Skip to content
cccskills
FreePublished on GitHub

zoom-out

Produce a higher-level architecture and context map for unfamiliar code. Use when you need to understand how a file, module, feature, or issue fits into the bigger picture, including relevant modules, callers, callees, dependencies, and next context.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

zoom-out

Use this skill when the user asks you to zoom out, says they do not know an area of code well, or needs a broader map before changing code.

Goal

Go up one layer of abstraction. Explain how the relevant code fits together before recommending implementation details.

Process

1) Anchor the question

Identify the smallest useful focus:

  • The file, symbol, feature, route, command, workflow, or Beads issue the user is asking about.
  • The user-facing behavior or agent workflow it supports.
  • Any alignment document, interface contract, or bd show <id> output that defines the current task.

If the focus is unclear, ask one targeted clarifying question before exploring broadly.

2) Load knowledge first

Read the relevant harness knowledge before source code:

  • knowledge/_shared.yaml
  • knowledge/repos/<repo>.yaml for sub-repo work, when present
  • Nearby plans, protocols, workflows, or skill docs that already describe the area

Use the knowledge files to name likely modules and boundaries, then verify those claims in source.

3) Map the code surface

Find the important pieces around the focus:

  • Entrypoints: commands, routes, scripts, hooks, workflows, components, or public exports.
  • Core modules: domain logic, shared types, parsers, adapters, persistence, or UI surfaces.
  • Callers: files or commands that invoke the focus.
  • Callees and dependencies: modules the focus imports, shells out to, reads from, writes to, or expects as data contracts.
  • Tests and fixtures: behavior examples that show intended use.

Prefer exact searches for symbols, imports, filenames, and route names. Expand outward only until the caller/callee map explains the behavior.

4) Trace the flow

Summarize the path through the system:

  • What starts the flow.
  • What data or control decisions move through each module.
  • Which side effects occur, such as filesystem writes, Beads updates, network calls, git operations, or UI state changes.
  • Where errors, validation, or quality gates happen.
  • What depends on this behavior staying stable.

5) Report the context map

Keep the response concise and actionable. Use this shape:

## Zoomed-Out Map

<2-4 sentence overview of what this area does and why it exists.>

| Area | Files / Symbols | Role | Callers | Callees / Dependencies |
|------|-----------------|------|---------|------------------------|
| ... | `path` / `symbol` | ... | ... | ... |

## Flow

1. <entrypoint starts the behavior>
2. <core module transforms or validates>
3. <outputs, side effects, or UI/result>

## Boundaries And Risks

- <important invariant, ownership boundary, or coupling>
- <test or quality gate that protects it>

## Next Context

- <the next file, test, or decision to inspect if implementation continues>

Do not turn the zoom-out into a full implementation plan unless the user asks for one. The output should make the surrounding architecture legible enough for the next coding or review step.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Capture free-text work as a tracked Beads issue. Use when the user runs /add-bead or wants to quickly file a Beads issue.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 22, 2026

Register a new sub-repo in the knowledge base.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 22, 2026

Add focused Bun unit tests for mission-critical behavior and edge cases — not blanket coverage.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 22, 2026

ask

Free

Answer questions about the codebase from knowledge files. Use when the user runs /ask or asks a domain/knowledge question about the repos.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 22, 2026

Meta-skill for creating Agent Forge skills under .claude/skills/ with SKILL.md, optional references/ and scripts/, and Bun scaffolds. Use when the user wants to add or author a skill, scaffold a new skill folder, or align skill docs with harness conventions (JSON script output, Beads for tasks).

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 22, 2026

Choose Beads issue priority (P0–P4, numeric, or named) from urgency, impact, and risk when creating or triaging work.

The English summary is being prepared. Showing the original description.

jupes/agent-forge-harness2Updated Oct 22, 2026

See all skills by jupes

Report a problem with this skill