@zmice/zc 0.2.8 → 0.3.0

package/vendor/packages/toolkit/src/content/skills/using-agent-skills/body.md

@@ -1,193 +1,193 @@
-# Using Agent Skills
-
-## Overview
-
-Agent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.
-
-## Skill Discovery
-
-When a task arrives, identify the development phase and apply the corresponding skill:
-
-```
-Task arrives
-    │
-    ├── Vague idea/need refinement? ──→ idea-refine
-    ├── New project/feature/change? ──→ spec-driven-development
-    ├── Have a spec, need tasks? ──────→ planning-and-task-breakdown
-    ├── Implementing code? ────────────→ incremental-implementation
-    │   ├── UI work? ─────────────────→ frontend-ui-engineering
-    │   ├── API work? ────────────────→ api-and-interface-design
-    │   ├── Need better context? ─────→ context-engineering
-    │   └── Need doc-verified code? ───→ source-driven-development
-    ├── Writing/running tests? ────────→ test-driven-development
-    │   └── Browser-based? ───────────→ browser-testing-with-devtools
-    ├── Something broke? ──────────────→ debugging-and-error-recovery
-    ├── Reviewing code? ───────────────→ code-review-and-quality
-    │   ├── Security concerns? ───────→ security-and-hardening
-    │   └── Performance concerns? ────→ performance-optimization
-    ├── Committing/branching? ─────────→ git-workflow-and-versioning
-    ├── CI/CD pipeline work? ──────────→ ci-cd-and-automation
-    ├── Writing docs/ADRs? ───────────→ documentation-and-adrs
-    └── Deploying/launching? ─────────→ shipping-and-launch
-```
-
-## Routing Metadata and Context Loading
-
-Skill discovery depends on short metadata before the full skill is loaded. Treat each
-skill description as an activation contract:
-
-- It must say what capability the skill provides.
-- It must say when to activate it.
-- It should include exclusions when a nearby skill would be a better fit.
-- It should not summarize the entire workflow; the agent should read the full skill
-  only after the skill is selected.
-
-Prefer on-demand skill loading over always-on context. Persistent files such as
-`AGENTS.md`, `GEMINI.md`, `CLAUDE.md`, or platform rules should contain stable project
-conventions and canonical routing only. Do not load every skill into every session;
-that wastes context and makes phase-specific rules compete with each other.
-
-When a platform has native skill discovery, use its native directory or metadata model.
-When it does not, use agent-driven routing through the project entry file. Do not imply
-native plugin or slash-command behavior that the platform does not actually support.
-
-## Core Operating Behaviors
-
-These behaviors apply at all times, across all skills. They are non-negotiable.
-
-### 1. Surface Assumptions
-
-Before implementing anything non-trivial, explicitly state your assumptions:
-
-```
-ASSUMPTIONS I'M MAKING:
-1. [assumption about requirements]
-2. [assumption about architecture]
-3. [assumption about scope]
-→ Correct me now or I'll proceed with these.
-```
-
-Don't silently fill in ambiguous requirements. The most common failure mode is making wrong assumptions and running with them unchecked. Surface uncertainty early — it's cheaper than rework.
-
-### 2. Manage Confusion Actively
-
-When you encounter inconsistencies, conflicting requirements, or unclear specifications:
-
-1. **STOP.** Do not proceed with a guess.
-2. Name the specific confusion.
-3. Present the tradeoff or ask the clarifying question.
-4. Wait for resolution before continuing.
-
-**Bad:** Silently picking one interpretation and hoping it's right.
-**Good:** "I see X in the spec but Y in the existing code. Which takes precedence?"
-
-### 3. Push Back When Warranted
-
-You are not a yes-machine. When an approach has clear problems:
-
-- Point out the issue directly
-- Explain the concrete downside (quantify when possible — "this adds ~200ms latency" not "this might be slower")
-- Propose an alternative
-- Accept the human's decision if they override with full information
-
-Sycophancy is a failure mode. "Of course!" followed by implementing a bad idea helps no one. Honest technical disagreement is more valuable than false agreement.
-
-### 4. Enforce Simplicity
-
-Your natural tendency is to overcomplicate. Actively resist it.
-
-Before finishing any implementation, ask:
-- Can this be done in fewer lines?
-- Are these abstractions earning their complexity?
-- Would a staff engineer look at this and say "why didn't you just..."?
-
-If you build 1000 lines and 100 would suffice, you have failed. Prefer the boring, obvious solution. Cleverness is expensive.
-
-### 5. Maintain Scope Discipline
-
