study

Deeply study the current project so you are ready to implement features.

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/banksy-said-hi-study

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Deeply study the current project so you are ready to implement features. Builds a mental model of stack, structure, architecture, conventions, recent activity, and past lessons. Use when the user types /study or at the start of work on an unfamiliar repo.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/study

What's inside

Skill name: study
Description: Deeply study the current project so you are ready to implement features. Builds a mental model of stack, structure, architecture, conventions, recent activity, and past lessons. Use when the user types /study or at the start of work on an unfamiliar repo.
License: MIT
Instructions: 23 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

Explore autonomously. Do not ask questions.

1. **Identity** — read README, CLAUDE.md/AGENTS.md, and the manifest (package.json, pyproject.toml, Cargo.toml, go.mod…). Name, purpose, stack.
2. **Structure** — top-level layout, entry points, config (.env.example, compose, CI).
3. **Architecture** — trace input → processing → output/storage. Modules, layers, external integrations.
4. **Core logic** — read entry points, core modules, shared utilities. Domain types and how features are wired (routing, events, state).
5. **Conventions** — naming, folder patterns, test runner and test locations, anything project-specific.
6. **Current state** — `git log --oneline -10`; TODO/FIXME in code.
7. **Past lessons** — only when this is the first substantial turn of the session: if `lessons/` exists, read every file. Treat lessons as hard facts; surface the ones relevant to upcoming work.

## Output

**Project:** name + one-line purpose
**Stack:** languages, frameworks, runtimes
**Architecture:** 2–4 sentences
**Key modules:** bullets, path + one line each
**Patterns to follow:** bullets
**Hot areas:** bullets from git log
**Ready to build:** confirm, or flag blockers/ambiguities

Depth of understanding over length of report.

From Banksy-said-hi/claude-skills, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Banksy-said-hi/claude-skills
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Banksy-said-hi

Cite this page

study skill. Agent Mart. https://agentmart.dev/skills/banksy-said-hi-study (last updated 2026-10-24)