版本并通过 npm Trusted Publishing 发布
  • .github/workflows/docs.yml — 生成文档站 changelog 并部署 Pages

Branching Table

维度本地或确定性分支生产或发布分支
资格入口qualify:local 顺序执行 14 项且不接触付费凭据qualify:production 在本地门禁后追加 Chromium preflight 和付费真实 API
测试证据unit/integration/E2E 允许隔离、mock 或本地 fixturerelease matrix 要求真实 Provider、production surface 和宿主侧副作用证据
覆盖率与性能coverage 插桩运行除 performance 外的项目performance 在 production build 后独立运行,避免插桩污染时序
发布准备与发布本地负责冻结候选、版本、双语 changelog、资格证据与 tagtag workflow 只校验版本、构建、幂等发布 npm/GitHub Release
文档源与站点产物docs/、CHANGELOG.md、CHANGELOG.zh.md 是 Git 可见源docs/changelog.md 与 docs/en/changelog.md 在部署时生成且被忽略
浏览器依赖npm 包携带固定 Playwright 运行库但不下载 Chromium浏览器门禁要求显式安装并通过离线 launch/close preflight

Affected Scope

  • packages/cli/src/ — 每个运行时变更都要映射到确定性回归与适当的真实轨迹
  • packages/cli/web/src/ — Web 行为同时受组件测试、production Chromium 轨迹和 bundle 预算约束
  • packages/cli/tests/ — 汇集本地回归、跨表面驱动、资源回收和发布矩阵
  • packages/cli/scripts/ — 决定测试项目选择、超时、凭据隔离、构建顺序和本地发布行为
  • .github/workflows/ — 把静态检查、跨平台 smoke、coverage、安全审计、npm 与 Pages 分成独立作业
  • packages/cli/package.json — 发布版本、npm 文件清单、运行时依赖和质量命令的权威入口
  • CHANGELOG.md、CHANGELOG.zh.md — 英文包内更新信息与中文同步发布记录
  • docs/ — 用户行为契约、设计冻结记录和可审计的资格证据

Gotchas

  • bun run test:all 不是完整准出:它不执行资格编排的类型、格式、lint、构建、浏览器 preflight 和付费矩阵,发布判断必须使用 qualify:local 与 qualify:production (package.json, packages/cli/scripts/qualification.ts)
  • tag 触发的发布工作流不重新运行测试或真实 API;错误地把 publish.yml 成功当作候选质量证明,会发布仅“可构建”的未资格版本 (.github/workflows/publish.yml, docs/testing/qualification.md)
  • 当前 release:patch 路径由配置关闭测试、代码质量和安全检查,只能做版本/tag 编排,不能替代冻结 SHA 上的资格流程 (packages/cli/release.config.js, packages/cli/scripts/release.js)
  • tests/e2e/ 的名称不代表生产端到端证据,其中仍有 mock 与占位断言;发布级行为由显式 realApiQualification.files 决定 (packages/cli/tests/e2e/core-features.test.ts, packages/cli/tests/e2e/flows/chat-flow.test.ts, packages/cli/scripts/test-config.js)
Show full SKILL.md (147 more words)Show less

Architecture

  • 资格编排严格串行且首个非零退出即停止,避免后续通过项掩盖更早的失败;CI 则拆成并行作业,最终由 ci-pass 汇总失败与取消状态 (packages/cli/scripts/qualification.ts, .github/workflows/ci.yml)
  • 交付证据分为确定性代码门禁、真实 Provider/宿主轨迹、冻结候选 evidence 文档和 tag 后 registry/Release 验证,任一层都不能由另一层替代 (docs/testing/qualification.md)
  • 构建把后端与 Web 放入 packages/cli/dist/,npm 包再通过 files 白名单发布该目录及少量运行时资产;性能与 Web 制品测试因此必须位于构建之后 (packages/cli/scripts/build.ts, packages/cli/package.json, packages/cli/scripts/qualification.ts)

Decisions

  • 公共 CI 不注入付费 Provider 凭据,真实 API 是发布者在候选 SHA 上显式运行的门禁;这避免 secret 暴露,但意味着 tag workflow 本身不是完整准出权威 (docs/testing/qualification.md, .github/workflows/ci.yml)
  • 每个独立功能或修复单独发布 patch,并让版本、双语 changelog、用户文档和资格证据共同描述同一个行为增量 (AGENTS.md)

Patterns

  • 高风险功能通常同时增加确定性单测、真实 API 跨表面轨迹、test-config.js 白名单断言、资格文档和最终版本元数据,缺一项会留下未覆盖分支 (packages/cli/tests/unit/scripts/test-runner.test.ts, docs/testing/qualification.md)
  • 近期开版提交稳定地把 packages/cli/package.json、CHANGELOG.md 与 CHANGELOG.zh.md 一起变更,防止包版本与两种语言的发布记录漂移 (packages/cli/package.json, CHANGELOG.md, CHANGELOG.zh.md, git:1ce74b03)