-Touch only what you're asked to touch.
-
-Do NOT:
-- Remove comments you don't understand
-- "Clean up" code orthogonal to the task
-- Refactor adjacent systems as a side effect
-- Delete code that seems unused without explicit approval
-- Add features not in the spec because they "seem useful"
-
-Your job is surgical precision, not unsolicited renovation.
-
-### 6. Verify, Don't Assume
-
-Every skill includes a verification step. A task is not complete until verification passes. "Seems right" is never sufficient — there must be evidence (passing tests, build output, runtime data).
-
-## Failure Modes to Avoid
-
-These are the subtle errors that look like productivity but create problems:
-
-1. Making wrong assumptions without checking
-2. Not managing your own confusion — plowing ahead when lost
-3. Not surfacing inconsistencies you notice
-4. Not presenting tradeoffs on non-obvious decisions
-5. Being sycophantic ("Of course!") to approaches with clear problems
-6. Overcomplicating code and APIs
-7. Modifying code or comments orthogonal to the task
-8. Removing things you don't fully understand
-9. Building without a spec because "it's obvious"
-10. Skipping verification because "it looks right"
-
-## Skill Rules
-
-1. **Check for an applicable skill before starting work.** Skills encode processes that prevent common mistakes.
-
-2. **Skills are workflows, not suggestions.** Follow the steps in order. Don't skip verification steps.
-
-3. **Load only the skills needed for the current phase.** If a task moves from planning to implementation, switch skills instead of carrying the entire planning context forward.
-
-4. **Multiple skills can apply in sequence.** A feature implementation might involve `idea-refine` → `spec-driven-development` → `planning-and-task-breakdown` → `incremental-implementation` → `test-driven-development` → `code-review-and-quality` → `shipping-and-launch`.
-
-5. **When in doubt, start with a spec.** If the task is non-trivial and there's no spec, begin with `spec-driven-development`.
-
-6. **Ask only when it changes the route.** If the correct skill can be inferred from evidence, select it and state the assumption. Ask only for high-stakes ambiguity, conflicting goals, or missing context that would change the workflow.
-
-## Lifecycle Sequence
-
-For a complete feature, the typical skill sequence is:
-
-```
-1. idea-refine                 → Refine vague ideas
-2. spec-driven-development     → Define what we're building
-3. planning-and-task-breakdown → Break into verifiable chunks
-4. context-engineering         → Load the right context
-5. source-driven-development   → Verify against official docs
-6. incremental-implementation  → Build slice by slice
-7. test-driven-development     → Prove each slice works
-8. code-review-and-quality     → Review before merge
-9. git-workflow-and-versioning → Clean commit history
-10. documentation-and-adrs     → Document decisions
-11. shipping-and-launch        → Deploy safely
-```
-
-Not every task needs every skill. A bug fix might only need: `debugging-and-error-recovery` → `test-driven-development` → `code-review-and-quality`.
-
-## Quick Reference
-
-| Phase | Skill | One-Line Summary |
-|-------|-------|-----------------|
-| Define | idea-refine | Refine ideas through structured divergent and convergent thinking |
-| Define | spec-driven-development | Requirements and acceptance criteria before code |
-| Plan | planning-and-task-breakdown | Decompose into small, verifiable tasks |
-| Build | incremental-implementation | Thin vertical slices, test each before expanding |
-| Build | source-driven-development | Verify against official docs before implementing |
-| Build | context-engineering | Right context at the right time |
-| Build | frontend-ui-engineering | Production-quality UI with accessibility |
-| Build | api-and-interface-design | Stable interfaces with clear contracts |
-| Verify | test-driven-development | Failing test first, then make it pass |
-| Verify | browser-testing-with-devtools | Chrome DevTools MCP for runtime verification |
-| Verify | debugging-and-error-recovery | Reproduce → localize → fix → guard |
-| Review | code-review-and-quality | Five-axis review with quality gates |
-| Review | security-and-hardening | OWASP prevention, input validation, least privilege |
-| Review | performance-optimization | Measure first, optimize only what matters |
-| Ship | git-workflow-and-versioning | Atomic commits, clean history |
-| Ship | ci-cd-and-automation | Automated quality gates on every change |
-| Ship | documentation-and-adrs | Document the why, not just the what |
