Agentic Doc Templates — Testing skill for Claude Code
Stop coding agents from losing intent or building the wrong product shape.
How to install Agentic Doc Templates
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open BrianCLowe/Agentic-Doc-Templates and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentic Doc Templates does
Stop coding agents from losing intent or building the wrong product shape. Modular Understanding/spec/TODO docs + agent playbooks (Cursor, Grok Build, Claude Code, OpenClaw). Optional ship-first; orchestrate → verify → branch-PR.
Alternatives in Testing
- Claude Codepro — by Max Ritter - Professional development environment for Claude Code with spec-driven workflow, TDD enforcemen 1.6k ★
- Claude Android Ninja — Agent Skill for Android development with Kotlin and Jetpack Compose, covering modular architecture, Navigation 112 ★
- PM Skills — 24 product management skills across the Triple Diamond lifecycle with agentskills.io spec compliance, template 84 ★
README
Agentic Doc Templates
**Stop coding agents from losing intent or building the wrong product shape.** Modular Understanding / spec / TODO docs plus tool-agnostic agent playbooks — so Cursor, Grok Build, Claude Code, OpenClaw, and friends stay aligned across chats, not just one clever session.
[](https://creativecommons.org/licenses/by/4.0/)  
If this sounds like you
Use this pack when any of these keep happening:
- The agent forgets decisions from last week and treats every chat as greenfield
- It builds a different product than you meant (wrong architecture, wrong surfaces, “helpful” scope creep)
- Intent lives only in Grok.com / ChatGPT / Discord threads and never becomes durable project docs
AGENTS.mdor always-on rules grew into a second codebase and still don’t fix drift- TODOs say done but nothing is operable (library checklist ≠ product you can run)
- You jump between Cursor, Grok Build, Claude, OpenClaw and want the same docs workflow
What this is / is NOT
| This is | This is not |
|---|---|
| Repo-owned modular docs + short agent playbooks agents open on demand | Another coding agent runtime (not a Cursor/Claude/Prime-Agent replacement) |
A small docs/ map: Master Index, features, Understandings, specs, TODOs, Human-TODO |
Notion / Linear / a hosted PM product |
Tool-agnostic install (Cursor rules, Grok agents, Claude, Copilot, AGENTS.md, …) |
One mega always-on rule file that tries to be the whole process |
| Optional |
Related Skills
Shape
Shape work through a relentless interview — interrogate an idea, a transcript, existing code, or an existing s
Gsd 2 Next
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work
Webtest Orch
Token-efficient e2e orchestration skill for Claude Code: explore once, replay deterministically. Playwright +
Boss Plan
You are the /boss-plan command. Your job is to cut scope from a roadmap, TODO list, spec, or feature plan.
Logic Locate
Locate the root cause of a confirmed failure — use when you have a stack trace, failing test, or wrong output
Logic Review
Review code for logic bugs — use when you suspect something is wrong but have no failing test yet
Related Agents
Cursor Delegate
Proactively use when this coding agent should hand a substantial coding, diagnosis, or implementation task to
Model Runner
Deterministic wrapper that runs a prompt on a non-Claude model (OpenAI via Codex, Cursor's composer/grok/glm,
Cursor Rescue
Proactively use as an extra agentic lane on Cursor's own quota — bounded coding tasks (a spec file, a rename,
