install-github-plugin
Install GitHub Plugin
Overview
claude plugin install clones repos via SSH. If SSH auth isn't configured, or if the repo has no .claude-plugin/marketplace.json manifest, the install fails. This skill works around both problems.
Workflow
1. Clone the repo via gh CLI (bypasses SSH)
gh repo clone <owner>/<repo> "~/.claude/plugins/marketplaces/<marketplace-name>"
Use the same directory the marketplace manager would have used (check known_marketplaces.json if the marketplace was already added).
2. Check for an existing manifest
ls "~/.claude/plugins/marketplaces/<name>/.claude-plugin/"
If marketplace.json exists, skip to step 4.
3. Inspect the repo structure and generate manifest
Common layouts to look for:
skills/<skill-name>/SKILL.md— skill collectionagents/— agent personashooks/— session lifecycle hooks.claude/commands/— slash commands
Read one or two SKILL.md files to understand the content, then write .claude-plugin/marketplace.json:
{
"name": "<marketplace-name>",
"owner": { "name": "<author>", "email": "" },
"metadata": {
"description": "<one-line description>",
"version": "1.0.0"
},
"plugins": [
{
"name": "<plugin-name>",
"description": "<what the plugin does>",
"source": "./",
"strict": false,
"skills": [
"./skills/<skill-1>",
"./skills/<skill-2>"
]
}
]
}
List every skill directory under skills/ in the skills array.
4. Install the plugin
claude plugin install <plugin-name>@<marketplace-name>
5. Verify
claude plugin list
Confirm the plugin shows as ✔ enabled.
Notes
- If the marketplace was added via
claude plugin marketplace addbut the clone failed, the marketplace entry exists inknown_marketplaces.jsonbut the directory is empty or missing. Re-clone manually into theinstallLocationpath shown there. - Skills with only
SKILL.md(noplugin.json) are bundled via the marketplace manifest'sskillsarray — no per-skill plugin.json is needed. - After install, a Claude restart is required for new skills to appear in the available-skills list.
More from tebjan/agent-skills
caveman-smart
Intelligent token-efficiency mode. Compresses routine chat and thinking but stays in full prose for reasoning, architecture, and safety-critical topics. Applies per response, not per session. Use when the user says 'caveman', 'terse', 'kurz', 'kurz&knapp', 'kurz bitte', 'weniger text', 'less tokens', 'smart mode', or invokes /caveman-smart. Stays active until the user says 'normal mode', 'verbose', or 'ausführlich'. Built for HPC, real-time, graphics, embedded, and kernel work where technical precision matters more than word count but explanation-of-why still demands full prose.
2fix-jsonl-surrogates
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.
2swarm-advisor
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.
1gsd-orchestrator
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.
1ralph-orchestrator
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.
1claude-mem-orchestrator
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.
1