-| Ship | shipping-and-launch | Pre-launch checklist, monitoring, rollback plan |
+# Using Agent Skills
+
+## Overview
+
+Agent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.
+
+## Skill Discovery
+
+When a task arrives, identify the development phase and apply the corresponding skill:
+
+```
+Task arrives
+    │
+    ├── Vague idea/need refinement? ──→ idea-refine
+    ├── New project/feature/change? ──→ spec-driven-development
+    ├── Have a spec, need tasks? ──────→ planning-and-task-breakdown
+    ├── Implementing code? ────────────→ incremental-implementation
+    │   ├── UI work? ─────────────────→ frontend-ui-engineering
+    │   ├── API work? ────────────────→ api-and-interface-design
+    │   ├── Need better context? ─────→ context-engineering
+    │   └── Need doc-verified code? ───→ source-driven-development
+    ├── Writing/running tests? ────────→ test-driven-development
+    │   └── Browser-based? ───────────→ browser-qa-testing
+    ├── Something broke? ──────────────→ debugging-and-error-recovery
+    ├── Reviewing code? ───────────────→ code-review-and-quality
+    │   ├── Security concerns? ───────→ security-and-hardening
+    │   └── Performance concerns? ────→ performance-optimization
+    ├── Committing/branching? ─────────→ git-workflow-and-versioning
+    ├── CI/CD pipeline work? ──────────→ ci-cd-and-automation
+    ├── Writing docs/ADRs? ───────────→ documentation-and-adrs
+    └── Deploying/launching? ─────────→ shipping-and-launch
+```
+
+## Routing Metadata and Context Loading
+
+Skill discovery depends on short metadata before the full skill is loaded. Treat each
+skill description as an activation contract:
+
+- It must say what capability the skill provides.
+- It must say when to activate it.
+- It should include exclusions when a nearby skill would be a better fit.
+- It should not summarize the entire workflow; the agent should read the full skill
+  only after the skill is selected.
+
+Prefer on-demand skill loading over always-on context. Persistent files such as
+`AGENTS.md`, `GEMINI.md`, `CLAUDE.md`, or platform rules should contain stable project
+conventions and canonical routing only. Do not load every skill into every session;
+that wastes context and makes phase-specific rules compete with each other.
+
+When a platform has native skill discovery, use its native directory or metadata model.
+When it does not, use agent-driven routing through the project entry file. Do not imply
+native plugin or slash-command behavior that the platform does not actually support.
+
+## Core Operating Behaviors
+
+These behaviors apply at all times, across all skills. They are non-negotiable.
+
+### 1. Surface Assumptions
+
+Before implementing anything non-trivial, explicitly state your assumptions:
+
+```
+ASSUMPTIONS I'M MAKING:
+1. [assumption about requirements]
+2. [assumption about architecture]
+3. [assumption about scope]
+→ Correct me now or I'll proceed with these.
+```
+
+Don't silently fill in ambiguous requirements. The most common failure mode is making wrong assumptions and running with them unchecked. Surface uncertainty early — it's cheaper than rework.
+
+### 2. Manage Confusion Actively
+
+When you encounter inconsistencies, conflicting requirements, or unclear specifications:
+
+1. **STOP.** Do not proceed with a guess.
+2. Name the specific confusion.
+3. Present the tradeoff or ask the clarifying question.
+4. Wait for resolution before continuing.
+
+**Bad:** Silently picking one interpretation and hoping it's right.
+**Good:** "I see X in the spec but Y in the existing code. Which takes precedence?"
+
+### 3. Push Back When Warranted
+
+You are not a yes-machine. When an approach has clear problems:
+
+- Point out the issue directly
+- Explain the concrete downside (quantify when possible — "this adds ~200ms latency" not "this might be slower")
+- Propose an alternative
+- Accept the human's decision if they override with full information
+
+Sycophancy is a failure mode. "Of course!" followed by implementing a bad idea helps no one. Honest technical disagreement is more valuable than false agreement.
+
+### 4. Enforce Simplicity
+
+Your natural tendency is to overcomplicate. Actively resist it.
+
+Before finishing any implementation, ask:
+- Can this be done in fewer lines?
+- Are these abstractions earning their complexity?
+- Would a staff engineer look at this and say "why didn't you just..."?
+
+If you build 1000 lines and 100 would suffice, you have failed. Prefer the boring, obvious solution. Cleverness is expensive.
+
+### 5. Maintain Scope Discipline
+
+Touch only what you're asked to touch.
+
+Do NOT:
