@givolt/i3-composer-agent 2.1.1 → 2.2.1

package/docs/opencode-setup.md

@@ -1,5 +1,13 @@
 # OpenCode Setup
 
+<!-- i3:zh-guide:start -->
+## 中文使用说明
+
+按下文完整工程步骤、检查项与验证条件执行。根据任务选择适用步骤，保留证据、风险和退出条件；正文示例中的英文标签在面向用户输出时译为中文。
+
+默认使用简体中文解释、追问及生成报告；用户明确要求其他语言时可切换。原方法正文、引用、阈值和审批条件完整保留。代码标识、路径、命令、工具参数、JSON 键/枚举与原文引用保持原样。
+<!-- i3:zh-guide:end -->
+
 This guide explains how to use i3 Composer Agent with OpenCode. The reusable assets are the markdown skills in the `skills/` directory; the root `AGENTS.md` file in this repository is repo-scoped and should not be copied into other projects.
 
 ## Overview

package/docs/other-hosts.md

@@ -1,5 +1,13 @@
 # Other hosts
 
+<!-- i3:zh-guide:start -->
+## 中文使用说明
+
+按下文完整工程步骤、检查项与验证条件执行。根据任务选择适用步骤，保留证据、风险和退出条件；正文示例中的英文标签在面向用户输出时译为中文。
+
+默认使用简体中文解释、追问及生成报告；用户明确要求其他语言时可切换。原方法正文、引用、阈值和审批条件完整保留。代码标识、路径、命令、工具参数、JSON 键/枚举与原文引用保持原样。
+<!-- i3:zh-guide:end -->
+
 These hosts install the pack but are not in the README's install section, because no maintainer has run the current release on them. Each entry is one line: the host and its install command. To add one, see [Adding a Host Guide](../CONTRIBUTING.md#adding-a-host-guide).
 
 Skills are plain `SKILL.md` folders, so any agent that reads the i3 Composer Agent layout can load them. See [getting-started.md](getting-started.md).

package/docs/windsurf-setup.md

@@ -1,5 +1,13 @@
 # Using i3-composer-agent with Windsurf
 
+<!-- i3:zh-guide:start -->
+## 中文使用说明
+
+按下文完整工程步骤、检查项与验证条件执行。根据任务选择适用步骤，保留证据、风险和退出条件；正文示例中的英文标签在面向用户输出时译为中文。
+
+默认使用简体中文解释、追问及生成报告；用户明确要求其他语言时可切换。原方法正文、引用、阈值和审批条件完整保留。代码标识、路径、命令、工具参数、JSON 键/枚举与原文引用保持原样。
+<!-- i3:zh-guide:end -->
+
 ## Setup
 
 ### Project Rules

package/docs/workbuddy-setup.md

@@ -1,40 +1,35 @@
-# Using i3 Composer Agent with WorkBuddy
+# 在 WorkBuddy 使用 i3 Composer Agent
 
-## Recommended global installation
-
-Install WorkBuddy assets in its user configuration directory:
+## 推荐全局安装
 
 ```bash
 npx @givolt/i3-composer-agent --workbuddy --scope global
-```
-
-The terminal wizard preselects WorkBuddy and confirms the global installation.
-For installation without prompts:
-
-```bash
 npx @givolt/i3-composer-agent --workbuddy --scope global --yes
 npx @givolt/i3-composer-agent --agents codebuddy,workbuddy --scope global --yes
 ```
 
-Global WorkBuddy installation includes:
+向导中 WorkBuddy 位于第 2 项，预选后仍可多选。全局目录：
+
+- `~/.workbuddy/skills/`：25 个 `i3-` 技能，选择说明和默认回复中文。
+- `~/.workbuddy/commands/`：9 个 `/i3-*` 短命令。
+- `~/.workbuddy/agents/`：4 个专业角色。
+- `~/.workbuddy/references/`：共享参考和标准 MIT 许可。
+- `~/.workbuddy/docs/agents.md`：角色说明。
+- `~/.workbuddy/i3-composer-agent/`：完整评测、Hook、脚本及依赖资料。
+- `~/.workbuddy/.i3-composer-agent.json`：安装内容所有权及客户端清单。
 
