AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Task Bundle

skill-jerrylalala-compound-engineering-task-bundle · by Jerrylalala

管理 Task Bundle 工件结构（docs/tasks/），提供创建、查询、状态更新的规范

↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-jerrylalala-compound-engineering-task-bundle

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jerrylalala-compound-engineering-task-bundle)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Task Bundle? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Task Bundle 管理

什么是 Task Bundle

Task Bundle 是任务的统一工件结构。每个任务由三个文件组成：

| 文件 | 职责 | 写入时机 | |------|------|----------| | plan.md | 目标、约束、验收标准 | 任务创建时 | | state.md | 当前步骤、阻塞点、状态机历史 | 执行过程中持续更新 | | review.md | findings、证据、结论 | 审查阶段 |

创建新 Task Bundle

  1. 生成 task-id：YYYY-MM-DD--
  2. 创建目录 docs/tasks//
  3. 从模板复制三个文件，替换占位符
  4. 更新 frontmatter 中的 taskid、createdat、owner

状态转换规则

参见 Failure FSM 协议（docs/specs/failure-fsm.md）。

每次状态转换必须：

  1. 更新 state.md 的 status frontmatter 字段
  2. 在状态历史表追加一行（时间、从、到、原因、操作者）
  3. 更新 last_checkpoint 时间戳

与现有工作流的关系

> Phase 0 说明：当前 Task Bundle 是独立的文档协议，自身不含自动集成机制。 > 如需在 ce:work 执行时自动读写 state.md，需配合加载 ce-work-integration overlay（见 skills-custom/ce-work-integration/SKILL.md）。 > Phase 2 将在上游合并后，将 Task Bundle 读写集成到 ce-work/ce-review 中。

手动使用方式：

  • /workflows:plan 输出后，手动创建 Task Bundle 并链接 plan 文件
  • /workflows:work 执行中，手动更新 state.md
  • /workflows:review 完成后，手动填写 review.md

模板位置

skills-custom/task-bundle/templates/
├── plan.md.tpl
├── state.md.tpl
└── review.md.tpl

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills