claude-code · prathamdby — Claude Code skill: setup and CLI runs
This Claude Code skill runs the local CLI with selected options and checks the result. It also handles requests to change installation, sign-in, or connected tools.
MIT 329 installs ★ 6 updated 2026-11-10
npx skills add prathamdby/skills --skill claude-code -a claude-codeWhat claude-code does
The skill resolves the working directory, run mode, session details, and wait limit, then starts claude and inspects the project status and diff. It runs focused tests for edited executable code.
Requests can select plan mode, the interactive interface, a model, session continuation, a worktree, or JSON output. The skill builds the matching CLI arguments and uses supporting references for these modes. If the binary is missing, it follows the installation guide. Missing authentication blocks a run unless signing in was requested.
A standard run skips permission prompts, but CLI output alone does not confirm a change: the project tree is inspected. A failed command ends as BLOCKED; when the wait limit expires, only that run's process is stopped. Plan mode must leave the tree unchanged.
What it helps with
- run Claude Code from the intended workspace
- switch the CLI to plan or interactive mode
- resume an existing session by ID
- run a task in a separate worktree
- check project changes and tests after a CLI run
Example prompts for the agent
- Run Claude Code in plan mode and draft changes for
src/. - Resume session
abc123and inspect the diff when it finishes. - Run the task in worktree
fix-loginusing modelsonnet.
How to install claude-code
1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill claude-code -a claude-code2Manually: put the files in place
~/.claude/skills/claude-code/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/claude-code/
1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill claude-code -a codex2Manually: put the files in place
.agents/skills/claude-code/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill claude-code -a cursor2Manually: put the files in place
.cursor/skills/claude-code/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install prathamdby/skills skills/engineering/claude-code2Manually: put the files in place
.github/skills/claude-code/SKILL.md1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill claude-code -a gemini-cli2Platform CLI
gemini skills install https://github.com/prathamdby/skills --path skills/engineering/claude-codeManually: put the files in place
.devin/skills/claude-code/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add prathamdby/skills --skill claude-code -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about claude-code
How do I install claude-code in Claude Code?
Run npx skills add prathamdby/skills --skill claude-code -a claude-code. The skill file is at ~/.claude/skills/claude-code/SKILL.md.
What does the claude-code skill do?
It controls local Claude Code CLI runs: sets options and session mode, starts the command, then checks the project state and outcome.
What happens if Claude Code is not authenticated?
The skill blocks the run unless you asked it to sign in. It checks authentication with claude auth status --text.
Source text
SKILL.md · MIT
--- name: claude-code description: > When the user wants the local Claude Code CLI run or its installation, login, or connected tools changed. --- # Claude Code ## Options and boundaries Default: `claude --print --dangerously-skip-permissions --output-format text "<prompt>"` from the target directory; model omitted; parent wait 15m. Calling this skill authorizes that run: pass `--dangerously-skip-permissions` without asking. There is no `--yolo` flag; this skip is the yolo run. Print alone can write. "Read-only" / "plan" uses `--permission-mode plan` and omits the skip flag. "Use <model>" adds `--model`. "Interactive" / "TUI" omits `--print` and the skip flag. "Resume <id>" adds `--resume`; "continue" adds `--continue`; both wait until exit and keep the same permission choice as the selected mode. "Worktree [name]" adds `--worktree [name]`; record the emitted path. "JSON" / "stream-json" selects that print output. Missing needed values or conflicting options are `BLOCKED`. For plan, restricted, or another named permission mode, follow `references/permissions.md`. A default run does not stop for a permission prompt. `claude help` starts a session: use `claude --help`. `remote-control` is not documentation. ## 1. Resolve Fix absolute workspace, prompt, mode, session, worktree, output, and wait. Check binary and `claude auth status --text` without exposing secrets. Missing binary → follow `references/install.md`; missing auth → `BLOCKED` unless login was requested. Wrong cwd blocks. Record `cmd | workspace | mode | session | worktree | wait | evidence | terminal`. Done when target, binary, auth, and the permission choice are fixed. ## 2. Run Build argv from those options and quote the prompt literally. Default text is quiet until process exit; silence is not a hang. Wait for exit or the recorded deadline, and kill only this run's PID when that deadline expires. Nonzero exit: capture stderr, inspect the tree, and report `BLOCKED`. Do not ask the user and do not add a second bypass. For JSON/stream output, follow `references/streaming.md`. For resume, continue, or background sessions, follow `references/sessions.md`. For worktrees or parallel runs, follow `references/worktrees.md`. For an asked-for TUI or management command, follow `references/management.md`. A rejected flag requires scoped `--help`, not a guessed replacement. Done when the process exits, an intended live handle is recorded, or a failure is reported. ## 3. Verify and report Inspect status and diff; CLI text is not proof. Run the narrowest covering tests for edited executable code. Plan mode must leave the tree unchanged. Verify each worktree and any integrated tree. Clean up only this run's sessions/worktrees unless explicitly kept; preserve auth, MCP, and plugins. Report command, mode, session/worktree, wait, and outcome evidence. Done when every requested outcome is observed or a blocker is evidenced. Terminals: `SUCCESS`, `NO_CHANGES`, `BLOCKED`.
© prathamdby · MIT · prathamdby/skills
Similar skills
All skills for Agent setup: memory, context, orchestration →claude-code by other authors comes first.