-- `~/.workbuddy/skills/`: all 25 Skills with their existing `i3-` IDs.
-- `~/.workbuddy/commands/`: all 9 short `/i3-*` workflows.
-- `~/.workbuddy/agents/`: all 4 Agents (role definitions).
-- `~/.workbuddy/references/`: shared references and the standard MIT license.
-- `~/.workbuddy/docs/agents.md`: Agent role documentation.
-- `~/.workbuddy/.i3-composer-agent.json`: managed asset and client records.
+自定义 profile 可设置 `WORKBUDDY_CONFIG_DIR`，安装后打开对应 profile。
+WorkBuddy 的目录选择使用自己的配置，不借用 `CODEBUDDY_CONFIG_DIR`。
 
-If you use a separate WorkBuddy profile, set `WORKBUDDY_CONFIG_DIR` to its
-configuration directory when installing. The installer does not borrow
-`CODEBUDDY_CONFIG_DIR` for WorkBuddy. Open the corresponding profile in the host.
+## 配套检查
 
-## Discovery and invocation
+进入 `~/.workbuddy/i3-composer-agent/` 运行 `npm test`，检查技能格式及中英文触发，
+不会调用模型。项目安装对应 `.codebuddy/i3-composer-agent/`。行为评测用例、样例和
+脚本用法见 [评测说明](../evals/README.md)。Hook 文件默认提供，启用需适配宿主事件协议。
 
-Open your project in WorkBuddy and start a new chat after installation. Type `/`
-to inspect Commands, and open the Skills list. Global installation resolves the
-desktop Skills list issue observed in WorkBuddy 5.7.7 and confirmed by user testing.
-Examples:
+## 发现和调用
+
+安装后新建会话，查看 Skills 列表并输入 `/` 查看命令：
 
 ```text
 /i3-spec
@@ -45,62 +40,43 @@ Examples:
 /i3-ship
 ```
 
-Commands invoke the installed Skill IDs without a plugin namespace. Native
-Buddy commands refer to `CODEBUDDY.md` and the installed persona directories.
-Shared project commands refer to the current host's user-level persona directory
-so they work for either client. `/i3-ship` uses native subagents when available
-and reads the installed persona prompts sequentially otherwise. Skill content,
-`$ARGUMENTS`, workflow approval gates, and relative reference links are retained.
-
-The [task-bar command documentation](https://www.codebuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Task-Bar)
-describes command discovery, and the [CLI command documentation](https://www.codebuddy.cn/docs/cli/slash-commands)
-describes Markdown commands and `$ARGUMENTS`.
+命令调用安装的技能 ID，按 `CODEBUDDY.md` 与安装后的角色目录工作。
+`/i3-ship` 支持时使用原生子代理并行审查，不可用时读取三个角色提示顺序执行，
+主会话汇总 GO/NO-GO 与必需回滚计划。保留参数、审批边界和相对参考链接。
 
-## Project installation and mixed clients
+## 项目与多客户端
 
-| Selected clients | Project files | Global files |
+| 选择 | 项目目录 | 全局目录 |
 | --- | --- | --- |
 | CodeBuddy | `.codebuddy/` | `~/.codebuddy/` |
-| WorkBuddy | `.codebuddy/` (desktop Skills list limitation) | `~/.workbuddy/` (recommended) |
-| CodeBuddy and WorkBuddy | One shared `.codebuddy/` installation | One installation in each client's directory |
-
-Project installation remains available for shared `.codebuddy/` assets. However,
-WorkBuddy 5.7.7 scans `.workbuddy/skills/` for its desktop Skills list, so Skills
-installed at `.codebuddy/skills/` do not appear there even though Commands are
-discoverable. The [WorkBuddy project documentation](https://www.codebuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Project)
-describes `.codebuddy/` paths; that documentation does not establish desktop
-Skills list compatibility for this host version.
+| WorkBuddy | `.codebuddy/` | `~/.workbuddy/`（推荐） |
+| 两者 | 共用一次 `.codebuddy/` 安装 | 各自独立安装 |
 
-For CodeBuddy at project scope and WorkBuddy at global scope, run:
+已观察到 WorkBuddy 5.7.7 桌面 Skills 列表扫描 `.workbuddy/skills/`，
+所以项目安装的 `.codebuddy/skills/` 可能不显示，项目命令仍可发现。
+全局安装已由用户测试确认可发现技能。项目原有 `.workbuddy/` 设置保留。
+也可混合选择：
 
 ```bash
 npx @givolt/i3-composer-agent --codebuddy --scope project --yes
 npx @givolt/i3-composer-agent --workbuddy --scope global --yes
 ```
 
-Existing `.workbuddy/` project settings are preserved. A shared project
-installation may add `.codebuddy/`, so both directories can exist in a workspace.
-
-## Adding a second client or upgrading
-
-When both clients use project scope, either can be installed first. Installing
-the other at the same package version and scope reuses unmodified manifest-owned
-files and merges the client IDs. It does not create a second project copy. Global
-installations remain independent. Missing files are restored;
-unrelated settings and custom command filenames are preserved.
+## 追加客户端与升级
 
-Review an upgrade or conflict before replacing files:
+同版本/范围的清单所属未修改内容复用，第二个客户端合并到清单，不建立第二份项目副本。
+缺失内容可恢复，设置与自定义命令文件名保留。升级或冲突可先查看：
 
 ```bash
 npx @givolt/i3-composer-agent --workbuddy --scope global --dry-run
 npx @givolt/i3-composer-agent --workbuddy --scope global --yes --force
 ```
 
-Modified assets, unowned filename collisions and different versions require
-confirmation or `--force`. Successful replacements remove old files and managed
-historical backups. If installation fails, the previous files are restored.
+升级、修改内容和未登记同名冲突需要确认；成功替换后清理旧文件与所属历史备份，失败恢复。
+原生安装同时提供 Skills、Commands、Agents 和完整 evals/hooks/scripts 配套。
+`--prepare --workbuddy` 不支持，原生安装不会启用插件 Hook。
 
-Native installation provides Commands, Skills and Agent role definitions. It does not register
-a WorkBuddy plugin or enable plugin hooks; `--prepare --workbuddy` is unsupported.
-File installation and command discovery are separate from model execution and
-workflow acceptance in the host.
+可参照 [任务栏命令说明](https://www.codebuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Task-Bar)、
+[命令格式](https://www.codebuddy.cn/docs/cli/slash-commands) 和
+[项目目录说明](https://www.codebuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Project)。
+目录落盘、发现与模型行为分别验收。

package/evals/README.md

@@ -0,0 +1,86 @@
+# 技能评测与配套脚本
+
+本目录随默认安装、npm 包和插件导出一起提供，评测 i3 Composer Agent 技能的结构、
+触发与行为。评测不在安装时自动执行。它检查技能库自身，不能代替业务项目测试、
+宿主发现验证或真实模型验收。
+
+## 运行位置
+
+原生安装的完整配套目录是宿主目录下的 `i3-composer-agent/`。
+例如 CodeBuddy 项目安装为 `.codebuddy/i3-composer-agent/`，
+WorkBuddy 全局安装为 `~/.workbuddy/i3-composer-agent/`。
+先进入该目录；若使用 `--prepare` / `--extract`，进入指定的导出目录。
+配套目录保留技能、命令、角色、参考资料和插件清单，保证校验及 Hook 的相对路径可解析。
+宿主实际使用的原生入口仍位于它自己的 `skills/`、`commands/`、`agents/`。
+
+## 不调用模型的检查
+
+需要 Node.js 20 或以上，无需额外 npm 依赖。
+
+```bash
+# 技能格式、清单版本、三种命令格式一致性、引用与产物路径
+npm run validate
+
+# 中英文分别检查；省略 --locale 时检查两种语言
+node scripts/run-evals.js --locale zh-CN --min-rank1 95
+node scripts/run-evals.js --locale en --min-rank1 95
+
+# 一次运行结构检查和中英文触发评测
+npm test
+```
+
+`scripts/` 包含 `run-evals.js`、五个 `validate-*.js` 和它们依赖的 `lib/skill-lint.js`。
+`evals/cases/` 保留英文用例，`evals/zh-CN/cases/` 提供中文用例，
+`evals/fixtures/` 是执行型评测使用的测试项目样例，`evals/plugin/` 是插件级评测用例。
+
+触发评测使用词法评分检查正例、负例、描述冲突、用例结构及样例是否齐全。
+中英文各自满足指定门槛；这不能证明模型在实际宿主中一定选择正确技能。
+失败时应调查技能描述或实现，不能为了通过检查降低门槛或删改失败用例。
+
+## 主动运行模型行为评测
+
+先预览，不调用模型、不生成评测结果：
+
+```bash
+node scripts/run-evals.js --behavioral i3-test-driven-development --locale zh-CN --dry-run
+```
+
+确认需要后，移除 `--dry-run` 才会调用已登录的 Claude Code，并消耗该账户的模型额度：
+
+```bash
+node scripts/run-evals.js --behavioral i3-test-driven-development --locale zh-CN
+```
+
+执行型用例需要 Git，并在临时 Git 项目中复制 `fixtures/` 的真实输入；
+对话型用例评估对话，不要求项目文件。执行器使用 `acceptEdits` 及明确的工具列表，
+可能编辑文件、运行命令、访问网络；各样例还可能需要自身的语言运行环境。
+评分依据执行轨迹或对话与 `expectations`，不会把“声称完成”当成实际执行证据。
+模型输出按不可信数据评分，执行和评分均有限时。临时项目完成后清理。
+
+`--locale en` 运行英文用例，省略该参数运行两种语言。可通过 `I3_EVAL_MODEL`
+和 `I3_EVAL_GRADER_MODEL` 指定执行/评分模型；报告同时记录宿主和模型信息。
+结果写入 `evals/results/`，不会进入发行包，也不属于安装器的替换清单。
+
+## 插件级评测
+
+插件清单中的 `experimental.evals` 指向随包提供的 `evals/plugin/`。
+它包含整体插件的触发/不触发提示和评分规则；支持 `plugin eval` 的 Claude Code
+可从配套目录主动运行：
+
+```bash
+claude plugin eval . --no-publish
+```
+
+该检查同样会调用模型；具体参数以当前 Claude Code 的帮助为准。
+`--no-publish` 保持结果本地，报告写入 `evals/plugin/results/`。
+用是否触发、回答质量及对照结果一起判断效果；调用一次成功不能代替多次行为验收。
+
+## Hooks
+
+`hooks/` 默认交付会话注入、文档缓存、代码块保护脚本及说明。
+安装文件不会自动注册事件。中文回复与普通技能调用不依赖启用 Hook。
+会话注入仅适用于缺少原生技能路由的宿主；已有路由时不要重复注入。
+缓存及保护的当前配置示例针对 Claude Code，详见
+[文档缓存](../hooks/SDD-CACHE.md) 和 [代码块保护](../hooks/SIMPLIFY-IGNORE.md)。
+其他宿主须按各自事件协议适配。脚本需要 Bash、jq 及说明中的 curl/哈希工具；
+Windows PowerShell 本身不提供这些依赖。

package/evals/cases/i3-api-and-interface-design.json

@@ -0,0 +1,45 @@
+{
+  "skill_name": "i3-api-and-interface-design",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Design a REST endpoint for creating invoices, including error responses and versioning",
+        "top_k": 3
+      },
+      {
+        "prompt": "What should the public interface of this payments module expose to other teams?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Help me define the contract between the frontend and the orders service",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "My unit test is failing with a null pointer exception",
+        "owner": "i3-debugging-and-error-recovery"
+      },
+      {
+        "prompt": "Make this landing page responsive on mobile",
+        "owner": "i3-frontend-ui-engineering"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Design the public API for a URL-shortening service: create, resolve, stats. Produce the endpoint contracts.",
+      "expected_output": "Endpoint contracts with methods, paths, request/response shapes, and explicit error semantics",
+      "files": [
+        "i3-api-and-interface-design"
+      ],
+      "expectations": [
+        "Error responses are specified with status codes and a consistent error shape, not just happy paths",
+        "Input validation at the boundary is addressed for user-supplied URLs",
+        "Versioning or compatibility strategy is stated",
+        "The response does not silently invent unstated requirements"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-browser-testing-with-devtools.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "i3-browser-testing-with-devtools",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Use Chrome DevTools to figure out why the checkout button click does nothing",
+        "top_k": 3
+      },
+      {
+        "prompt": "Inspect the network requests the dashboard makes when it first loads",
+        "top_k": 3
+      },
+      {
+        "prompt": "Verify in a real browser that the form submits and the data persists in localStorage",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Write a spec for the new billing feature before we start",
+        "owner": "i3-spec-driven-development"
+      },
+      {
+        "prompt": "Break this PRD into ordered implementation tasks",
+        "owner": "i3-planning-and-task-breakdown"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "The signup form renders but submitting it appears to do nothing. Verify the real behavior in the browser and report findings.",
+      "expected_output": "Runtime evidence from the browser: console errors, network activity, DOM state, and a diagnosis",
+      "files": [
+        "i3-browser-testing-with-devtools"
+      ],
+      "expectations": [
+        "Findings are grounded in observed runtime data (console, network, DOM), not static code reading alone",
+        "The report distinguishes what was observed from what is inferred",
+        "A concrete next step or fix hypothesis is provided"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-ci-cd-and-automation.json

@@ -0,0 +1,45 @@
+{
+  "skill_name": "i3-ci-cd-and-automation",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Set up a GitHub Actions pipeline that runs the tests on every pull request",
+        "top_k": 3
+      },
+      {
+        "prompt": "Add a deploy stage to the pipeline with a manual approval gate",
+        "top_k": 3
+      },
+      {
+        "prompt": "Automate the quality gates so nothing merges without passing checks",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Refactor this function so it is easier to read",
+        "owner": "i3-code-simplification"
+      },
+      {
+        "prompt": "Add structured logging to the checkout service",
+        "owner": "i3-observability-and-instrumentation"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Create a CI pipeline for a Node project: install, lint, test on every PR, and block merge on failure.",
+      "expected_output": "A working workflow definition with correct triggers, steps, and failure behavior",
+      "files": [
+        "i3-ci-cd-and-automation"
+      ],
+      "expectations": [
+        "The workflow triggers on pull requests",
+        "Failure of any quality gate fails the pipeline run",
+        "Steps are ordered logically and cache or setup steps are sane",
+        "No secrets are hardcoded in the workflow"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-code-review-and-quality.json

@@ -0,0 +1,49 @@
+{
+  "skill_name": "i3-code-review-and-quality",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Review this pull request before I merge it",
+        "top_k": 3
+      },
+      {
+        "prompt": "Do a quality pass on this diff for correctness and readability",
+        "top_k": 3
+      },
+      {
+        "prompt": "Can you review the changes another model just wrote for me?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Review this diff before I merge it. It adds paging to the orders endpoint.",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Deploy this to production now",
+        "owner": "i3-shipping-and-launch"
+      },
+      {
+        "prompt": "Write a failing test for the bug before fixing it",
+        "owner": "i3-test-driven-development"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Review the provided diff that adds a user-search endpoint. Deliver a structured review.",
+      "expected_output": "A multi-axis review with severity-labelled findings and file:line references",
+      "files": [
+        "i3-code-review-and-quality"
+      ],
+      "expectations": [
+        "Findings cover more than one axis (correctness, readability, architecture, security, performance)",
+        "Every finding carries a severity label from the skill's taxonomy",
+        "Security of user input is explicitly considered for the new endpoint",
+        "The review leads with high-leverage findings rather than nits"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-code-simplification.json

@@ -0,0 +1,45 @@
+{
+  "skill_name": "i3-code-simplification",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "This function works but it is way too clever, simplify it without changing behavior",
+        "top_k": 3
+      },
+      {
+        "prompt": "Reduce the complexity of this module so juniors can maintain it",
+        "top_k": 3
+      },
+      {
+        "prompt": "Clean up this working code, it has grown hard to follow",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Add a feature flag system to the app",
+        "owner": "i3-incremental-implementation"
+      },
+      {
+        "prompt": "Diagnose why the build broke overnight",
+        "owner": "i3-debugging-and-error-recovery"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Simplify the provided 80-line function that parses config files, preserving exact behavior.",
+      "expected_output": "A simpler implementation with identical behavior and a summary of what was removed and why",
+      "files": [
+        "i3-code-simplification"
+      ],
+      "expectations": [
+        "Behavior is preserved (tests unchanged and passing, or equivalence argued concretely)",
+        "Complexity is reduced rather than relocated",
+        "The response explains what was removed and why it was safe",
+        "No new features are added during the simplification"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-constraint-driven-development.json

