skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
christofferbergj/agent-skills69 installs

how

Use for Pstack code walkthroughs, subsystem behavior, or module placement and ownership questions.

How do I install this agent skill?

npx skills add https://github.com/christofferbergj/agent-skills --skill how
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides architectural explanations and code walkthroughs by analyzing the project codebase. It uses subagents to explore code and report on subsystem behavior. While the skill is designed for read-only investigations, it is susceptible to indirect prompt injection if the code it analyzes contains malicious instructions intended to mislead the agent.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Invoke /domain-modeling to resolve and read the invoking project's configured artifacts. Read-only investigations and reviews report documentation drift without edits; creation or implementation reconciles accepted model changes through that owner.

How

Explore the codebase to answer "how does X work?" questions.

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

  1. Explain. Use /swarm to start one read-only subagent that explores and explains in one pass. Give it the user's question and this brief:

    You are writing an architectural explanation for a senior engineer. Explore the codebase and write an explanation that a senior engineer unfamiliar with this area could read and walk away with a solid mental model. They should understand the architecture well enough to start working in it confidently. You have read-only access to the codebase.

    With no delegation, explore and write the explanation yourself from the same brief, and disclose it. Complete when the explanation is supported by inspected code.

  2. Present the subagent's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it. Complete when the reader can trace the subsystem and distinguish current behavior from rationale, which belongs to /why.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/christofferbergj/agent-skills/how">View how on skillZs</a>