Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Doc Architecture · hashgraph-online | DecimalAI

documentationby hashgraph-online

Doc Architecture

hashgraph-online/doc-architecture

Source hashgraph-online/awesome-codex-plugins ↗License Apache-2.0

将需求发现、领域建模、一致性审计整合到 /team-* 主链，以 artifacts/adr/memory 为唯一落盘目标产出可审计文档。当 Tech Lead、Architect、QA 需要补齐或演进架构文档时使用。

SkillScore95Maintained

Automatic

Doc Ops pack

Last verified 8/15/2026

What it changes

Passed 21 of 22 test cases with the skill, and 3 of 22 without it.

Without skill14%

With skill95%

Checks it passed that the model alone missed

Belongs to Step 2 Modeling.
Stored in docs/memory/lessons-learned.md.
Stored in docs/memory/project-context.md.

and 20 more in the full report

18 fixed3 passed either way1 still failing0 broke

Pass-rate lift: +82 pp
Tokens: +10%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 8/15/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/hashgraph-online-doc-architecture/SKILL.md https://app.decimal.ai/s/hashgraph-online-doc-architecture/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add hashgraph-online-doc-architecture, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/hashgraph-online-doc-architecture/ and pins it in .decimal/skills.lock

decimalai skills add hashgraph-online-doc-architecture

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/hashgraph-online-doc-architecture/SKILL.md https://app.decimal.ai/s/hashgraph-online-doc-architecture/SKILL.md

Raw file: /s/hashgraph-online-doc-architecture/SKILL.md ↗ · machine-readable summary at /s/hashgraph-online-doc-architecture.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 18

Prompt

架构师与 QA 团队使用一致性 Checklist 对服务名称、鉴权逻辑及接口覆盖率进行全面审查后，最终审查结论落盘文件是哪个？

What was checked, without and with the skill
Checked	Without skill	With skill
Consistency audit findings are output into test-plan.md within the artifact directory.	Missed	Passed

case-10 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md85 lines7 files

Doc Architecture

用途

将文档能力拆入现有 team-skills 主链，不新增并行文档体系。
统一 Discovery、Service Decomposition、NFR、Audit 的输入输出结构。
保证文档可追溯落盘到 docs/artifacts/、docs/adr/ 与 docs/memory/。

完整工作流

Step 1: Discovery

使用 discovery-questionnaire.md 收集项目背景、技术栈、架构风格与约束。
若是既有项目（brownfield），先补做现状扫描：盘点现有模块、入口、外部依赖、关键数据流和历史包袱；必要时借助 /update-codemaps 生成 token-lean 结构快照。
形成 Project Profile Card。
按 tech-stack-profiles.md 锁定文档术语风格。

输出回落：prd.md、delivery-plan.md

Step 2: Modeling

使用 service-decomposition-guide.md 识别领域与服务边界。
产出 Service Catalog 与 Communication Matrix。
收集 NFR（可用性、性能、安全、可观测性）。

输出回落：arch-design.md、api-contract.md

Step 3: Generation Mapping

按 artifact-mapping.md 将文档输出映射到 artifacts。
参考 references/templates/ 选择章节结构。
若属于 brownfield 任务，把现状扫描结果回落为 brownfield context snapshot，写入 delivery-plan.md / arch-design.md，不要新建平行事实源。
对缺失信息使用  标记，不虚构业务事实。

输出回落：delivery-plan.md、arch-design.md、api-contract.md

Step 4: Execute Backfill

在执行阶段记录实现偏差、接口漂移、事件变更。
关键取舍进入 ADR，轻量决策进入 decisions。

Track record

Benchmark

21 / 22

test cases passed, vs 3 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

hashgraph-online / awesome-codex-plugins

plugins/Colin4k1024/tsp/skills/doc-architecture/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 6 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Doc Architecture

用途

完整工作流

Step 1: Discovery

Step 2: Modeling

Step 3: Generation Mapping

Step 4: Execute Backfill

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills