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. Use why for motivation.

License 许可
MIT
最近更新
2026-11-03
Stars
★ 35
Forks
0

01 前言 Front Matter

name
how
license
MIT
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. Use why for motivation.
disable-model-invocation
true

02 资源文件 2

03 SKILL.md 正文

How

Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.

Every spawn is a subagent call with a registered read-only pstack agent. Explorers use the verification role, and every explainer uses the judgment role. Set the role's model and thinking through /setup-pstack, or leave it at the default if the role or the line is missing. Leave model unset when the value is inherit, so that seat runs on the parent model. If the host rejects a configured model, use the default and say so. If it rejects the default, use the closest valid configured model of the same family and reasoning tier, and report the substitution. Pick each subagent's thinking for the job, per the Subagents section of the poteto-mode skill.

1. Assess complexity

If the scope is ambiguous, state your interpretation and explore. The user can redirect.

  • Simple (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. Spawn one explainer that explores and explains in one pass, built from explainer-prompt.md without the explorer-findings section. Go to step 4.
  • Complex (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.

When in doubt, take the simple path.

2. Explore (complex only)

Decompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with explorer-prompt.md and its angle filled in.

3. Synthesize (complex only)

Once all explorers have returned, spawn one explainer with references/explainer-prompt.md and every explorer's findings filled in.

4. Present

Present the explainer's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.

Output format

The explanation uses the sections defined in references/explainer-prompt.md, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.

Pi adaptation

Adapted from Lauren Tan’s pstack v0.15.25, MIT, fixed revision f713f14203cd6420cec13cd7c55c32d598dbab68. Read the Pi adapter for host mappings.

Delegation requires current operator or applicable project authorization and a compatible pi-subagents integration. If unavailable or unauthorized, perform authorized stages locally, disclose self-review and missing independence, and report any required independent stage as open. Use only registered pstack.* agents. Models and thinking bind through /setup-pstack roles and user agentOverrides; never put model in a task item or on the outer subagent call. Report unavailable or identical configured models; do not silently substitute. Await native completion notices and collect every required result before synthesis.

Use read for file contents, grep/find/ls for search and directories, and ffgrep/fffind when available. Batch independent reads with codemode when available. Use edit/write only for authorized changes; bash executes programs and Git in an explicit working directory, never reads or searches files. Keep one writer per worktree and isolate candidate output paths. Read-only reviewers never receive bash, edit, write, or nested delegation. Loading this skill grants no new permission: push, PR creation, merge, external messages, and destructive operations require explicit authorization in the current session. Commit only when authorized.

Explorers launch together through one parallel workflow, with the angle named only in each task:

subagent({ workflow: "parallel", args: { tasks: [
  { agent: "pstack.verifier", task: "<references/explorer-prompt.md with angle 1>" },
  { agent: "pstack.verifier", task: "<references/explorer-prompt.md with angle 2>" }
] } })

Never put model in a task item or on the outer call.

04 同仓库更多 Skills