Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Atlas

ASecurity

Forge's code-graph. Use to find where a symbol is defined (where-is-X), to discover reusable code before writing new, and to check a symbol actually exists before calling it (anti-hallucination). Backed by `forge atlas`.

2 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsapi

Works with

apimcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add CodeWithJuber/forgekit --skill atlas --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Atlas?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Atlas
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/codewithjuber-atlas/badge)](https://www.skillsdirectory.com/skills/codewithjuber-atlas)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: atlas
description: Forge's code-graph. Use to find where a symbol is defined (where-is-X), to discover reusable code before writing new, and to check a symbol actually exists before calling it (anti-hallucination). Backed by `forge atlas`.
---

# atlas — the code-graph

A precomputed, portable symbol index at `.forge/atlas.json`. Any tool reads it via
`forge atlas` or plain `jq` — no MCP required to consume.

## Use it
- `forge atlas build` — (re)build the index for this repo. Cheap; run once, and
  again after large changes.
- `forge atlas query <term>` — where is `<term>` defined? Returns file:line + kind.
  Prefer this over grep-and-read-files (far fewer tokens).
- `forge atlas has <symbol>` — is this symbol defined anywhere? Use before calling
  an unfamiliar function/class: "not found" is a strong hallucinated-API signal.

## When
- Reuse-first: before writing a helper, `forge atlas query` for an existing one.
- Verification: after generating code that calls project symbols, spot-check the
  unfamiliar ones with `forge atlas has`.

## Honest boundary
v1 indexes symbol *definitions* + membership, not a full call graph ("what calls
Z"). It flags likely-missing symbols; it does not certify correctness. The call
graph is the documented upgrade (LSP / serena-backed export).

Attribution

CodeWithJuberCodeWithJuber
View sourceMore from CodeWithJuber →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →