mcp
25brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Manage MCP (Model Context Protocol) servers β list configured tools, check status, show invocation format, or add a new server to .claude/settings.json.
π§ Give Claude Code the operating context it's missing: persistent rules, enforced hooks, on-demand skills and deep knowledge of your codebase.
This repository also configures its own agents. See what claude-code-brain-bootstrap tells them β
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Manage MCP (Model Context Protocol) servers β list configured tools, check status, show invocation format, or add a new server to .claude/settings.json.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Run database or schema migrations β up, down, rollback, status, or create a new migration. Reads claude/build.md for migration commands.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Generate a PR/MR description after the review passes. Use after /review confirms the code is ready to merge. Reads claude/templates.md for the required format.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Plan a non-trivial task before implementing. Use when the task requires 3+ steps, multiple files, or an architectural decision. Writes a checkable plan to claude/tasks/todo.md.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Browser automation β navigate, click, fill, snapshot web pages. Use for UI testing, documentation scraping, OAuth flows, web research.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
PR triage β audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "fr" for French output, no arg = audit only in English.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Use when receiving code review feedback β before implementing suggestions, especially if feedback seems unclear or technically questionable.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Generate a comprehensive repo recap (PRs, issues, releases) ready to share with the team. Pass "fr" for French output (default is English).
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Isolated codebase exploration that preserves your main context. Use when you need to understand code structure, trace call paths, or gather evidence before making changes. Spawns an explorer subagent.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Resume a previous session from claude/tasks/todo.md. Use at the start of a new session to restore context and continue where you left off.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Full 10-point expert code review. Use before any PR or MR. Checks correctness, cross-layer consistency, transaction safety, test coverage, and security. Spawns reviewer subagent for isolation.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Use when errors occur deep in execution and you need to trace back to the original trigger. Applies 5-step investigation β observe, hypothesize, trace backwards, binary search, prove.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Use when renaming symbols across files, finding all references to a function/class, moving code between files, or inlining variables β LSP-backed atomic multi-file refactoring.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Start service(s) locally for development. Accepts a service name, all, frontend, or backend. Reads claude/build.md for the actual start commands.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Generate a parallel workstream plan for multi-agent Claude Code work. Decomposes a feature into independent workstreams, each ownable by a separate Claude Code instance. Saves to claude/tasks/ACTIONPLAN.md.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Project status dashboard β CLAUDE.md budget, unfilled placeholders, lessons file size, hooks executability, jq availability, plugin states. One-glance health report.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Use when executing implementation plans with independent tasks β dispatches fresh subagents per task with two-stage review (spec compliance, then code quality).
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Fire when creating or modifying test files. Enforces write-test-first discipline and correct framework selection per project layer.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Create a ticket/issue description with evidence-backed proof sections. Reads claude/templates.md for the template format. Saves to claude/tasks/ticket- .md.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Scan codebase exports and generate CODEINDEX.md organized by capability. Check this index before writing new functions to prevent duplication (no more formatDate2 when formatDate exists).
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Show all active git worktrees with branch name, dirty/clean status, and last commit. Use after /worktree to check state across all parallel branches.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code needs its repo
Manage git worktrees for parallel work on multiple branches simultaneously. Use when you need to work on two features at once without stashing or branch-switching.
brain-bootstrap/claude-code-brain-bootstrap
Skill Claude Code
Use when creating new skill files, editing existing SKILL.md files, or reviewing skills before deployment β covers structure, CSO (discoverability), and quality standards.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page β the rest are on their repository pages: