- Home
- Skills
- Technical Documentation
- Planning Docs
Works with the AI Agents you already use
Planning Docs
Enforces a structured docs/ folder using templates for ADRs, specs, implementation plans, and investigation logs.
$19.95
Planning Docs
Example session with this skill installed
We need to move from REST to gRPC for the internal microservices. Can you draft an ADR for this decision and create a spec for the first service migration?
- Read your context and instructions
- Compiled the planning docs
I have initialized the documentation structure, drafted the ADR for the protocol migration, created the initial service specification, and updated the project index.
Documentation Update
| File | Action | Description |
|---|---|---|
docs/index.md | Updated | Added links to gRPC migration ADR and User Service spec. |
docs/adr/0001-move-to-grpc.md | Created | Records the decision to switch from REST to gRPC. |
docs/specs/user-service-grpc.md | Created | Defines the design and requirements for the first service migration. |
# ADR 0001: Transition from REST to gRPC for Internal Communication
## Status
Proposed
## Context
Our current REST implementation over HTTP/1.1 is causing significant latency in inter-service communication due to text-based payloads and lack of multiplexing. As we scale to 50+ microservices, we need a more efficient serialization format.
## Decision
We will adopt gRPC and Protocol Buffers (proto3) for all internal service-to-service communication.
## Consequences
- **Positive:** Reduced payload size, strictly typed contracts, and improved performance.
- **Negative:** Increased complexity in debugging and requirement for custom load balancing logic.
---
# Spec: User Service gRPC Migration
## Goals
Migrate the legacy `/users` endpoints to a gRPC-based `UserService`.
## Design
The service will implement the following proto definition:
```mermaid
graph TD
Client -->|gRPC| UserService
UserService -->|SQL| Database
syntax = "proto3";
service UserService {
rpc GetUser (UserRequest) returns (UserResponse);
}
**Next steps**
- Review the ADR consequences with the infrastructure team.
- Define the detailed `.proto` messages in the User Service spec.
- Initialize `docs/plans/migration-sprint-1.md` to track the implementation tasks.
Connects securely to your tools. The creator never sees your data.
About this skill
Project documentation often turns into a dumping ground of stale notes, scattered READMEs, and conflicting specs. This skill enforces a professional, opinionated docs/ architecture for your repository. It stops documentation rot by classifying every piece of information into a specific, long-lived structure.
What it does
- Standardizes layouts by organizing all technical debt and design notes into a fixed
docs/tree. - Drafts ADRs to record immutable architectural decisions and their specific reasoning.
- Generates specs that define what a feature does and why, separate from implementation details.
- Builds implementation plans to sequence tasks, milestones, and technical execution steps.
- Logs investigations to capture debugging trails and root-cause analysis for future reference.
- Maintains a central index by automatically updating
docs/index.mdwhenever new files are added.
How it works
- Root resolution identifies the nearest
docs/directory or initializes one at the project root. - Classification maps your input to the correct document type, such as a spec, plan, or process guide.
- Template application uses pre-defined markdown structures to ensure consistent formatting across the team.
- Cross-linking establishes relative links between documents and updates the main index for discoverability.
Frameworks & tools
This skill produces standard Markdown files compatible with any IDE or static site generator. It utilizes mermaid for diagrams and follows specific shell command formatting for CLI documentation.
Why this beats prompting it yourself
Generic prompts often blur the lines between design (specs) and execution (plans). This skill uses a strict reference system to keep architectural decisions immutable while allowing implementation docs to evolve, preventing the "one giant README" problem.
Use cases
- Initializing a professional documentation structure for a new repository.
- Recording a complex architectural pivot through a formal ADR.
- Drafting a technical implementation plan for a multi-week feature build.
- Documenting a deep-dive bug investigation to prevent regression.
Known limitations
Does not invent facts to fill template sections. Git-specific steps mentioned in references are skipped if working outside a code repository.
Does not invent facts for missing sections. Repository-specific git steps are ignored when working in non-code environments. Requires manual review of AI-generated hypotheses.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 22 days ago