software-architecture-document-type
中文优先指导汽车控制器产品 Software Architecture(SwAD,软件架构)文档写作;保留 ASPICE SWE.2、ISO 26262-6 软件层接口、SwRS 追溯、组件分配、接口边界、tier、HITL 与 candidate-update 约束。
Skill by Exquisite0828
Chalk Labs
Need help deploying software-architecture-document-type?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/exquisite0828-software-architecture-document-type
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/software-architecture-document-type
What's inside
- Skill name
software-architecture-document-type- Description
- 中文优先指导汽车控制器产品 Software Architecture(SwAD,软件架构)文档写作;保留 ASPICE SWE.2、ISO 26262-6 软件层接口、SwRS 追溯、组件分配、接口边界、tier、HITL 与 candidate-update 约束。
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "software-architecture-document-type" does not match folder "SoftwareArchitecture"
Files (14)
- SKILL.md
- step-candidate-profile-update.md · steps/
- step-conservative-draft.md · steps/
- step-evidence-map.md · steps/
- step-final-report.md · steps/
- step-input-materials.md · steps/
- step-material-inventory.md · steps/
- step-research-questions.md · steps/
- step-review.md · steps/
- step-revision.md · steps/
- step-run-summary.md · steps/
- step-source-index.md · steps/
- step-template-outline.md · steps/
- step-verification.md · steps/
SKILL.md (first lines)
# Software Architecture Document Type Skill Use this skill for `task_type: SoftwareArchitecture` only when the agent workflow explicitly selects this guidance. This is a non-official L3 Skill/overlay asset. The metadata builder may place its paths/hashes in StepContextPackage for that exact task type, but Python has no Software Architecture rules registry or end-to-end content engine. Default communication is Chinese; keep Software Architecture、SwAD、SWE.2、ISO 26262-6、SwRS、System Architecture、SWA-COMP-xx、SWA-IF-xx、RTE、BSW、HITL、NEEDS_USER_CONFIRMATION. ## Purpose Software Architecture supports a review-ready ECU software architecture package in ASPICE SWE.2 / ISO 26262-6 context. It organizes software boundary, layers, logical/physical architecture, components, interfaces, SwRS allocation, diagnostics/degradation, safety-related software constraints by citation only, resources/timing, verification method candidates, assumptions, and open confirmations. It does not produce HARA, FSR, TSC, detailed design, code-level design, ASPICE assessment pass, ISO compliance, architecture approval, or production release approval. ## Method Boundaries - Read materials by L1→L2→L3→original text. - One architecture fact = one claim with T0/T1 EVD or explicit open; no blanket evidence for whole tables. - From-Scratch: many `confirmation_required` / placeholder rows are expected; do not fill missing SwRS, interface direction, task period, stack size, RTE port direction, or component split. - With-Reference: historical SwAD is `sample` only. It may guide section/table shape, never component/interface/task/resource facts. Include SEC-DIFF / TASK-DIFF when reference is used. ## Typical Inputs T1 source examples: SwRS, current project System Architecture, software context/layering, AUTOSAR/BSW/MCAL/OS constraints, RTE/service/internal API specs, diagnostics/degradation notes, chip/memory/timing budgets, existing TSR/software safety inputs for SEC-SAFE-ARCH citation only. Template/checklist/reference/sample keep their roles. Historical SwAD is T4 sample unless the user provides explicit current-project source status. ## Expected Sections Core sections: scope, inputs/source boundary, software context/layers, upstream SwRS/System Architecture, logical architecture, physical/task architecture, components, interfaces/direction, SwRS allocation, diagnostics/degradation, safety-related architecture constraints by citation, resources/timing, verification candidates, assumptions/open items, review status, optional SEC-DIFF for With-Reference. ## Critical Claims Critical claims include architecture decomposition, upstream linkage, component definition, interface direction/boundary, allocation rationale, task/scheduling, diagnostics/degradation, resource/timing budgets, safety-related software architecture linkage, verification method, completeness/consistency/sufficiency, and final approval/compliance. They require T0/T1 support or remain `NEEDS_USER_CONFIRMATION`. ## Forbidden Content - hazard、hazardous event、S/E/C、ASIL、Safety Goal as new HARA/FSR output. - TSR / technical safety mechanisms as TSC final content. - detailed design, unit design, algorithms, code, class-level implementation. - approved / compliant / ASPICE level achieved / ISO 26262 compliant / production ready. - sample SwAD components, interfaces, tasks, timing, resource budgets as project facts. SEC-SAFE-ARCH may only cite existing TSR/software safety source and link it to components/interfaces/partitioning; no new HARA, ASIL, or TSR judgment. ## Source Policy T0=HITL, T1=current project source, T2=template/checklist, T3=reference methodology, T4=sample shape/style, T5=inference. Current project `SystemArchitecture` and SwRS can be T1. Historical SwAD cannot support `SWA-COMP-xx`, `SWA-IF-xx`, task periods, memory/stack budgets, interface timeouts, or allocation facts. sample 绝不是 fact source。reference is not project-specific fact support. ## Review / Verification Focus - SWE.2 architecture decomposition, allocation, interface, and design constraints. - Every component/interface/allocation has source or open. - Interfaces include direction, peer, boundary, responsibility. - Logical and physical architecture are consistent. - Diagnostics/degradation/resources/timing have source or open. - No HARA/ASIL/SG/TSR/TSC/detailed-design leakage. - Historical SwAD/sample not used as fact. - `NEEDS_USER_CONFIRMATION` preserved. Final report is review-ready, not formal sign-off.
