Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Getting Oriented

ASecurity

Learn an unfamiliar codebase before changing it — what it is, how it builds, how it is tested, what the house rules are. Use on your first runs in a workspace, or when you are handed a part of the repo you have never touched.

6 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentsgogit

Security Analysis

A100/100

Scanned 9/30/2026

$npx -y skills add mirzaaghazadeh/StandBye --skill getting-oriented --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Getting Oriented?

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

Security grade badge for Getting Oriented
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mirzaaghazadeh-getting-oriented/badge)](https://www.skillsdirectory.com/skills/mirzaaghazadeh-getting-oriented)

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

Download with Pro
Files
SKILL.md
---
name: getting-oriented
description: Learn an unfamiliar codebase before changing it — what it is, how it builds, how it is tested, what the house rules are. Use on your first runs in a workspace, or when you are handed a part of the repo you have never touched.
---

# Getting oriented

You are cheaper to the owner when you already know the repo. Spend one run learning it properly
and write down what you found, so nobody on the team pays for this again.

## What to read, in this order

1. `README.md` — what the project is and who it is for.
2. `CLAUDE.md`, `AGENTS.md`, `CONTRIBUTING.md` — the house rules. These override your habits.
3. The package manifest (`package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`) — the real
   commands. Read the `scripts` block rather than guessing that `npm test` exists.
4. The directory listing, two levels deep. Name the handful of folders that hold the actual work.
5. `git log --oneline -30` and `git log --stat -5` — what the team has been touching lately, and
   what a commit here looks like.
6. The CI config (`.github/workflows/`, `.gitlab-ci.yml`). Whatever it runs is the definition of
   "green", and the definition you must not break.

## Then prove it runs

Do not take the README's word for it. Run the install, the build, the typecheck and the test suite,
in that order, and note how long each takes and whether it actually passed. A README that lies is a
finding worth reporting — say so rather than quietly working around it.

If a step needs a credential or a service you do not have, stop there and record what was missing.
Do not invent a workaround and do not go looking for secrets.

## Write down what you learned

End the run by calling `remember` with the things that will be true tomorrow:

- the exact build, test, typecheck and lint commands, copied verbatim;
- where the code that matters lives, in one line per area;
- the conventions the repo actually follows (test framework, commit message shape, branch naming);
- anything that surprised you — a generated file, a step that must run before another, a test that
  is slow or flaky.

Keep it to facts a teammate could act on. "The build is complex" helps nobody; "`pnpm typecheck`
needs `pnpm --filter @crew/shared build` first" saves someone an hour.

If the same orientation would help every agent on the team, call `learn_skill` with
`scope: "team"` instead, and name it after the repo.

## What not to do

- Do not change anything on an orientation run. Reading is the whole job.
- Do not read the entire codebase file by file. Read what the entry points point at.
- Do not report a plan for improving the project. Nobody asked yet.

Attribution

mirzaaghazadehmirzaaghazadeh
View sourceSee grades on GitHubMore from mirzaaghazadeh →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, 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.

741 votes
View all in ai-agents →