Implementing Architecture
v1.0.2Use when: about to write code and docs/architecture/ exists with STATUS: APPROVED in architecture.yaml. Not when: no approved architecture yet (use compiling...
⭐ 0· 89·0 current·0 all-time
by@inetgas
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The skill is an instruction-only 'implement approved architecture' helper. It requires an approved docs/architecture/ and points the agent at repo patterns, schemas, and config to implement/refactor code. It does not ask for unrelated credentials, binaries, or external services; the requested capabilities match the name and description.
Instruction Scope
The SKILL.md tells the agent to read AGENTS.md, architecture artifacts, and pattern files in the repo and to treat certain directories as read-only unless explicitly asked to do compiler-maintenance. The workflow boundaries are explicit and focused on repository-local implementation work; there are no instructions to read unrelated system files or to send data to external endpoints.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. Nothing is downloaded or written by an installer, which minimizes installation risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. The absence of secrets and external credentials is proportionate to the described repo-local implementation task.
Persistence & Privilege
The skill is not always-enabled and uses default autonomy settings. It does not request persistent system-level privileges or changes to other skills' configs. The SKILL.md explicitly instructs agents to follow repo rules (AGENTS.md) and treat certain folders as read-only by default.
Assessment
This skill appears coherent and limited to implementing an already-approved architecture in the repository. Before installing: (1) confirm the agent will only get access to the intended repo (it needs to read docs/architecture and code), (2) review AGENTS.md and this SKILL.md so the agent's read/write boundaries are acceptable, and (3) when you let the agent run terminal commands, apply the usual repository-level safeguards (branch protection, code review, human approval for pushes) to avoid unintended changes.Like a lobster shell, security has layers — review code before you run it.
architectural-decision-recordsvk9780ryv7hayrtnrrm1zbx5q3h84tskdarchitecture-as-code-toolsvk9780ryv7hayrtnrrm1zbx5q3h84tskdarchitecture-constraints-enforcementvk9780ryv7hayrtnrrm1zbx5q3h84tskdbrownfield-refactoringvk9780ryv7hayrtnrrm1zbx5q3h84tskddeterministic-executionvk9780ryv7hayrtnrrm1zbx5q3h84tskddeveloper-toolsvk9780ryv7hayrtnrrm1zbx5q3h84tskdlatestvk9780ryv7hayrtnrrm1zbx5q3h84tskdnfr-enforcementvk9780ryv7hayrtnrrm1zbx5q3h84tskdprototype-refactoringvk9780ryv7hayrtnrrm1zbx5q3h84tskdsoftware-architecture-patternsvk9780ryv7hayrtnrrm1zbx5q3h84tskd
License
MIT-0
Free to use, modify, and redistribute. No attribution required.