gh-tooling-setting-up
Use this skill when the user just installed the gh-tooling plugin and needs to configure it, asks "help me set up gh-tooling" or for guidance on configuring GitHub tooling for this session, or when gh-tooling MCP tools fail with authentication or missing-repo errors. Verifies the gh CLI is installed and authenticated, checks that jq is available, and optionally creates .mcp-gh-tooling.json to set a default repository, enable the write server, and configure label definitions.
What this skill does
# Plugin Setup
Interactive setup assistant. Read references/plugin-setup.md for all plugin-specific details including prerequisites, configuration files, validation steps, and post-setup instructions.
## Workflow
### Phase 1: Detect Current State
Read the plugin setup guide reference file. It contains all plugin-specific information organized in standard sections.
For each prerequisite listed under `## Prerequisites`:
1. Run its check command (the **Check** field) via Bash
2. Record the result: installed (with version) or missing
For each config file listed under `## Configuration Files`:
1. Check if it exists at the specified location using Glob
2. Record the result: exists or missing
Report findings to the user:
- Installed prerequisites with versions
- Missing prerequisites (distinguish required vs optional)
- Existing config files
- Missing config files
If everything is already configured, skip to Phase 5 (Configure Permissions) — permissions are always offered.
### Phase 2: Fix Prerequisites
For each missing prerequisite:
1. Tell the user what is missing, what requires it (the **Required by** field), and provide the install link
2. If the prerequisite is marked as optional, ask via AskUserQuestion whether they want to install it. Skip if they decline.
3. For required prerequisites, tell the user to install it and ask them to confirm when done
4. After confirmation, re-run the check command to verify
If a required prerequisite cannot be installed, stop and explain which config files and features depend on it. Do not proceed to Phase 3 for config files that depend on missing prerequisites.
### Phase 3: Create Config Files
For each config file from the guide that does not exist:
1. If the file is marked `Required: No`, ask via AskUserQuestion whether the user wants to configure it. Skip if they decline.
2. Read the **Setup Questions** section for this config file
3. Ask each question one at a time via AskUserQuestion, presenting the options and descriptions exactly as written in the guide
4. Skip conditional questions when their condition is not met (conditions are noted in parentheses, e.g., "only if environment = docker")
5. Build the config JSON object from the answers
6. Present the complete config to the user and ask for confirmation
7. Write the file to the specified location using Write
### Phase 4: Plugin Scope Setup (optional)
Read the `## Plugin Scope Setup` section of the guide and walk the dialogue. Skip this phase entirely if the user answers No to the gate question.
### Phase 5: Configure Permissions
Pre-approve the plugin's tools in `.claude/settings.local.json` so the user is not prompted on first use. Read the `## Permission Groups` section of the guide. Each group bundles related tools behind a single question — never ask per individual tool.
1. Check whether `.claude/settings.local.json` exists at the project root. If present, read it with Read. Otherwise treat the starting state as `{"permissions": {"allow": [], "ask": [], "deny": []}}`.
2. For each group listed in the guide:
- Skip the group if its **Optional** condition is not met (e.g., the related config file was not created, or a dependent feature like `enable_write_server` is disabled).
- Skip the group silently if every pattern in it is already present in any of the `allow`, `ask`, or `deny` lists.
- Otherwise ask via AskUserQuestion, using the group's name and description. Offer three options — `allow`, `ask`, `deny` — with the group's **Recommended** value as the default.
3. Merge the answers into the settings:
- Append each selected pattern to the chosen list.
- Deduplicate: never add a pattern that already exists anywhere in `allow`, `ask`, or `deny`.
- Never remove, reorder, or move existing entries between lists.
- Preserve every other key in the file verbatim.
4. Show the user the new entries that will be added (grouped by target list) and ask for confirmation. On confirmation, Write the updated file.
### Phase 6: Validate
Read the `## Validation` section of the guide. For each validation step:
1. Run the described check or MCP tool call
2. Report pass or fail
3. If a check fails, diagnose the likely cause and offer to fix it (e.g., wrong container name, container not running, missing PHP extension)
### Phase 7: Post-Setup
Read the `## Post-Setup` section of the guide. Report the remaining steps the user must take (e.g., restarting Claude Code to load MCP servers).
## Rules
- Ask one question at a time via AskUserQuestion. Never batch multiple questions.
- Skip phases and individual steps that are already satisfied (prerequisite installed, config file exists, permission pattern already in settings).
- Never proceed to config file creation if a required prerequisite it depends on is missing.
- Always show the user the complete config content before writing it.
- When updating `.claude/settings.local.json`, only append new entries. Never remove, reorder, or move existing permission entries between lists.
- If validation fails, attempt to diagnose the cause before giving up.
- Use the exact options, descriptions, defaults, and permission groups from the plugin setup guide. Do not improvise.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.