+- Remove comments you don't understand
+- "Clean up" code orthogonal to the task
+- Refactor adjacent systems as a side effect
+- Delete code that seems unused without explicit approval
+- Add features not in the spec because they "seem useful"
+
+Your job is surgical precision, not unsolicited renovation.
+
+### 6. Verify, Don't Assume
+
+Every skill includes a verification step. A task is not complete until verification passes. "Seems right" is never sufficient — there must be evidence (passing tests, build output, runtime data).
+
+## Failure Modes to Avoid
+
+These are the subtle errors that look like productivity but create problems:
+
+1. Making wrong assumptions without checking
+2. Not managing your own confusion — plowing ahead when lost
+3. Not surfacing inconsistencies you notice
+4. Not presenting tradeoffs on non-obvious decisions
+5. Being sycophantic ("Of course!") to approaches with clear problems
+6. Overcomplicating code and APIs
+7. Modifying code or comments orthogonal to the task
+8. Removing things you don't fully understand
+9. Building without a spec because "it's obvious"
+10. Skipping verification because "it looks right"
+
+## Skill Rules
+
+1. **Check for an applicable skill before starting work.** Skills encode processes that prevent common mistakes.
+
+2. **Skills are workflows, not suggestions.** Follow the steps in order. Don't skip verification steps.
+
+3. **Load only the skills needed for the current phase.** If a task moves from planning to implementation, switch skills instead of carrying the entire planning context forward.
+
+4. **Multiple skills can apply in sequence.** A feature implementation might involve `idea-refine` → `spec-driven-development` → `planning-and-task-breakdown` → `incremental-implementation` → `test-driven-development` → `code-review-and-quality` → `shipping-and-launch`.
+
+5. **When in doubt, start with a spec.** If the task is non-trivial and there's no spec, begin with `spec-driven-development`.
+
+6. **Ask only when it changes the route.** If the correct skill can be inferred from evidence, select it and state the assumption. Ask only for high-stakes ambiguity, conflicting goals, or missing context that would change the workflow.
+
+## Lifecycle Sequence
+
+For a complete feature, the typical skill sequence is:
+
+```
+1. idea-refine                 → Refine vague ideas
+2. spec-driven-development     → Define what we're building
+3. planning-and-task-breakdown → Break into verifiable chunks
+4. context-engineering         → Load the right context
+5. source-driven-development   → Verify against official docs
+6. incremental-implementation  → Build slice by slice
+7. test-driven-development     → Prove each slice works
+8. code-review-and-quality     → Review before merge
+9. git-workflow-and-versioning → Clean commit history
+10. documentation-and-adrs     → Document decisions
+11. shipping-and-launch        → Deploy safely
+```
+
+Not every task needs every skill. A bug fix might only need: `debugging-and-error-recovery` → `test-driven-development` → `code-review-and-quality`.
+
+## Quick Reference
+
+| Phase | Skill | One-Line Summary |
+|-------|-------|-----------------|
+| Define | idea-refine | Refine ideas through structured divergent and convergent thinking |
+| Define | spec-driven-development | Requirements and acceptance criteria before code |
+| Plan | planning-and-task-breakdown | Decompose into small, verifiable tasks |
+| Build | incremental-implementation | Thin vertical slices, test each before expanding |
+| Build | source-driven-development | Verify against official docs before implementing |
+| Build | context-engineering | Right context at the right time |
+| Build | frontend-ui-engineering | Production-quality UI with accessibility |
+| Build | api-and-interface-design | Stable interfaces with clear contracts |
+| Verify | test-driven-development | Failing test first, then make it pass |
+| Verify | browser-qa-testing | Real-browser runtime verification for user-facing flows |
+| Verify | debugging-and-error-recovery | Reproduce → localize → fix → guard |
+| Review | code-review-and-quality | Five-axis review with quality gates |
+| Review | security-and-hardening | OWASP prevention, input validation, least privilege |
+| Review | performance-optimization | Measure first, optimize only what matters |
+| Ship | git-workflow-and-versioning | Atomic commits, clean history |
+| Ship | ci-cd-and-automation | Automated quality gates on every change |
+| Ship | documentation-and-adrs | Document the why, not just the what |
+| Ship | shipping-and-launch | Pre-launch checklist, monitoring, rollback plan |

