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
caezium/skills
最近更新
2026-08-24
Stars
★ 3
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 7

03 SKILL.md 正文

How

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 run independent architectural reviews when the host permits them

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): use parallel explorer agents when the user and host policy permit delegation; otherwise explore the same slices inline. Go to Step 2a.

When in doubt, lean simple. You can widen the exploration if the first pass 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.

When delegation is authorized, launch the explorers together with non-overlapping briefs, the inherited model, and read-only posture. Do not request a named model or broader permissions. When delegation is unavailable, work through the same exploration angles inline and keep their findings separate until synthesis.

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: Glob for relevant directories, Grep for key types/interfaces/class names
  • Follow the thread: from an entry point, trace the call chain (callers, callees, data flow, type definitions)
  • Read the actual code, don't guess from file names
  • Stop when it can describe the full path from input to output (or trigger to effect) without hand-waving any step
  • Note things that are surprising, non-obvious, or that a newcomer would 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)

Explore and explain in one pass. Read references/explainer-prompt.md for the communication style and output format. Use repository search and file reads directly; there is no need to delegate a narrow question.

Proceed to Step 4.

Step 3. Synthesize (complex questions only)

Synthesize the exploration slices into one coherent explanation. You may use one independent explainer when delegation is already authorized and the subsystem is large; otherwise synthesize inline. Read references/explainer-prompt.md for the full prompt template. Reconcile overlap and contradictions before presenting the result.

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. Run independent critiques

After the explanation is complete, run independent architectural critiques. Use parallel critics only when the user and host policy permit delegation, and use the host's inherited model unless the user explicitly asks for model diversity. Otherwise perform one fresh critique pass after setting the explanation aside.

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

caezium
caezium/skills

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

内容创作者写作与文案
★ 3
caezium
caezium/skills

wrangler

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

后端与接口
★ 3
caezium
caezium/skills

workers-best-practices

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

★ 3
caezium
caezium/skills

wizard

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

★ 3
caezium
caezium/skills

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

★ 3
caezium
caezium/skills

week-prep

Generate a briefing with calendar, tasks, and attention flags. Use for "week prep", "briefing", or "what's on this week".

Skill与智能体开发
★ 3