AGENT SKILL

how

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.

License 许可
MIT
所属仓库
emo-eth/skills
最近更新
2026-11-13
Stars
★ 0
Forks
0

01 前言 Front Matter

name
how
description
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.

02 资源文件 5

03 SKILL.md 正文

How

Read pstack-runtime before the first host-specific operation.

Explore the codebase to answer "how does X work?" questions. Produce clear architectural explanations at the level of a senior engineer onboarding onto a subsystem. Enough to build a working mental model, not annotated source code.

Two modes:

  1. Explain (default). Explore the codebase and produce a clear explanation
  2. Critique. Explain first, then spawn independent reviewers through the current host.

Explain Mode

Step 1. Understand the Question and Assess Complexity

Parse what the user is asking about:

  • "How does the rate limiter work?", a subsystem
  • "How do we handle billing for on-demand usage?", a feature flow
  • "How is the auth service structured?", an architectural overview
  • "Walk me through what happens when a user submits a form", a runtime trace

Identify the scope. If ambiguous, state your best-guess interpretation before exploring. Don't ask. Let the user redirect if you're off.

Assess complexity to decide the approach:

  • Simple (a single module, a small utility, a narrow question like "how does function X work"): skip explorer agents; the explainer explores and explains in a single pass. Go to Step 2b.
  • Complex (a subsystem spanning multiple files/services, a cross-cutting feature, a full architectural overview): spawn parallel explorer agents first, then hand off to the explainer. Go to Step 2a.

When in doubt, lean simple. You can always spawn explorers if the explainer hits a wall.

Step 2a. Explore (complex questions only)

Decompose the question into 2-4 parallel exploration angles, each a distinct slice of the subsystem so explorers don't duplicate work. Example split for "how does the rate limiter work?":

  • Explorer 1: data model and state management
  • Explorer 2: request path and enforcement
  • Explorer 3: configuration and metrics infrastructure

The right decomposition depends on the question. Use your judgment. Narrow questions: 2 explorers is fine. Broad subsystems: up to 4.

Read ~/.config/pstack/omp-agents.json when it exists. Spawn every explorer in one OMP task batch. Use the configured how-explorer type, or scout by default. Explorer tasks are read-only and must use the scout contract. Each explorer gets the same base prompt from references/explorer-prompt.md plus a specific exploration angle naming its slice. Each explorer should:

  • Start broad with glob for relevant directories and grep for key types, interfaces, and names
  • Follow symbols with lsp references and definitions when a language server is available; otherwise trace callers, callees, data flow, and type definitions from source
  • Read the actual code instead of guessing from file names
  • Stop when it can describe the full path from input to output, or trigger to effect, without hand-waving a step
  • Note surprising or non-obvious behavior that a newcomer could get wrong

Each explorer returns structured findings: components found, flow traced, files read, anything non-obvious. Overlap between explorers is fine; the explainer reconciles.

Then proceed to Step 3.

Step 2b. Direct Explain (simple questions)

Spawn one read-only scout task that explores and explains in one pass. Use the configured how-explainer type only when it is a read-only research agent available in the current OMP roster.

The agent does its own exploration with glob, grep, read, and lsp, then writes the explanation directly. Read references/explainer-prompt.md for the communication style and output format. Use the same structure with no explorer findings as input.

Proceed to Step 4.

Step 3. Synthesize (complex questions only)

After all explorers return, spawn one synthesis task. Use the configured how-explainer type, or scout by default. Pass the explorer results by local:// artifact when they are large instead of inlining raw output.

The explainer writes the human-facing explanation. Read references/explainer-prompt.md for the full prompt template. It reconciles overlap, resolves contradictions against cited source, and joins the slices into one model.

Step 4. Present

Present the explainer's output to the user. You may lightly edit for clarity or add context from the conversation, but don't substantially rewrite. The explainer's communication is the product.

Output Format

Follow this structure, adapted to the question. Not every section is needed for every question.

Overview. 1-2 paragraphs. What it is, what it does, why it exists. Enough to decide whether to keep reading.

Key Concepts. The important types, services, or abstractions. Brief definition of each. Not exhaustive, just the ones needed to understand the rest.

How It Works. The core of the explanation. Walk through the flow: what triggers it, what happens step by step, where data goes, the decision points. Prose, not pseudocode. Reference specific files and functions so the reader can go look, but don't dump code blocks unless a snippet is genuinely necessary.

Where Things Live. A brief map of the relevant files/directories. Not every file, just the ones needed to start working in this area.

Gotchas. Non-obvious or surprising things that would trip someone up. Historical context that explains why something looks weird. Known sharp edges.

Critique Mode

Triggered when the user asks for architectural issues, problems, or improvements, not just understanding.

Step 1. Explain First

Run the full explain flow above (Steps 1-4). You must understand the architecture before critiquing it.

Step 2. Spawn Critics

After the explanation is complete, read the how-critics list from ~/.config/pstack/omp-agents.json when present. Otherwise use two reviewer tasks. Spawn all critics in one OMP task batch. Every critic is read-only.

OMP agent types can use the same underlying model. Treat this as independent review, not guaranteed model-family diversity. A missing configured type falls back to reviewer.

Read references/critic-prompt.md for the prompt template. Each critic gets:

  1. The explanation from Step 1 (so they don't re-explore)
  2. The relevant file paths (so they can read the actual code)
  3. The architectural critique rubric from references/critique-rubric.md

Step 3. Lead Judgment

Same framework as the interrogate skill. You're a pragmatic lead, not an aggregator.

Categorize findings:

  • Act on. Architectural problems worth fixing now
  • Consider. Real concerns, but the cost/benefit is unclear
  • Noted. Valid observations, low priority
  • Dismissed. Wrong, missing context, or style preference

Present the explanation first (from Step 1), then the critique verdict below it. The explanation should stand on its own; someone who just wants to understand the system shouldn't wade through critique.

04 同仓库更多 Skills