documentation-criteria — agent-skills documentation-criteria, agentic-code, community, agent-skills, ide skills, agentic-ai, agentic-workflow, ai-agents, developer-tools, gemini-cli, Claude Code

v1.0.0

About this Skill

Perfect for Development Agents needing systematic test-first workflows with quality gates for AI coding agents, powered by AGENTS.md Guides PRD, ADR, Design Doc, and Work Plan creation. Use when: planning features, writing specs, or creating technical documents.

# Core Topics

shinpr shinpr
[35]
[3]
Updated: 3/2/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 7/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Locale and body language aligned
Review Score
7/11
Quality Score
44
Canonical Locale
en
Detected Body Locale
en

Perfect for Development Agents needing systematic test-first workflows with quality gates for AI coding agents, powered by AGENTS.md Guides PRD, ADR, Design Doc, and Work Plan creation. Use when: planning features, writing specs, or creating technical documents.

Core Value

Empowers agents to create comprehensive content analysis using Creation Decision Matrix, supporting PRD, ADR, Design Doc, and Work Plan documents, with systematic test-first workflows and quality gates for AI coding agents

Ideal Agent Persona

Perfect for Development Agents needing systematic test-first workflows with quality gates for AI coding agents, powered by AGENTS.md

Capabilities Granted for documentation-criteria

Automating documentation creation for new feature additions
Generating Architecture Decision Records (ADRs) for complex projects
Creating design documents and work plans for projects with 6+ files

! Prerequisites & Limits

  • Requires AGENTS.md framework
  • Limited to specific document types (PRD, ADR, Design Doc, Work Plan)

Why this page is reference-only

  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Curated Collection Review

Reviewed In Curated Collections

This section shows how Killer-Skills has already collected, reviewed, and maintained this skill inside first-party curated paths. For operators and crawlers alike, this is a stronger signal than treating the upstream README as the primary story.

Reviewed Collection

Developer Workflow Tools to Install First

Reviewed 2026-04-17

Reviewed on 2026-04-17 against coding workflow fit, installation clarity, review and testing value, and release guardrails. This page is now positioned as an install-first developer workflow entry point instead of a vague tooling roundup.

We prioritize this page because developer-intent users usually need one toolchain they can install, validate, and prove inside a real coding loop before they standardize it across the team.

12 entries Killer-Skills editorial review within the recovery-focused authority queue.
Reviewed Collection

Best Codex Workflow Tools to Install First

Reviewed 2026-04-17

Reviewed on 2026-04-17 for setup clarity, maintainer reliability, repo review coverage, and handoff readiness. We kept the tools that help Codex operators move from first install to steady daily use.

Most people landing here already know they want to work in Codex. What they need next is a smaller list tied to review, handoff, and terminal execution instead of another broad integrations directory.

10 entries Killer-Skills editorial review with monthly collection checks.
Reviewed Collection

Agent Workflow Automation Tools to Install First

Reviewed 2026-04-17

Reviewed on 2026-04-17 against workflow automation fit, install clarity, operator handoff, and production usefulness. This page now acts as an installation-first gateway instead of a generic automation list.

We prioritize this page because automation-intent users should move quickly from comparison into installation and validation. That path is stronger for recovery than trapping them in broad tooling research.

9 entries Killer-Skills editorial review inside the recovery-focused authority queue.
After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is documentation-criteria?

Perfect for Development Agents needing systematic test-first workflows with quality gates for AI coding agents, powered by AGENTS.md Guides PRD, ADR, Design Doc, and Work Plan creation. Use when: planning features, writing specs, or creating technical documents.

How do I install documentation-criteria?

Run the command: npx killer-skills add shinpr/agentic-code/documentation-criteria. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for documentation-criteria?

Key use cases include: Automating documentation creation for new feature additions, Generating Architecture Decision Records (ADRs) for complex projects, Creating design documents and work plans for projects with 6+ files.

Which IDEs are compatible with documentation-criteria?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for documentation-criteria?

Requires AGENTS.md framework. Limited to specific document types (PRD, ADR, Design Doc, Work Plan).

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add shinpr/agentic-code/documentation-criteria. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use documentation-criteria immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

documentation-criteria

Install documentation-criteria, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Documentation Creation Criteria

Creation Decision Matrix

ConditionRequired DocumentsCreation Order
New Feature AdditionPRD → [ADR] → Design Doc → Work PlanAfter PRD approval
ADR Conditions Met (see below)ADR → Design Doc → Work PlanStart immediately
6+ FilesADR → Design Doc → Work Plan (Required)Start immediately
3-5 FilesDesign Doc → Work Plan (Recommended)Start immediately
1-2 FilesNoneDirect implementation

ADR Creation Conditions (Required if Any Apply)

1. Type System Changes

  • Adding nested types/structures with 3+ levels: e.g., A { B { C { D } } }
    • Rationale: Deep nesting has high complexity and wide impact scope
  • Changing/deleting types used in 3+ locations
    • Rationale: Multiple location impacts require careful consideration
  • Data representation responsibility changes (e.g., transfer object→domain model)
    • Rationale: Conceptual model changes affect design philosophy

2. Data Flow Changes

  • Storage location changes (DB→File, Memory→Cache)
  • Processing order changes with 3+ steps
    • Example: "Input→Validation→Save" to "Input→Save→Async Validation"
  • Data passing method changes (props→Context, direct reference→events)

3. Architecture Changes

  • Layer addition, responsibility changes, component relocation

4. External Dependency Changes

  • Library/framework/external API introduction or replacement

5. Complex Implementation Logic (Regardless of Scale)

  • Managing 3+ states
  • Coordinating 5+ asynchronous processes

Detailed Document Definitions

PRD (Product Requirements Document)

Purpose: Define business requirements and user value

Includes:

  • Business requirements and user value
  • Success metrics and KPIs (measurable format)
  • User stories and use cases
  • MoSCoW prioritization (Must/Should/Could/Won't)
  • MVP and Future phase separation
  • User journey diagram
  • Scope boundary diagram

Excludes:

  • Technical implementation details (→Design Doc)
  • Technical selection rationale (→ADR)
  • Implementation phases (→Work Plan)
  • Task breakdown (→Work Plan)

ADR (Architecture Decision Record)

Purpose: Record technical decisions

Includes:

  • Decision (what was selected)
  • Rationale (why that selection was made)
  • Option comparison (minimum 3 options) and trade-offs
  • Architecture impact
  • Principled implementation guidelines

Excludes:

  • Implementation schedule, duration (→Work Plan)
  • Detailed implementation procedures (→Design Doc)
  • Specific code examples (→Design Doc)
  • Resource assignments (→Work Plan)

Design Document

Purpose: Define technical implementation

Includes:

  • Existing codebase analysis (required)
    • Implementation path mapping (both existing and new)
    • Integration point clarification (connection points with existing code even for new implementations)
  • Technical implementation approach (vertical/horizontal/hybrid)
  • Technical dependencies and implementation constraints (required implementation order)
  • Interface and type definitions
  • Data flow and component design
  • E2E verification procedures at integration points
  • Acceptance criteria (measurable format)
  • Change impact map (clearly specify direct impact/indirect impact/no ripple effect)
  • Complete enumeration of integration points
  • Data contract clarification
  • Agreement checklist (agreements with stakeholders)
  • Code inspection evidence (inspected files/functions during investigation)
  • Field propagation map (when fields cross component boundaries)
  • Data representation decision (when introducing new structures)
  • Applicable standards (explicit/implicit classification)
  • Prerequisite ADRs (including common ADRs)

Required Structural Elements:

yaml
1Change Impact Map: 2 Change Target: [Component/Feature] 3 Direct Impact: [Files/Functions] 4 Indirect Impact: [Data format/Processing time] 5 No Ripple Effect: [Unaffected features] 6 7API Contract Change Matrix: 8 Existing: [Function/operation signature] 9 New: [Function/operation signature] 10 Conversion Required: [Yes/No] 11 Compatibility Strategy: [Approach]

Excludes:

  • Why that technology was chosen (→Reference ADR)
  • When to implement, duration (→Work Plan)
  • Who will implement (→Work Plan)

Work Plan

Purpose: Implementation task management and progress tracking

Includes:

  • Task breakdown and dependencies (maximum 2 levels)
  • Schedule and duration estimates
  • Copy E2E verification procedures from Design Doc (cannot delete, can add)
  • Stage 4 Quality Assurance Stage (required)
  • Progress records (checkbox format)

Excludes:

  • Technical rationale (→ADR)
  • Design details (→Design Doc)

Stage Division Criteria:

  1. Stage 1: Foundation Implementation - Type definitions, interfaces, test preparation
  2. Stage 2: Core Feature Implementation - Business logic, unit tests
  3. Stage 3: Integration Implementation - External connections, presentation layer
  4. Stage 4: Quality Assurance (Required) - Acceptance criteria achievement, all tests passing, quality checks

Three Elements of Task Completion Definition:

  1. Implementation Complete: Code is functional
  2. Quality Complete: Tests, type checks, linting pass
  3. Integration Complete: Verified connection with other components

Creation Process

  1. Problem Analysis: Change scale assessment, ADR condition check
    • Identify explicit and implicit project standards before investigation
  2. ADR Option Consideration (ADR only): Compare 3+ options, specify trade-offs
  3. Creation: Use templates, include measurable conditions
  4. Approval: "Accepted" after review enables implementation

Storage Locations

DocumentPathNaming ConventionTemplate
PRDdocs/prd/[feature-name]-prd.mdtemplate-en.md
ADRdocs/adr/ADR-[4-digits]-[title].mdtemplate-en.md
Design Docdocs/design/[feature-name]-design.mdtemplate-en.md
Work Plandocs/plans/YYYYMMDD-{type}-{description}.mdtemplate-en.md

*Note: Work plans are stored in docs/plans/ and excluded by .gitignore

ADR Status

ProposedAcceptedDeprecated/Superseded/Rejected

AI Automation Rules

  • 5+ files: Suggest ADR creation
  • Type/data flow change detected: ADR mandatory
  • Check existing ADRs before implementation

Diagram Requirements

Required diagrams for each document (using mermaid notation):

DocumentRequired DiagramsPurpose
PRDUser journey diagram, Scope boundary diagramClarify user experience and scope
ADROption comparison diagram (when needed)Visualize trade-offs
Design DocArchitecture diagram, Data flow diagramUnderstand technical structure
Work PlanPhase structure diagram, Task dependency diagramClarify implementation order

Common ADR Relationships

  1. At creation: Identify common technical areas (logging, error handling, async processing, etc.), reference existing common ADRs
  2. When missing: Consider creating necessary common ADRs
  3. Design Doc: Specify common ADRs in "Prerequisite ADRs" section
  4. Compliance check: Verify design aligns with common ADR decisions

Related Skills

Looking for an alternative to documentation-criteria or another community skill for your workflow? Explore these related open-source skills.

View All

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

149.6k
0
AI

flags

Logo of vercel
vercel

The React Framework

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Developer