Install
$ agentstack add skill-blueprintos-analysis-to-delivery-setup-analysis-delivery ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Setup Analysis-Delivery — 项目配置初始化
Contract
- 输入: 项目根目录,已检测到的项目文件,可选的既有项目配置
- 输出:
paths/knowledge-path.md、paths/compliance-path.md、paths/tech-stack-path.md、paths/doc-naming-path.md;可选decisions.mdADR - 门控: 4 个
paths/*.md文件存在且非空(legacy 项目根*-path.md可接受但产生 warning);knowledge-path.md至少含 1 个真实路径后才进入下游字段工作 - Required rules:
context-pointer - Required paths:
knowledge-path,compliance-path,tech-stack-path,doc-naming-path - 下一步:
/grill-task
适用场景
- 拿到一个新项目,需要接 analysis-to-delivery 工作流
- 给现有项目补这套工作流的配置
流程步骤
1. 检测项目根
- 必须在 git 仓库根执行(
git rev-parse --show-toplevel) - 项目根不存在
.git→ 提示用户先git init
2. 检测项目类型
读项目根文件,推断技术栈:
pom.xml/build.gradle→ Java/Maven/Gradlepackage.json→ Node/前端pyproject.toml/requirements.txt→ Pythongo.mod→ Go
3. 生成 4 个项目级配置(canonical)
默认:在项目根的 paths/ 目录下生成 4 个空模板(用户填写后提交到 git)。 这 4 个文件是唯一项目级配置加载输入:
| Canonical 文件 | 作用 | 模板来源 | |---|---|---| | paths/knowledge-path.md | 列项目涉及的外部知识库(领域表结构、合规法规等)路径 | paths/knowledge-path.md | | paths/compliance-path.md | 列项目适用的合规规则文件路径 + 启用开关 | paths/compliance-path.md | | paths/tech-stack-path.md | 列后端/前端/数据库/中间件 + 团队规范路径 | paths/tech-stack-path.md | | paths/doc-naming-path.md | 文档编号、命名前缀、存放目录 | paths/doc-naming-path.md |
Legacy 兼容:既有 v1.1 项目可能用项目根 *.md(knowledge-path.md 等)。setup-check.py 会把它们识别为 warning 并继续通过。生成时加 --legacy 切换到兼容输出位置(仅 v1.1 旧项目)。
4. 可选记录配置使用 ADR
config-used.md不是配置文件,不参与配置加载,不属于 4 个项目级配置- 如需记录"本项目用了哪些配置、为什么这么选",从
templates/CONFIG_USED.md复制生成 config-used.md应作为阶段 1 交付产物提交,用于审计和交接
5. 验证
- 4 个文件存在且非空(允许只有注释)
- 跑
python3 scripts/setup-check.py --strict确认通过(legacy 项目根文件会产生 warning 但仍通过) - 跑
python3 scripts/field-alignment-check.py --help确认脚本可用
调用的 rule
rules/context-pointer— 三层配置加载规则
结束条件
- [ ] 4 个
paths/*.md全部生成在项目根(或兼容的 legacy 项目根*.md) - [ ] 用户已填写真实内容(
paths/knowledge-path.md必须至少 1 个真实路径) - [ ] 如生成
config-used.md,已明确标注为配置使用记录 / ADR,而非配置输入 - [ ]
setup-check.py --strict通过(warning 可接受) - [ ] 已提交到 git(可选,但建议)
反模式
- ❌ 4 个 paths/*.md 留 TBD / placeholder — 必须填真实路径,
setup-check.py --strict必过 - ❌ knowledge-path 写"待补充" — 必须至少 1 个真实可访问路径,否则字段对齐时无据可查
- ❌ compliance-path 不标
mode— 必须mode=gsp/mode=hipaa/mode=none选一 - ❌ tech-stack-path 不标 Target_DB — 必须标
oracle/postgresql/mysql/firestore等,否则 SQL 方言检查失据 - ❌
config-used.md写成配置文件 — 实际是 ADR / 配置使用记录,不参与加载,严禁误用 - ❌ 把项目级
paths/*.md复制到 skill 内 — skill 级是 fallback,项目级才是真实配置,优先级不同 - ❌ 混用 legacy 项目根 + canonical paths/ — 选一种;legacy 项目可逐步迁移到 paths/ 并删除根目录旧文件
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: BlueprintOS
- Source: BlueprintOS/analysis-to-delivery
- License: MIT
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.