package/vendor/references/upstreams.yaml

@@ -1,94 +1,94 @@
-schema_version: 1
-
-governance:
-  manual_review_required: true
-  notes_root: references/notes
-  snapshots_root: references/snapshots
-  snapshot_policy: immutable
-
-upstreams:
-  - id: agent-skills
-    title: Agent Skills
-    kind: github-public-repo
-    status: active
-    owner: codex
-    source_url: https://github.com/addyosmani/agent-skills.git
-    source_paths:
-      - skills
-      - commands
-    notes_path: references/notes/agent-skills.md
-    snapshots_path: references/snapshots/agent-skills/
-    sync:
-      mode: manual-review
-      review_required: true
-      compare_against: snapshots
-      publish_target: toolkit-and-platform-generation
-  - id: superpowers
-    title: Superpowers
-    kind: github-public-repo
-    status: active
-    owner: codex
-    source_url: https://github.com/obra/superpowers.git
-    source_paths:
-      - prompts
-      - instructions
-      - agents
-    notes_path: references/notes/superpowers.md
-    snapshots_path: references/snapshots/superpowers/
-    sync:
-      mode: manual-review
-      review_required: true
-      compare_against: snapshots
-      publish_target: toolkit-and-platform-generation
-  - id: everything-claude-code
-    title: Everything Claude Code
-    kind: github-public-repo
-    status: active
-    owner: codex
-    source_url: https://github.com/affaan-m/everything-claude-code.git
-    source_paths:
-      - CLAUDE.md
-      - docs
-      - commands
-    notes_path: references/notes/everything-claude-code.md
-    snapshots_path: references/snapshots/everything-claude-code/
-    sync:
-      mode: manual-review
-      review_required: true
-      compare_against: snapshots
-      publish_target: toolkit-and-platform-generation
-  - id: gstack
-    title: GStack
-    kind: github-public-repo
-    status: active
-    owner: codex
-    source_url: https://github.com/garrytan/gstack.git
-    source_paths:
-      - prompts
-      - commands
-      - docs
-    notes_path: references/notes/gstack.md
-    snapshots_path: references/snapshots/gstack/
-    sync:
-      mode: manual-review
-      review_required: true
-      compare_against: snapshots
-      publish_target: toolkit-and-platform-generation
-  - id: andrej-karpathy-skills
-    title: Andrej Karpathy Skills
-    kind: github-public-repo
-    status: active
-    owner: codex
-    source_url: https://github.com/multica-ai/andrej-karpathy-skills.git
-    source_paths:
-      - CLAUDE.md
-      - README.md
-      - EXAMPLES.md
-      - skills/karpathy-guidelines
-    notes_path: references/notes/andrej-karpathy-skills.md
-    snapshots_path: references/snapshots/andrej-karpathy-skills/
-    sync:
-      mode: manual-review
-      review_required: true
-      compare_against: snapshots
-      publish_target: toolkit-and-platform-generation
+schema_version: 1
+
+governance:
+  manual_review_required: true
+  notes_root: references/notes
+  snapshots_root: references/snapshots
+  snapshot_policy: immutable
+
+upstreams:
+  - id: agent-skills
+    title: Agent Skills
+    kind: github-public-repo
+    status: active
+    owner: codex
+    source_url: https://github.com/addyosmani/agent-skills.git
+    source_paths:
+      - skills
+      - commands
+    notes_path: references/notes/agent-skills.md
+    snapshots_path: references/snapshots/agent-skills/
+    sync:
+      mode: manual-review
+      review_required: true
+      compare_against: snapshots
+      publish_target: toolkit-and-platform-generation
+  - id: superpowers
+    title: Superpowers
+    kind: github-public-repo
+    status: active
+    owner: codex
+    source_url: https://github.com/obra/superpowers.git
+    source_paths:
+      - prompts
+      - instructions
+      - agents
+    notes_path: references/notes/superpowers.md
+    snapshots_path: references/snapshots/superpowers/
+    sync:
+      mode: manual-review
+      review_required: true
+      compare_against: snapshots
+      publish_target: toolkit-and-platform-generation
+  - id: everything-claude-code
+    title: Everything Claude Code
+    kind: github-public-repo
+    status: active
+    owner: codex
+    source_url: https://github.com/affaan-m/everything-claude-code.git
+    source_paths:
+      - CLAUDE.md
+      - docs
+      - commands
+    notes_path: references/notes/everything-claude-code.md
+    snapshots_path: references/snapshots/everything-claude-code/
+    sync:
+      mode: manual-review
+      review_required: true
+      compare_against: snapshots
+      publish_target: toolkit-and-platform-generation
+  - id: gstack
+    title: GStack
+    kind: github-public-repo
+    status: active
+    owner: codex
+    source_url: https://github.com/garrytan/gstack.git
+    source_paths:
+      - prompts
+      - commands
+      - docs
+    notes_path: references/notes/gstack.md
+    snapshots_path: references/snapshots/gstack/
+    sync:
+      mode: manual-review
+      review_required: true
+      compare_against: snapshots
+      publish_target: toolkit-and-platform-generation
+  - id: andrej-karpathy-skills
+    title: Andrej Karpathy Skills
+    kind: github-public-repo
+    status: active
+    owner: codex
+    source_url: https://github.com/multica-ai/andrej-karpathy-skills.git
+    source_paths:
+      - CLAUDE.md
+      - README.md
+      - EXAMPLES.md
+      - skills/karpathy-guidelines
+    notes_path: references/notes/andrej-karpathy-skills.md
+    snapshots_path: references/snapshots/andrej-karpathy-skills/
+    sync:
+      mode: manual-review
+      review_required: true
+      compare_against: snapshots
+      publish_target: toolkit-and-platform-generation

package/dist/cli/setup.d.ts

@@ -1,3 +0,0 @@
-import type { Command } from "commander";
-export declare function registerSetupCommand(program: Command): void;
-//# sourceMappingURL=setup.d.ts.map

package/dist/cli/setup.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"setup.d.ts","sourceRoot":"","sources":["../../src/cli/setup.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAOzC,wBAAgB,oBAAoB,CAAC,OAAO,EAAE,OAAO,GAAG,IAAI,CA2C3D"}

package/dist/cli/setup.js

@@ -1,41 +0,0 @@
-import { discoverSkills, discoverCommands, discoverAgents, } from "../utils/skill-loader.js";
-export function registerSetupCommand(program) {
-    program
-        .command("setup")
-        .description("扫描并验证 toolkit 资产")
-        .option("-r, --root <dir>", "项目根目录")
-        .action(async (opts) => {
-        console.log("\n🔍 正在扫描项目资产...\n");
-        const [skills, commands, agents] = await Promise.all([
-            discoverSkills(opts.root),
-            discoverCommands(opts.root),
-            discoverAgents(opts.root),
-        ]);
-        // Skills
-        console.log(`📦 技能：${skills.length} 个`);
-        for (const s of skills) {
-            console.log(`   ✅ ${s.name}`);
-        }
-        // Commands
-        console.log(`\n📋 命令：${commands.length} 个`);
-        for (const c of commands) {
-            console.log(`   ✅ ${c.name}`);
-        }
-        // Agents
-        console.log(`\n🤖 代理：${agents.length} 个`);
-        for (const a of agents) {
-            console.log(`   ✅ ${a.name}`);
-        }
-        // Summary
-        const total = skills.length + commands.length + agents.length;
-        console.log(`\n📊 总计：${total} 个资产`);
-        if (total === 0) {
-            console.log("\n⚠️  未发现任何资产，请检查目录结构是否正确");
-            console.log("   期望结构：packages/toolkit/src/content/<kind>/<name>/{meta.yaml,body.md,assets/}");
-        }
-        else {
-            console.log("\n✅ 目录结构验证通过");
-        }
-    });
-}
-//# sourceMappingURL=setup.js.map

