agentsclimarketplace

Automated software guidebook generator

Skill anyulled/architecture-guardrails-skills/skills/automated-software-guidebook-generator

Agent-agnostic software architecture guardrails skills collection

Install
npx -y skills add anyulled/architecture-guardrails-skills --skill automated-software-guidebook-generator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate and maintain a living software guidebook by scanning repository code, infrastructure, deployment files, and docs. Use when periodic documentation updates are needed, especially after IaC, deployment script, or major release changes.

SKILL.md

2.9 KB, 530 tokens by cl100k_base, as published. Nobody here has run it

Automated Software Guidebook Generator

Generate and keep a repository guidebook current from code and documentation.

When to Use

  • Weekly or sprint-end documentation reviews
  • Major releases
  • IaC, deployment, or build script changes
  • Repositories where architecture docs must stay current with minimal overhead

Required Sections

Validate that the guidebook includes:

  • Context
  • Functional Overview
  • Quality Attributes
  • Constraints
  • Principles
  • Software Architecture
  • Infrastructure Architecture
  • Deployment
  • Operation and Support
  • Development Environment

Scope

  • Scans: documentation directories, README files, architecture docs, IaC, build scripts, and other artifacts needed to maintain a living guidebook.
  • Exclusions: ADR completeness checks, code-only refactors with no documentation impact, and runtime-only behavior.
  • Fallback: if the guidebook structure is incomplete or ambiguous, fall back to the shared conventions heuristic order and emit warning with low confidence.
  • Routing: defer decision-record completeness to Decision Log and ADR Tracer and explicit architecture-rule enforcement to Automated Architecture Governance.

Workflow

  1. Validate structure.
    • Check docs/ and top-level markdown such as README.md.
    • Flag missing required sections.
  2. Extract infrastructure and deployment facts.
    • Inspect IaC, container, and deployment scripts.
    • Map runtime, environment, logging, monitoring, and diagnostics.
  3. Map principles and constraints.
    • Read configuration, lint rules, framework choices, and repository conventions.
    • Derive protocols, formats, layering, dependency, and style constraints.
  4. Report and draft.
    • List outdated or missing sections.
    • Produce markdown drafts for absent sections.

Rules

  • Use static analysis only.
  • Prefer repository truth over inferred intent.
  • Treat docs as living artifacts: update the smallest relevant section first.
  • Do not invent infrastructure details that are not supported by files.

Shared Conventions

  • Follow the repository-wide conventions in shared-skill-conventions.
  • Use the canonical output contract, severity levels, confidence rubric, routing rules, and false-positive downgrades defined there.
  • If this skill is not the closest match, defer to the routing guidance in the shared conventions file.

Output

Return a structured report with:

  • Missing guidebook sections
  • Outdated sections
  • Extracted facts for deployment and operations
  • Draft markdown for missing content

Template Source

Use the bundled template in assets/guidebook_template.md.

What ships with it: 1 file

1.1 KB alongside SKILL.md

assets/

Keep looking

Skills are one crate of 327,069. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.