Skip to content
Back to skills

How

ASecurity

Explain codebase behavior, ownership, or architecture from source evidence.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
research

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add BumpyClock/agent-templates --skill how --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of How?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for How
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bumpyclock-how/badge)](https://www.skillsdirectory.com/skills/bumpyclock-how)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: how
description: Explain codebase behavior, ownership, or architecture from source evidence.
---

# How

Answer the codebase question at the level needed for a useful mental model.
An explanation or design recommendation is read-only unless the user also requests changes.

## Direct answer

Inspect the relevant entry points, contracts, callers, and documented decisions.
Trace the path needed to answer the question.
Distinguish observed behavior, documented intent, and inferred rationale.
State unresolved uncertainty rather than invent a reason.

Return the supported answer and useful source locations.
For a decision, give a recommendation and its tradeoffs.
A narrow question needs neither a repository map nor a full architecture report.

## Complex questions

Use [Complex investigation](references/complex-investigation.md) when several independent paths or substantial source context need synthesis.
Use [Architecture critique](references/critique-rubric.md) for a requested critique or an unresolved design tradeoff.
These routes do not require delegation or a separate explanation artifact.

Do not create a prototype, edit source, commit, or open a pull request unless the task authorizes that action.

Files in this skill

  • SKILL.md1.2 KB
  • agents/openai.yaml270 B
  • references/complex-investigation.md1.9 KB
  • references/critic-prompt.md2.2 KB
  • references/critique-rubric.md2.8 KB
  • references/explainer-prompt.md2.8 KB
  • references/explorer-prompt.md2.4 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.