@@ -0,0 +1,79 @@
+{
+  "skill_name": "i3-constraint-driven-development",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "Set up quality constraints for this project — I want to define our bar before the agent writes more code",
+        "top_k": 3
+      },
+      {
+        "prompt": "We have no written standards. Ask me what I care about and write it down with sane defaults",
+        "top_k": 3
+      },
+      {
+        "prompt": "The agent keeps adding @ts-ignore and skipping tests to get green. How do I stop that?",
+        "top_k": 3
+      },
+      {
+        "prompt": "What coverage threshold should we enforce, and where should it run so it doesn't slow us down?",
+        "top_k": 3
+      },
+      {
+        "prompt": "I care about accessibility and web performance — set those up as enforced constraints",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Review this pull request across correctness and security",
+        "owner": "i3-code-review-and-quality"
+      },
+      {
+        "prompt": "Add a deploy stage to our pipeline with a manual approval gate",
+        "owner": "i3-ci-cd-and-automation"
+      },
+      {
+        "prompt": "Write a failing test for this bug before we fix it",
+        "owner": "i3-test-driven-development"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "kind": "dialogue",
+      "prompt": "Set up constraints for this repo. I don't really know what numbers to pick.",
+      "expected_output": "A short interview with defaults offered, followed by a CONSTRAINTS.md the user can explain",
+      "expectations": [
+        "The agent inspects the repo for stack, test runner, and existing linters before asking anything",
+        "No more than four questions are asked, and each one carries a usable default",
+        "When the user has no target number, the agent proposes recording today's value and holding it rather than inventing a threshold",
+        "The resulting constraints say where each check runs, keeping fast checks in the edit loop and slow checks later",
+        "Every number written down is accompanied by a reason"
+      ]
+    },
+    {
+      "id": 2,
+      "kind": "dialogue",
+      "prompt": "Our coverage is 62% and I want to enforce 85% starting today.",
+      "expected_output": "Pushback on setting an unmeetable budget, with the ratchet alternative offered",
+      "expectations": [
+        "The agent points out that a threshold the codebase fails today produces a permanently red build",
+        "It offers to record 62% and require that it not fall, as an adoptable alternative",
+        "It does not silently accept 85% without noting the consequence"
+      ]
+    },
+    {
+      "id": 3,
+      "kind": "dialogue",
+      "prompt": "Accessibility matters to us. Add it as a constraint.",
+      "expected_output": "A working accessibility check, not just a threshold written down",
+      "expectations": [
+        "The agent names axe-core and gives the install and run commands rather than only stating a violation threshold",
+        "It notes that axe needs a running URL and asks for one, or drops the dimension if the project has no URL to hit",
+        "The command that produces the verdict is recorded alongside the rule in CONSTRAINTS.md",
+        "The check is placed at the preview-deploy stage rather than in the per-edit loop"
+      ]
+    }
+  ]
+}

package/evals/cases/i3-context-engineering.json

@@ -0,0 +1,44 @@
+{
+  "skill_name": "i3-context-engineering",
+  "trigger": {
+    "positive": [
+      {
+        "prompt": "What context should I load into the agent before starting this refactor?",
+        "top_k": 3
+      },
+      {
+        "prompt": "The model's output quality dropped mid-session, how do I fix its context?",
+        "top_k": 3
+      },
+      {
+        "prompt": "Set up rules files and context packing for my repository",
+        "top_k": 3
+      }
+    ],
+    "negative": [
+      {
+        "prompt": "Write unit tests for the date parser",
+        "owner": "i3-test-driven-development"
+      },
+      {
+        "prompt": "Harden this endpoint against SQL injection",
+        "owner": "i3-security-and-hardening"
+      }
+    ]
+  },
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "An agent session has degraded: responses are generic and it keeps forgetting project conventions. Fix the context setup.",
+      "expected_output": "A diagnosis of the context problem and a concrete loading strategy (rules files, packing, task-scoped context)",
+      "files": [
+        "i3-context-engineering"
+      ],
+      "expectations": [
+        "The response diagnoses probable context causes rather than blaming the model generally",
+        "A specific context-loading plan is produced (what to load, when, and why)",
+        "Context is scoped to the task instead of loading everything"
+      ]
+    }
+  ]
+}