agent-skills

Aggressive token-efficiency mode. Stays in telegraph form by default — fragments, no articles, no preamble — and only breaks pattern for code, errors, and destructive operations needing confirmation. Built for users who are domain experts and want answers, not tutorials. Use when the user says 'caveman', 'terse', 'kurz', 'kurz&knapp', 'kurz bitte', 'weniger text', 'less tokens', 'smart mode', or invokes /caveman-smart. Stays active across the session — never auto-exits — until the user says 'normal mode', 'verbose', or 'ausführlich'.

Orchestrates claude-mem persistent memory for maximum session context. Use at conversation start to load relevant past work, when the user says 'what did we do last time', 'load context', 'recall', 'remember', 'search memory', 'what do you know about this project', or when starting work on a project that has prior sessions. Also use when the user wants to save important decisions, search past sessions, or generate project history reports.

Orchestrates end-to-end software development using the addyosmani/agent-skills framework. Guides the user through define → plan → build → verify → review → ship phases, spawns subagents for each step, tracks state persistently, and never loses focus on workflow completion. Use when the user says "let's build X", "help me implement X", "walk me through X", or wants structured multi-phase dev guidance. Also triggers when a task is clearly non-trivial and would benefit from phased execution.

Orchestrates and advises on Gepetto planning sessions. Use when the user wants to plan a feature thoroughly before coding, asks 'should I use Gepetto for this?', wants to create a spec file for Gepetto, or is unsure what to do with Gepetto's output. Helps assess whether Gepetto's full 17-step pipeline is worth the investment, drafts the spec file, guides the user through the workflow, and advises on how to execute the resulting plan (manual, ralph-loop, or Ralphy CLI). Keeps context short — Gepetto itself handles the heavy lifting via subagents.

Orchestrates and advises on complete GSD (Get Shit Done) development workflows. Acts as both workflow driver and expert consultant — reads context, suggests the right tools, asks clarifying questions when intent is unclear, spawns subagents for each step, and never loses focus on workflow completion. Use when the user wants to build something, asks which GSD command to use, says 'help me with GSD', 'run the GSD workflow', 'let's start a project', 'what should I do next', or describes any dev task that might benefit from structured planning. Also triggers when the task scope is ambiguous and needs routing to fast/quick/full GSD flow.

Installs Claude Code plugins from GitHub repos that lack a marketplace manifest. Use this skill whenever a `claude plugin install` fails due to SSH key errors, missing `.claude-plugin/marketplace.json`, or a GitHub repo that wasn't designed as a Claude plugin marketplace. Also use when the user says "install plugin from GitHub", "add skills from a repo", or "the plugin install failed". Handles the full workflow: cloning via gh CLI, inspecting repo structure, generating the marketplace manifest, and running the install.

Orchestrates and advises on Ralph Loop automated development sessions. Use when the user wants to run ralph-loop, asks how to set up a Ralph task, wants iterative agent-driven development, says 'run this in a loop until it works', or has a task with testable acceptance criteria they want to automate. Helps write effective loop prompts, sets safe iteration limits, monitors loop progress, detects stuck loops, and advises on completion criteria. Keeps context short — the heavy work happens inside the loop.

Advises on multi-agent swarm design using Claude Code's TeammateTool and Task system. Use when the user wants to parallelize work across agents, asks 'should I use a swarm for this?', wants help designing team topology, needs to break a task into parallel workstreams, or is getting started with swarm-orchestration. Assesses whether a swarm is worth the overhead, recommends team size and structure, helps decompose tasks with correct dependencies, and tracks swarm health. Complements the swarm-orchestration skill by adding the 'think before you spawn' layer.

Diagnose and repair 'invalid high surrogate' API errors in Claude Code chat sessions. Use this skill when the user encounters API Error 400 with 'invalid high surrogate in string', 'not valid JSON', surrogate-related errors, or wants to fix/scan/repair a broken Claude Code JSONL chat file. Also use when a session refuses to resume due to JSON encoding errors, or when the user mentions request IDs (req_...) alongside JSON parse failures.