From Exquisite0828/AI_writer_plugin, MIT.
More from Exquisite0828/AI_writer_plugin
- 0.469score
step-candidate-profile-update
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow candidate profile update.
SkillCFreshness: CClaude Code +9 - 0.469score
step-conservative-draft
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow conservative draft generation.
SkillCFreshness: CClaude Code +9 - 0.469score
step-evidence-map
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 6 evidence map, citation plan, and section tasks.
SkillCFreshness: CClaude Code +9 - 0.469score
step-final-report
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow final report delivery.
SkillCFreshness: CClaude Code +9 - 0.469score
step-input-materials
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 1 input materials.
SkillCFreshness: CClaude Code +9 - 0.469score
step-material-inventory
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 2 material inventory.
SkillCFreshness: CClaude Code +9 - 0.469score
step-research-questions
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 5 research questions and writing-plan analysis.
SkillCFreshness: CClaude Code +9 - 0.469score
step-review
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow review.
SkillCFreshness: CClaude Code +9 - 0.468score
fsr-document-type
Exquisite0828
中文优先指导 fsr document type work,同时保留 functional safety requirement、safety goal、ASIL、source tier、provenance、sample/reference、HITL、final-report、TSC-deferred 和…
SkillCFreshness: CClaude Code +9 - 0.468score
hara-document-type
Exquisite0828
中文优先指导 HARA document type work,同时保留 HARA terminology、evidence、source tier、HITL、final-report、sample/reference 和 candidate-update boundaries。
SkillCFreshness: CClaude Code +9 - 0.468score
item-definition-document-type
Exquisite0828
中文优先指导 Item Definition Document(功能安全 Item 定义文档)写作;保留 ISO 26262-3 Clause 5 术语、source tier、HITL、sample/reference 边界与 candidate-update 约束。
SkillCFreshness: CClaude Code +9 - 0.468score
software-requirement-document-type
Exquisite0828
中文优先指导汽车控制器产品 Software Requirement(SwRS,软件需求)文档写作;保留 ASPICE SWE.1、ISO 26262-6 软件层接口、追溯、System Architecture 参考边界、tier、HITL 与 candidate-update 约束。
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 13, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Exquisite0828
- 0.469score
step-evidence-map
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 6 evidence map, citation plan, and section tasks.
SkillCFreshness: CClaude Code +9 - 0.469score
step-input-materials
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 1 input materials.
SkillCFreshness: CClaude Code +9 - 0.469score
step-candidate-profile-update
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow candidate profile update.
SkillCFreshness: CClaude Code +9 - 0.469score
step-conservative-draft
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow conservative draft generation.
SkillCFreshness: CClaude Code +9 - 0.469score
step-final-report
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow final report delivery.
SkillCFreshness: CClaude Code +9 - 0.469score
step-material-inventory
Exquisite0828
Registerable Claude Code wrapper for AI writing workflow Step 2 material inventory.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get software-architecture-document-type running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
software-architecture-document-type skill. Agent Mart. https://agentmart.dev/skills/exquisite0828-software-architecture-document-type (last updated 2026-10-24)