← all publishers

wenjunduan

@wenjunduan source repo

Report this profile Claim this profile

• 749 skills
• 0 followers
• last month last updated

1. ▌
   Experience 4 · wenjunduan

   Experience Skill
   5 installs
2. ▌
   Experience 5 · wenjunduan

   Experience management for pattern retrieval and deposit. Searches past solutions before development, deposits new patterns after completion. Works with continuous-learning skill for auto-extraction.
   5 installs
3. ▌
   Context7 30 · wenjunduan

   Intelligent library documentation fetcher using Context7 MCP tools. Auto-activates when: writing code with external libraries, needing API docs, setting up frameworks, or requesting code examples with specific packages. Fetches up-to-date, version-specific documentation to prevent hallucinated APIs.
   4 installs
4. ▌
   Cunzhi 19 · wenjunduan

   寸止协议 - Pause and wait mechanism using cunzhi MCP for human confirmation at critical decision points. Prevents AI from proceeding autonomously past important checkpoints.
   5 installs
5. ▌
   Context7 31 · wenjunduan

   Library documentation fetcher using Context7 CLI (npx ctx7). Provides up-to-date, version-specific docs for external libraries. CLI version replaces Context7 MCP for lower context overhead.
   7 installs
6. ▌
   Code Quality 13 · wenjunduan

   Rev 阶段 Plugin 编排顺序 + Linus 四问 + 经验沉淀
   8 installs
7. ▌
   Verification 21 · wenjunduan

   V 阶段分级清单 — Path 决定验证严格度和失败升级链
   6 installs
8. ▌
   Multi AI Sync 2 · wenjunduan

   多 AI 协调同步协议 - 解决 Claude/Codex/Gemini 如何协同工作
   5 installs
9. ▌
   Code Quality 14 · wenjunduan

   代码质量 (Code Quality)
   5 installs
10. ▌
    Phase Router 4 · wenjunduan

    Phase Router Skill
    5 installs
11. ▌
    Code Quality 15 · wenjunduan

    Code quality assurance with Linus-style review principles. Enforces simplicity, good naming, proper error handling, and "good taste". Integrates with verification-loop for automated checks.
    7 installs
12. ▌
    Phase Router 5 · wenjunduan

    Intent recognition and workflow routing. Analyzes user input to determine task type and routes to appropriate agent. Core decision layer.
    5 installs
13. ▌
    Context7 32 · wenjunduan

    Library documentation fetcher using Context7 CLI. Provides up-to-date, version-specific documentation for external libraries and frameworks. Uses `npx ctx7` CLI instead of MCP for lower context overhead.
    7 installs
14. ▌
    Experience 6 · wenjunduan

    Experience management. Stores learned patterns, mistakes, and best practices from past development sessions.
    5 installs
15. ▌
    Agent Teams 18 · wenjunduan

    Agent Teams orchestration for Claude Code. Coordinates multiple Claude instances working in parallel on shared codebase. Requires experimental flag CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. New in v8.0, replaces multi-ai skill for Claude Code platform.
    6 installs
16. ▌
    Knowledge Bridge 3 · wenjunduan

    知识桥接，公司规范索引，反模式库
    7 installs
17. ▌
    Knowledge Base 4 · wenjunduan

    Knowledge Base Skill
    6 installs
18. ▌
    Knowledge Base 5 · wenjunduan

    External knowledge base reader. Loads project docs, dev standards, company requirements from .knowledge/ directory. Auto-invoked during requirement analysis, design, and code review phases.
    6 installs
19. ▌
    Code Quality 16 · wenjunduan

    Linus-style code quality enforcement. Checks taste, simplicity, and engineering rigor.
    7 installs
20. ▌
    Eval Harness 3 · wenjunduan

    Evaluation framework for measuring code agent effectiveness. v8.0: Added Agent Teams collaboration quality metrics.
    5 installs
21. ▌
    Model Router 2 · wenjunduan

    Intelligent task-to-model routing based on benchmark data. Routes tasks to Claude Code or Codex CLI based on task type and model strengths. New in v8.0.
    5 installs
22. ▌
    Phase Router 6 · wenjunduan

    P.A.C.E. v2.0 complexity routing engine. Analyzes task complexity and routes to optimal path (A/B/C/D) with effort level mapping. v8.0: Added Path D for Agent Teams, effort parameter integration.
    5 installs
23. ▌
    Knowledge 12 · wenjunduan

    Knowledge
    5 installs
24. ▌
    Smart Archive 6 · wenjunduan

    Intelligent context archiving for the 1M token era. Replaces strategic-compact. Works with server-side Compaction API. Archives completed RIPER phases to .ai_state/ instead of emergency compression.
    5 installs
25. ▌
    Service Analysis 4 · wenjunduan

    Service Analysis Skill
    5 installs
26. ▌
    Service Analysis 5 · wenjunduan

    Service understanding and analysis. Provides service overview, business analysis, architecture analysis, and operations analysis. Use when onboarding to a codebase or understanding service boundaries.
    6 installs
27. ▌
    Eval Harness 4 · wenjunduan

    Verification loop evaluation framework. Provides graders, metrics, and pass@k evaluation for code quality assurance. Integrates with verification-loop for systematic quality gates.
    6 installs
28. ▌
    Knowledge Base 6 · wenjunduan

    Project knowledge management. Stores and retrieves project-specific documentation, standards, and technical references.
    4 installs
29. ▌
    Strategic Compact 2 · wenjunduan

    Intelligent context window management with strategic compaction suggestions. Monitors context usage and suggests /compact at logical boundaries. Saves state before compaction to enable recovery.
    5 installs
30. ▌
    Verification Loop 3 · wenjunduan

    Checkpoint-based verification for code quality assurance. Use for: running verification loops, saving checkpoints, evaluating implementations against acceptance criteria. Commands: /verify, /checkpoint.
    5 installs
31. ▌
    Lessons Loop 2 · wenjunduan

    自我改进循环 — 用户纠正后触发, 写入 knowledge.md 教训段
    7 installs
32. ▌
    Service Analysis 6 · wenjunduan

    Service boundary analysis. Identifies service boundaries, dependencies, and integration points in the codebase.
    6 installs
33. ▌
    Continuous Learning 3 · wenjunduan

    Auto-extract reusable patterns from coding sessions. Activates on session end or when /learn command is invoked. Identifies successful patterns, debugging solutions, and architectural decisions worth preserving for future sessions.
    4 installs
34. ▌
    Verification Loop 4 · wenjunduan

    Verify-fix-retry loop with cross-model validation support. v8.0: Added --cross mode for dual-model verification.
    4 installs
35. ▌
    Continuous Learning 4 · wenjunduan

    v1 basic learning. Extracts patterns from sessions and stores them in the experience skill.
    6 installs
36. ▌
    Iterative Retrieval 3 · wenjunduan

    Large context iterative retrieval. For tasks requiring information from many files, retrieves in batches to avoid overwhelming the context window.
    6 installs
37. ▌
    Iterative Retrieval 4 · wenjunduan

    Progressive context refinement for subagents and complex tasks. Retrieves context incrementally based on actual needs rather than loading everything upfront. Reduces context waste and improves relevance.
    5 installs
38. ▌
    Continuous Learning V2 3 · wenjunduan

    v2 Instinct-based learning system. Builds confidence through repeated observations and evolves high-confidence patterns into skills.
    6 installs
39. ▌
    Continuous Learning V2 4 · wenjunduan

    Instinct-based learning system with confidence scoring. Automatically learns patterns from sessions and evolves them into skills. Supports import/export for team sharing.
    5 installs
40. ▌
    Polish 16 · wenjunduan

    PACE polish stage. Refactor/System 路径强制. 5 检查项 + worktree 清理 + 触发 architecture 更新. v9.6.4 升级: 加 finishing-a-development-branch 流程 (借 Superpowers), 加 compound/ 触发.
    7 installs
41. ▌
    Polish 17 · wenjunduan bundle

    PACE polish stage，Refactor/System 强制。review PASS 后做清理并触发 architecture 更新时触发。
    6 installs
42. ▌
    Roadmap 9 · wenjunduan

    PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.
    8 installs
43. ▌
    Augment Context Engine 3 · wenjunduan

    augment-context-engine MCP 工具的调度说明. PACE plan / design 阶段做项目代码语义检索, 找"是否已经实现过"或"相关代码在哪里". 避免重复造轮子.
    5 installs
44. ▌
    Roadmap 10 · wenjunduan

    PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.
    6 installs
45. ▌
    Polish 18 · wenjunduan

    PACE polish stage. Refactor/System 路径强制. 5 检查项 + worktree 清理 + 触发 architecture 更新. 含 finishing-a-development-branch 流程 (借 Superpowers) + compound/ 触发.
    7 installs
46. ▌
    Polish 19 · wenjunduan bundle

    PACE polish stage，Refactor/System 强制。review PASS 后做清理并触发 architecture 更新时触发。
    6 installs
47. ▌
    Polish 20 · wenjunduan bundle

    PACE Refactor/System polish；runtime-verify 完成后、最终 review 前清理代码并更新架构。
    5 installs
48. ▌
    Compound 13 · wenjunduan bundle

    Compound Learning Loop. 跨 sprint 积累的经验沉淀到 compound/, 按 doc_type 分文件存档. 4 种 doc_type: learning / trick / decision / explore. v9.6.4 重写 (替代 v9.6.2 单文件 lessons.md). 铁律 13: 一事一档, ≤100 行.
    5 installs
49. ▌
    Compound 14 · wenjunduan bundle

    Compound Learning Loop. 跨 sprint 积累的经验沉淀到 compound/, 按 doc_type 分文件存档. 4 种 doc_type: learning / trick / decision / explore. v9.6.4 重写 (替代 v9.6.2 单文件 lessons.md). 铁律 13: 一事一档, ≤100 行.
    6 installs
50. ▌
    Context7 22 · wenjunduan

    调用 context7 (npx ctx7) 库文档解析工具. PACE plan / design / impl stage 在需要查第三方库 API / 用法 / 最佳实践时使用. 避免凭记忆瞎写库 API.
    4 installs
51. ▌
    Augment Context Engine 4 · wenjunduan

    augment-context-engine MCP 工具的调度说明. PACE plan / design 阶段做项目代码语义检索, 找"是否已经实现过"或"相关代码在哪里". 避免重复造轮子.
    5 installs
52. ▌
    Roadmap 11 · wenjunduan

    PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.
    3 installs
53. ▌
    Roadmap 12 · wenjunduan

    PACE 可选 stage. 大需求 (跨 ≥3 模块) 拆成子 feature 序列. 产出 .ai_state/roadmap/{slug}/items.yaml + roadmap.md. 每个子 item 完成后回写 status, 主 agent 自动进入下一个 item 的 plan stage.
    4 installs
54. ▌
    Roadmap 13 · wenjunduan bundle

    PACE 可选 stage。需求跨 3 个以上模块、需要拆成子 feature 序列时触发。
    5 installs
55. ▌
    Roadmap 14 · wenjunduan bundle

    PACE 可选 stage。至少两个可独立验收交付切片或用户明确要求拆分时触发。
    7 installs
56. ▌
    Athena Vm 13 · wenjunduan bundle

    把用户虚拟机注册为 runtime-verify 的真实环境。需要 VM 环境或跑 setup / doctor 时触发。
    5 installs
57. ▌
    Compound 15 · wenjunduan

    Compound Learning Loop. 跨 sprint 积累的经验、模式、约束沉淀到 lessons.md, 后续 sprint 自动加载.
    6 installs
58. ▌
    Context7 23 · wenjunduan

    调用 context7 (npx ctx7) 库文档解析工具. PACE plan / design / impl stage 在需要查第三方库 API / 用法 / 最佳实践时使用. 避免凭记忆瞎写库 API.
    6 installs
59. ▌
    Compound 16 · wenjunduan bundle

    Compound Learning Loop. 跨 sprint 积累的经验沉淀到 compound/, 按 doc_type 分文件存档. 4 种 doc_type: learning / trick / decision / explore. 铁律[复利]: 一事一档, ≤100 行.
    7 installs
60. ▌
    Compound 17 · wenjunduan bundle