package/dist/cli/setup.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"setup.js","sourceRoot":"","sources":["../../src/cli/setup.ts"],"names":[],"mappings":"AACA,OAAO,EACL,cAAc,EACd,gBAAgB,EAChB,cAAc,GACf,MAAM,0BAA0B,CAAC;AAElC,MAAM,UAAU,oBAAoB,CAAC,OAAgB;IACnD,OAAO;SACJ,OAAO,CAAC,OAAO,CAAC;SAChB,WAAW,CAAC,kBAAkB,CAAC;SAC/B,MAAM,CAAC,kBAAkB,EAAE,OAAO,CAAC;SACnC,MAAM,CAAC,KAAK,EAAE,IAAuB,EAAE,EAAE;QACxC,OAAO,CAAC,GAAG,CAAC,oBAAoB,CAAC,CAAC;QAElC,MAAM,CAAC,MAAM,EAAE,QAAQ,EAAE,MAAM,CAAC,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC;YACnD,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC;YACzB,gBAAgB,CAAC,IAAI,CAAC,IAAI,CAAC;YAC3B,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC;SAC1B,CAAC,CAAC;QAEH,SAAS;QACT,OAAO,CAAC,GAAG,CAAC,SAAS,MAAM,CAAC,MAAM,IAAI,CAAC,CAAC;QACxC,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;YACvB,OAAO,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QAChC,CAAC;QAED,WAAW;QACX,OAAO,CAAC,GAAG,CAAC,WAAW,QAAQ,CAAC,MAAM,IAAI,CAAC,CAAC;QAC5C,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;YACzB,OAAO,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QAChC,CAAC;QAED,SAAS;QACT,OAAO,CAAC,GAAG,CAAC,WAAW,MAAM,CAAC,MAAM,IAAI,CAAC,CAAC;QAC1C,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;YACvB,OAAO,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC;QAChC,CAAC;QAED,UAAU;QACV,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,GAAG,QAAQ,CAAC,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC;QAC9D,OAAO,CAAC,GAAG,CAAC,WAAW,KAAK,MAAM,CAAC,CAAC;QAEpC,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;YAChB,OAAO,CAAC,GAAG,CAAC,2BAA2B,CAAC,CAAC;YACzC,OAAO,CAAC,GAAG,CAAC,gFAAgF,CAAC,CAAC;QAChG,CAAC;aAAM,CAAC;YACN,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,CAAC;QAC9B,CAAC;IACH,CAAC,CAAC,CAAC;AACP,CAAC"}

package/dist/utils/codex-config-merge.d.ts

@@ -1,3 +0,0 @@
-export declare function isCodexAgentConfigContent(content: string): boolean;
-export declare function mergeCodexAgentConfig(existingContent: string | undefined, generatedContent: string): string;
-//# sourceMappingURL=codex-config-merge.d.ts.map

package/dist/utils/codex-config-merge.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"codex-config-merge.d.ts","sourceRoot":"","sources":["../../src/utils/codex-config-merge.ts"],"names":[],"mappings":"AAoCA,wBAAgB,yBAAyB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAElE;AAED,wBAAgB,qBAAqB,CAAC,eAAe,EAAE,MAAM,GAAG,SAAS,EAAE,gBAAgB,EAAE,MAAM,GAAG,MAAM,CAa3G"}