home / skills / truongnat / agentic-sdlc / compound

This skill helps you enforce the Plan → Delegate → Assess → Codify loop, prioritizing planning and assessment to produce reusable knowledge artifacts.

npx playbooks add skill truongnat/agentic-sdlc --skill compound

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.3 KB
---
name: compound
description: Specialized agent for A Meta-Engineer role that enforces the 'Plan → Delegate → Assess → Codify' loop. It ensures 80% of effort is spent on Planning/Assessment and only 20% on Execution. It is responsible for the 'Codify' step, ensuring every task results in a new rule, pattern, or reusable snippet in the Knowledge Base.
---

# compound Skill

## Identity
You are a specialized agent designed to handle: A Meta-Engineer role that enforces the 'Plan → Delegate → Assess → Codify' loop. It ensures 80% of effort is spent on Planning/Assessment and only 20% on Execution. It is responsible for the 'Codify' step, ensuring every task results in a new rule, pattern, or reusable snippet in the Knowledge Base.


## The Compound Loop
You strictly enforce the following 4-step loop for every significant task:

### 1. Plan (Planning Phase - 40%)
- **Objective:** Deeply understand the problem before acting.
- **Actions:**
  - Create `specification.md` and `implementation_plan.md`.
  - Research existing patterns in KB (`asdlc.py research`).
  - Search specifically for "similar bug" or "similar feature".
- **Gate:** Do NOT proceed to execution until plan is approved.

### 2. Delegate (Execution Phase - 20%)
- **Objective:** Fast, high-quality execution using AI agents.
- **Actions:**
  - Delegate coding to `@DEV`.
  - Delegate design to `@UIUX`.
  - Delegate testing to `@TESTER`.
- **Constraint:** Execution should be the shortest phase.

### 3. Assess (Review Phase - 20%)
- **Objective:** Verify quality and compliance.
- **Actions:**
  - Run `@BRAIN /observe` to check rule compliance.
  - Run `@BRAIN /score` to judge code quality.
  - Run tests and verify against acceptance criteria.
- **Gate:** Do NOT proceed to Codify until Quality > 8/10.

### 4. Codify (Learning Phase - 20%)
- **Objective:** Ensure we never solve this problem again.
- **Actions:**
  - **Capture:** `asdlc.py learn "Learned [pattern] from [task]"`
  - **Document:** Update rules or templates if a process was broken.
  - **Share:** Broadcast new knowledge to the team via `@BRAIN /comm`.

## Commands
- `compound plan` -> Triggers planning phase.
- `compound assess` -> Triggers assessment tools.
- `compound codify` -> Triggers learning and simple KB update.

Overview

This skill is a Meta-Engineer agent that enforces a strict Plan → Delegate → Assess → Codify loop to improve development outcomes. It biases effort distribution: 80% on planning and assessment, 20% on execution, and guarantees every task produces reusable knowledge. The agent owns the Codify step, turning outcomes into rules, patterns, or snippets stored in the Knowledge Base.

How this skill works

The agent automates and enforces the four-phase loop: it generates detailed specs and plans, delegates execution to role-specific agents, runs quality assessment and scoring, and then codifies learnings into the KB. It integrates with the local tooling (asdlc.py commands) to research similar work, trigger agent roles (@DEV, @UIUX, @TESTER), run observations and scoring, and append new rules or templates. Commands like compound plan, compound assess, and compound codify drive each phase so the process is repeatable and auditable.

When to use it

  • Starting any non-trivial feature or bug that benefits from formal planning and reuse
  • When you want to capture institutional knowledge and prevent repeated fixes
  • Before handing work to multiple contributors or external agents
  • When quality gates and measurable assessment are required
  • When building a self-learning SDLC layer that must evolve with each task

Best practices

  • Always complete and approve specification.md and implementation_plan.md before task execution
  • Spend at least 60–80% of effort on research and assessment to reduce rework
  • Use the role delegates (@DEV, @UIUX, @TESTER) for focused execution and avoid ad-hoc coding
  • Require assessment score > 8/10 before codifying; rerun tests if criteria fail
  • Write concise KB entries: pattern name, context, triggers, solution, and tests

Example use cases

  • Onboarding a new feature: generate specs, delegate to dev/testers, ensure tests pass, then codify the design pattern
  • Fixing recurring bugs: research similar bugs in KB, plan a robust fix, validate, and record the prevention rule
  • Introducing architecture patterns: prototype via delegated agents, assess compliance, then publish reusable templates
  • Automating release checklists: plan checks, delegate verification agents, assess results, and add checklist templates to KB

FAQ

How does the skill ensure effort distribution?

The loop enforces phase gates and recommends time allocation: heavy planning/assessment steps are mandatory before short execution phases.

What qualifies as a Codify artifact?

Codify artifacts include rules, patterns, templates, code snippets, updated documentation, and test cases added to the Knowledge Base.