    Compound Learning Loop. 跨 sprint 积累的经验沉淀到 compound/, 按 doc_type 分文件存档. 4 种 doc_type: learning / trick / decision / explore. 铁律[复利]: 一事一档, ≤100 行.
    6 installs
61. ▌
    Context7 24 · wenjunduan

    调用 context7 (npx ctx7) 库文档解析工具. PACE plan / design / impl stage 在需要查第三方库 API / 用法 / 最佳实践时使用. 避免凭记忆瞎写库 API.
    9 installs
62. ▌
    Compound 18 · wenjunduan bundle

    跨 sprint 经验沉淀到 compound/。learning / trick / decision / explore 时触发。
    6 installs
63. ▌
    Brainstorm 27 · wenjunduan

    PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.
    5 installs
64. ▌
    Playwright 3 · wenjunduan bundle

    Playwright browser/E2E testing workflow for runtime verification. Use when Codex needs to add, run, debug, or document frontend/browser tests, smoke-test a dev server, verify UI flows during athena-runtime-verify, capture traces/screenshots, or turn manual browser checks into repeatable tests.
    7 installs
65. ▌
    Brainstorm 28 · wenjunduan

    PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.
    7 installs
66. ▌
    Athena Dev 18 · wenjunduan bundle

    Athena 主入口。收到新任务需要 PACE 路由分诊时触发。
    5 installs
67. ▌
    Athena Vm 14 · wenjunduan bundle

    把用户虚拟机注册为 runtime-verify 的真实环境。需要 VM 环境或跑 setup / doctor 时触发。
    5 installs
68. ▌
    Antigravity 6 · wenjunduan

    通过 `agy -p "..."` 命令调度 Google Antigravity CLI (subagent / 并行任务). Athena 在 CX 端可用此 skill 把"重的、可并行的、不需要 CC 自己跑"的任务外包给 Antigravity. Antigravity 由用户的 Google 账号驱动, 默认使用 Gemini 3.5 Flash, 适合大批量、可独立切片的任务. 注: 用户不直接用 Antigravity, 调度由 Athena 负责.
    8 installs
69. ▌
    Antigravity 7 · wenjunduan

    通过 `agy -p "..."` 命令调度 Google Antigravity CLI (subagent / 并行任务). Athena 在 CX 端可用此 skill 把"重的、可并行的、不需要 CC 自己跑"的任务外包给 Antigravity. Antigravity 由用户的 Google 账号驱动, 默认使用 Gemini 3.5 Flash, 适合大批量、可独立切片的任务. 注: 用户不直接用 Antigravity, 调度由 Athena 负责.
    5 installs
70. ▌
    Athena Init 18 · wenjunduan bundle

    Athena 项目初始化：探测平台与工具、建 .ai_state/、填 _index 模板。用户显式调用时触发。
    5 installs
71. ▌
    Deps Check 3 · wenjunduan

    检查项目依赖 (库 / 包 / jar) 是否有可升级版本, 适配多生态: Maven / npm·pnpm·yarn·bun / PyPI / Cargo / Go / RubyGems / Composer / NuGet. 铁律: 版本号必须从官方 registry 在线查询, 不靠记忆/编造, 且区分 "声明的版本是否存在" 与 "是否最新". 用户要求"看有没有要更新的依赖"时使用.
    5 installs
72. ▌
    Brainstorm 29 · wenjunduan

    PACE 可选最早 stage. 用户想法模糊时通过对话理清楚. AI 角色: 思考伙伴, 挖用户真正想解决的问题, 必要时提出更好的替代方案. 完成后产出 sprints/{date}-{slug}/brainstorm.md 并路由到 plan / roadmap / direct design.
    6 installs
73. ▌
    Playwright 4 · wenjunduan bundle

    Playwright browser/E2E testing workflow for runtime verification. Use when Claude needs to add, run, debug, or document frontend/browser tests, smoke-test a dev server, verify UI flows during athena-runtime-verify, capture traces/screenshots, or turn manual browser checks into repeatable tests.
    7 installs
74. ▌
    Brainstorm 30 · wenjunduan bundle

    PACE 最早的可选 stage。想法模糊、写不出验收标准时触发。一次一问 + 推荐答 + 先查库再问人。
    5 installs
75. ▌
    Deps Check 4 · wenjunduan bundle

    在线查依赖可升级版本 (Maven / npm / PyPI / Cargo / Go / RubyGems / Composer / NuGet)。用户问有无依赖要更新时触发。
    5 installs
76. ▌
    Athena Dev 19 · wenjunduan bundle

    Athena 主入口。收到新任务需要 PACE 路由分诊时触发。
    5 installs
77. ▌
    Athena Dev 20 · wenjunduan bundle

    Athena 自然语言任务入口。一句话/一段话的检查、诊断、修复、修改、构建自动分诊；已有 sprint 先区分续做与新任务，无需用户报级别。
    5 installs
78. ▌
    Brainstorm 31 · wenjunduan bundle

    PACE 最早的可选 stage。想法模糊、写不出验收标准时触发。一次一问 + 推荐答 + 先查库再问人。
    6 installs
79. ▌
    Athena Issue 6 · wenjunduan

    Bugfix 路径的结构化问题流程: report → analyze → fix-note 三件套档案, 落在 sprints/{slug}/, Codex. 把"偏轻"的 Bugfix 升级成可复现 / 可追溯 / 可复盘. 借 CodeStable issue 实体, 适配 agent-in-loop.
    6 installs
80. ▌
    Athena Issue 7 · wenjunduan

    Bugfix 路径的结构化问题流程: report → analyze → fix-note 三件套档案, 落在 sprints/{slug}/, Codex. 把"偏轻"的 Bugfix 升级成可复现 / 可追溯 / 可复盘. 借 CodeStable issue 实体, 适配 agent-in-loop.
    5 installs
81. ▌
    Athena Issue 8 · wenjunduan

    Bugfix 路径的 report→analyze→fix-note 三件套档案。走 Bugfix 路径时触发。
    8 installs
82. ▌
    Vibe Review 3 · wenjunduan

    单独运行质量审查，不走完整开发流程。
    6 installs
83. ▌
    Antigravity 8 · wenjunduan

    通过 `agy -p "..."` 命令调度 Google Antigravity CLI (subagent / 并行任务). Athena 在 CC 端可用此 skill 把"重的、可并行的、不需要 CC 自己跑"的任务外包给 Antigravity. Antigravity 由用户的 Google 账号驱动, 默认使用 Gemini 3.5 Flash, 适合大批量、可独立切片的任务. 注: 用户不直接用 Antigravity, 调度由 Athena 负责.
    6 installs
84. ▌
    Athena Init 19 · wenjunduan

    Athena 项目初始化 skill. 在项目中执行 /athena-init 时调用. 职责: 探测平台 / 工具可用性, 创建 .ai_state/ 目录 + 复制 _index.md 模板 + 填入探测结果.
    5 installs
85. ▌
    Antigravity 9 · wenjunduan

    通过 `agy -p "..."` 命令调度 Google Antigravity CLI (subagent / 并行任务). Athena 在 CC 端可用此 skill 把"重的、可并行的、不需要 CC 自己跑"的任务外包给 Antigravity. Antigravity 由用户的 Google 账号驱动, 默认使用 Gemini 3.5 Flash, 适合大批量、可独立切片的任务. 注: 用户不直接用 Antigravity, 调度由 Athena 负责.
    6 installs
86. ▌
    Antigravity 10 · wenjunduan bundle

    把可并行的重任务外包给 Google Antigravity CLI (agy -p)。用户要求并行跑或批量外包时触发。
    5 installs
87. ▌
    Athena Init 20 · wenjunduan bundle

    Athena 项目初始化：探测平台与工具、建 .ai_state/、填 _index 模板。用户显式调用时触发。
    5 installs
88. ▌
    Athena Init 21 · wenjunduan bundle

    初始化 Athena 项目状态并按用户选择探测当前端 CLI，保留既有 .ai_state。
    5 installs
89. ▌
    Architect Doc 7 · wenjunduan

    维护 .ai_state/architecture/ 长效档案 (项目现状档). Refactor/System 路径完成后强制更新 ARCHITECTURE.md 总入口 + {type}-{slug}.md 子系统档. 注: 不同于 cx 端的 architect.toml subagent (后者是 design stage 工作者).
    5 installs
90. ▌
    Athena Review 18 · wenjunduan