Conventions

  • 中文文档位于 docs/ 根,英文镜像位于 docs/en/;行为变化需要同步两边,而生成的站点 changelog 只能由部署工作流复制 (AGENTS.md, .github/workflows/docs.yml)

Branching Behavior

  • 非付费检查会主动移除 real-API 开关、凭据文件位置和各 Provider key/model 变量;只有标记为 paid-api 的最后一项接收物化后的凭据环境 (packages/cli/scripts/qualification.ts)
  • production 分支在真实 API 前执行不联网的 Chromium 检查,preflight 失败会令顺序执行器停止,从而保证零 Provider 请求 (packages/cli/scripts/qualification.ts, packages/cli/tests/unit/scripts/qualification.test.ts)
  • coverage 分支排除 wall-clock performance,而本地资格分支在构建后单独执行 performance;新增制品性能断言时必须同时考虑这两个入口 (packages/cli/vitest.config.ts, packages/cli/scripts/test-config.js, packages/cli/scripts/qualification.ts)
  • 发布分支以 packages/cli/package.json 的版本匹配 v*.*.* tag;仓库根 package.json 的私有 monorepo 版本不是 npm 发布版本 (package.json, packages/cli/package.json, .github/workflows/publish.yml)

Child Knowledge Nodes

  • ./unit-integration-and-shared-test-harnesses/SKILL.md — Navigate when: 新增 unit/integration/Web 测试,调整 Vitest project、mock、临时目录或测试进程清理
  • ./real-api-qualification-and-e2e/SKILL.md — Navigate when: 修改真实 Provider、发布矩阵、跨表面驱动、凭据或资格证据
  • ./performance-security-and-snapshot-gates/SKILL.md — Navigate when: 调整性能预算、安全检查、coverage 或快照更新策略
  • ./build-release-and-documentation/SKILL.md — Navigate when: 修改构建输出、npm 包内容、版本/tag 发布、CI action 或双语文档部署

© echoVic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .trae/knowledges/engineering-quality-and-delivery of echoVic/blade-code.

Open the folder on GitHubat commit 30f8684

Compare with similar skills

Knowledge Engineering Quality And Delivery 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.

Knowledge Engineering Quality And Delivery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Engineering Quality And Delivery this skillechoVic/blade-code181—~1.4kAutomated safety check: PassMIT
CI Triageandymai/brepjs114—~3.7kAutomated safety check: PassApache-2.0
Flaker Storage Cache On CImizchi/skills356—~1.6kAutomated safety check: PassNone
Repo Hygiene Scan and FixQwenLM/qwen-code28k—~1.7kAutomated safety check: PassApache-2.0
Ccb GitHubSeemSeam/claude_codex_bridge3.6k—~4.9kAutomated safety check: PassCustom licence
Cline CLI Release Publishercline/cline70k—~3.4kAutomated safety check: WarnApache-2.0

Similar skills

  • CI Triage

    andymai/brepjs

    This skill should be used when a brepjs GitHub Actions job is red or behaving oddly on github.com (a remote CI run, not a local pre-commit/pre-push hook) — "CI failed", "ci-pass is failing", "npm ci…

    114 GitHub stars~3.7k tokensUpdated today
    Testing & QAAuto-check passed
  • Persist flaker's DuckDB storage across GitHub Actions runs and feed it from multiple sources (vitest reports, custom adapter reports, etc.).

    356 GitHub stars~1.6k tokensUpdated 6 days ago
    DevOps & CloudAuto-check passed
  • Scheduled CI skill that scans a repository for small, certain docs, test and code hygiene issues and fixes them on one branch with a commit per finding.

    28k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Ccb GitHub

    SeemSeam/claude_codex_bridge

    Maintain this CCB project's GitHub-facing release and npm publication surface.

    3.6k GitHub stars~4.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Walks through releasing the Cline CLI package to npm: release notes, version bump, matching git tag, and either the GitHub workflow or a local publish.

    70k GitHub stars~3.4k tokensUpdated today
    DevelopmentAuto-check: warnings
  • A skill your agent uses whenever the user asks for a new npm version, npm release, package release, new release, version bump, publishing to npm, cutting a GitHub release, tagging a release, or…

    866 GitHub stars~2.9k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from echoVic/blade-code

All 38 skills in this repo
  • Base64 Parser

    echoVic/blade-code

    Base64 编解码工具,支持编码/解码文本、JSON、二进制文件,自动检测格式,支持批量处理. An agent skill from echoVic/blade-code.