    PACE review stage 执行 skill (Codex). 6 维度 (并行 spawn 3 subagent: reviewer + spec-compliance + evaluator). v9.7.0: 由 deprecated prompts/ 迁为 skill; 清除 Stop hook prompt 类型残留引用 (该类型已删, 门禁统一由 delivery-gate 在 ship stage 执行).
    5 installs
91. ▌
    Athena Status 8 · wenjunduan

    快速查看当前项目的 Athena 状态: stage / path / sprint / 进度 / 活动 worktree. 无副作用, 只读. v9.7.0: 由 deprecated prompts/ 迁为 skill.
    7 installs
92. ▌
    Architect Doc 8 · wenjunduan

    维护 .ai_state/architecture/ 长效档案 (项目现状档). Refactor/System 路径完成后强制更新 ARCHITECTURE.md 总入口 + {type}-{slug}.md 子系统档. 注: 不同于 cx 端的 architect.toml subagent (后者是 design stage 工作者).
    7 installs
93. ▌
    Athena Setup 12 · wenjunduan

    Athena 全局首次配置 (跨项目, 一次性). 部署 rules / hooks / agents / skills 到 ~/.claude/ (CC) 或 ~/.codex/ (CX) 或 ~/.agents/skills/_athena/ (CX 端 skills). 和 athena-init 区别: setup 是全局一次性, init 是每项目一次.
    6 installs
94. ▌
    Athena Setup 13 · wenjunduan

    Athena 全局首次配置 (跨项目, 一次性). 从分发包部署 settings/config/rules/standards/hooks/agents/skills 到 ~/.claude/ (CC) 与 ~/.codex/ (CX). 和 athena-init 区别: setup 全局一次性, init 每项目一次. 已装则转 verify/upgrade (走 athena-migrate).
    6 installs
95. ▌
    Athena Issue 9 · wenjunduan

    Bugfix 路径的结构化问题流程: report → analyze → fix-note 三件套档案, 落在 sprints/{slug}/. 把"偏轻"的 Bugfix 升级成可复现 / 可追溯 / 可复盘. 借 CodeStable issue 实体, 适配 agent-in-loop.
    5 installs
96. ▌
    Athena Setup 14 · wenjunduan

    Athena 全局首次配置 (跨项目, 一次性). 从分发包部署 settings/config/rules/standards/hooks/agents/skills 到 ~/.claude/ (CC) 与 ~/.codex/ (CX). 和 athena-init 区别: setup 全局一次性, init 每项目一次. 已装则转 verify/upgrade (走 athena-migrate).
    6 installs
97. ▌
    Athena Setup 15 · wenjunduan bundle

    Fresh-install Athena v9.9.1 globally, install a missing Claude Code or Codex endpoint, or verify an existing v9.9.1 installation. Use for first-time global setup; route older installations to athena-migrate instead of overwriting them.
    7 installs
98. ▌
    Athena Setup 16 · wenjunduan bundle

    Fresh-install Athena v9.9.2 globally, install a missing Claude Code or Codex endpoint, or verify an existing v9.9.2 installation. Use for first-time global setup; route older installations to athena-migrate instead of overwriting them.
    5 installs
99. ▌
    Quantum Data 2 · wenjunduan bundle

    Use when you need to read live data or business-process state from a running project — users, departments, dictionaries, workflow/approval status, reports — through that project's MCP capability server. Connects over standard MCP (Streamable HTTP/SSE or stdio), pulls the Capability Manifest, and calls read-only tools. The caller's identity (JWT) is passed through and the target system enforces authentication, role/permission and row-level data-permission on every call. This is a runtime read skill — it does NOT generate or modify source code (use quantum-codegen (mode=module) for that).
    5 installs
100. ▌
     Athena Setup 17 · wenjunduan bundle

     Fresh-install Athena v9.9.3 globally, install a missing Claude Code or Codex endpoint, or verify an existing v9.9.3 installation. Use for first-time global setup; route older installations to athena-migrate instead of overwriting them.
     5 installs