    181 GitHub stars~545 tokensUpdated 11 days ago
    Auto-check: notes
  • Code Review

    echoVic/blade-code

    Review frontend code for best practices, bugs, and improvements.

    181 GitHub stars~377 tokensUpdated 11 days ago
    Auto-check: notes
  • GitHub Explorer

    echoVic/blade-code

    Explore and summarize popular GitHub projects. An agent skill from echoVic/blade-code.

    181 GitHub stars~434 tokensUpdated 11 days ago
    Auto-check passed
  • 覆盖 Session 级 LSP 配置快照、stdio 进程、文档同步、语义查询、诊断回注、崩溃恢复 和子 Session 继承。进入条件:新增语言服务器、修改 LSP 工具、排查诊断缺失/重复、 处理 worktree 或 ACP 差异、修复进程泄漏或 transport 代际问题。不包含:VS Code 扩展桥接(见…

    181 GitHub stars~1.9k tokensUpdated 11 days ago
    Auto-check passed
  • 覆盖 SkillRegistry、SKILL.md 延迟加载、自定义命令 Markdown 解析、来源覆盖、插件 命名空间、Session 快照和模型/用户调用入口。进入条件:新增 Skill 或命令字段、调整 发现优先级、调试 /command 或 Skill 工具、修改 Prompt 元数据或消费者集成。不包含: 插件安装生命周期(见…

    181 GitHub stars~2.1k tokensUpdated 11 days ago
    Auto-check passed
  • Covers 领域能力如何包装成内置工具、getBuiltinTools 的 Session 依赖注入、ToolSearch 延迟激活,以及 Goal/Task/Team/Plan/Skill/LSP/MCP/Web/Config/Worktree 适配边界。

    181 GitHub stars~2.1k tokensUpdated 11 days ago
    Auto-check passed

Categories

Questions about Knowledge Engineering Quality And Delivery

What does Knowledge Engineering Quality And Delivery do?

覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环. An agent skill from echoVic/blade-code. Knowledge Engineering Quality And Delivery is an agent skill from echoVic/blade-code. 覆盖 Blade Code 跨测试、构建、资格验证、发布与双语文档的工程质量闭环。 Navigate when: 调整测试分层、CI 门禁、真实 API 准出、构建产物、npm 发布或文档同步。 Excludes: 具体运行时业务语义(转到对应功能域);各门禁实现细节继续进入本节点的四个子节点。 Keywords: quality gate, qualification, Vitest, real API, performance, security, snapshot, build, release, npm, GitHub Actions, Docsify, changelog.

When should I use Knowledge Engineering Quality And Delivery?

Knowledge Engineering Quality And Delivery fits situations like: tasks that involve Unit testing; tasks that involve Changelog and release notes; tasks that involve Quality gates.

How do I install Knowledge Engineering Quality And Delivery in Claude Code?

Run `npx skills add echoVic/blade-code --skill knowledge-engineering-quality-and-delivery -a claude-code`. Or copy the skill folder (.trae/knowledges/engineering-quality-and-delivery in echoVic/blade-code) into .claude/skills/knowledge-engineering-quality-and-delivery in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Engineering Quality And Delivery in Codex?

Run `npx skills add echoVic/blade-code --skill knowledge-engineering-quality-and-delivery -a codex`. Or copy the skill folder (.trae/knowledges/engineering-quality-and-delivery in echoVic/blade-code) into .agents/skills/knowledge-engineering-quality-and-delivery in your project. Codex loads it when a task matches its description.

Can I use Knowledge Engineering Quality And Delivery 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 echoVic/blade-code --skill knowledge-engineering-quality-and-delivery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-engineering-quality-and-delivery, .gemini/skills/knowledge-engineering-quality-and-delivery, .github/skills/knowledge-engineering-quality-and-delivery and .opencode/skills/knowledge-engineering-quality-and-delivery in your project.

What does Knowledge Engineering Quality And Delivery need to run?

Going by SKILL.md and its folder, Knowledge Engineering Quality And Delivery needs the command-line tools its instructions call (bun).

Does Knowledge Engineering Quality And Delivery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Knowledge Engineering Quality And Delivery 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 Knowledge Engineering Quality And Delivery use?

Knowledge Engineering Quality And Delivery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Engineering Quality And Delivery 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 Knowledge Engineering Quality And Delivery?

Skills that share tags, products or a category with Knowledge Engineering Quality And Delivery: CI Triage (andymai/brepjs, 114 stars), Flaker Storage Cache On CI (mizchi/skills, 356 stars), Repo Hygiene Scan and Fix (QwenLM/qwen-code, 28k stars) and Ccb GitHub (SeemSeam/claude_codex_bridge, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Engineering Quality And Delivery?

echoVic (a GitHub user) maintains it in echoVic/blade-code, which has 181 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 27, 2026.

Source: echoVic/blade-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.