configure-repo
Repo onboarding driver: .claude/ directory, SessionStart hook, install_pkgs.sh. Use when onboarding any repo to Claude Code with the claude-plugins marketplace.
What this skill does
# /configure:repo End-to-end driver that brings any repo's Claude Code configuration to a healthy baseline in one command. Produces committed-ready files: `.claude/settings.json` (permissions + marketplace enrollment), a `SessionStart` hook, and `scripts/install_pkgs.sh`. ## When to Use This Skill | Use this skill when... | Use another approach when... | |------------------------|------------------------------| | Onboarding a new repo to Claude Code from scratch | Changing a single setting — use `/configure:claude-plugins` or `/configure:web-session` directly | | Updating an existing repo to the latest baseline config | Diagnosing a specific hook or plugin issue — use `/health:check` directly | | Checking what would change before committing | Running a health-only audit — use `/health:check` | | Setting up a repo for ephemeral web sessions (claude.ai/code) | Managing plugins on an already-configured repo | ## Context Detect current state and project stack: - Existing settings: !`find .claude -maxdepth 1 -name 'settings.json' -type f` - Install script: !`find . -name 'install_pkgs.sh' -path '*/scripts/*'` - Workflows: !`find .github/workflows -maxdepth 1 -name 'claude*.yml'` - Project files: !`find . -maxdepth 1 \( -name 'package.json' -o -name 'pyproject.toml' -o -name 'Cargo.toml' -o -name 'go.mod' -o -name 'justfile' -o -name 'Justfile' \)` - ESP indicators: !`find . -maxdepth 2 \( -name 'idf_component.yml' -o -name 'sdkconfig' \)` - Pre-commit config: !`find . -maxdepth 1 -name '.pre-commit-config.yaml'` - Git remote: !`git remote -v` ## Parameters | Parameter | Description | |-----------|-------------| | `--check-only` | Report what would change without modifying any files | | `--skip-health` | Skip the final `/health:check` validation step | | `--skip-migrations` | Skip migration detection (don't offer mypy→ty etc.) | ## Execution Execute this end-to-end repository configuration workflow: ### Step 1: Detect project stack Identify the stack from the context above. Produce a brief summary: ``` Stack detected: Language: Python (uv + ruff) | Node/TypeScript | Rust | Go | ESP-IDF | ESPHome | ... Tools: pre-commit, just, docker, ... Migrations: mypy→ty candidate | black→ruff-format candidate | flake8→ruff candidate | ESLint→Biome candidate ``` If `--check-only`, annotate all subsequent steps as "(would do)" rather than doing them. ### Step 2: Configure plugins, permissions, and marketplace enrollment Invoke `/configure:claude-plugins --fix` using the SlashCommand tool. This step: - Selects recommended plugins based on detected stack - Writes `permissions.allow` (common + stack-aware) to `.claude/settings.json` - Writes `extraKnownMarketplaces` + `enabledPlugins` to `.claude/settings.json` (critical for web sessions) - Creates/updates `.github/workflows/claude.yml` and `claude-code-review.yml` ### Step 3: Configure SessionStart hook and install script Invoke `/configure:web-session --fix` using the SlashCommand tool. This step generates `scripts/install_pkgs.sh` with idempotent tool installs gated on `CLAUDE_CODE_REMOTE=true`, and wires the `SessionStart` hook in `.claude/settings.json`. If the project uses language-level deps (Python, Node, Rust, Go), also invoke `/hooks:session-start-hook --remote-only` using the SlashCommand tool to add dependency installation to the hook script. ### Step 4: Offer migrations (unless --skip-migrations) Detect these migratable patterns and ask whether to run each migration via `AskUserQuestion`: | Pattern detected | Migration to offer | Skill to invoke | |------------------|--------------------|-----------------| | `.pre-commit-config.yaml` contains `mirrors-mypy` or `[tool.mypy]` in pyproject.toml | mypy → ty | `/migration-patterns:mypy-to-ty` | | `.pre-commit-config.yaml` contains `psf/black` | black → ruff-format | `/migration-patterns:black-to-ruff-format` | | `.pre-commit-config.yaml` contains `pycqa/flake8` or `PyCQA/isort` | flake8/isort → ruff | `/migration-patterns:flake8-to-ruff` | | `.eslintrc*` or `eslint.config.*` present, no `biome.json` | ESLint → Biome | `/migration-patterns:eslint-to-biome` | For each detected pattern, ask: "Found [pattern] — offer to migrate? (y/n)". Only run the migration skill if the user confirms. Migrations are **not** part of the happy path. If the user declines all migrations, continue to Step 5. ### Step 5: Validate with health check (unless --skip-health) Invoke `/health:check` using the SlashCommand tool. Parse the health check output. If any checks fail: - Report the specific failures - Suggest how to fix them - Continue (do not abort — the config files are still staged) ### Step 6: Stage files and report Run `git status` to list all created/modified files. Stage the relevant files: ```bash git add .claude/settings.json git add scripts/install_pkgs.sh # if created git add .github/workflows/claude.yml # if created git add .github/workflows/claude-code-review.yml # if created ``` Print a summary: ``` configure-repo complete ======================= Repository: <repo-name> Files staged: .claude/settings.json [CREATED | UPDATED] scripts/install_pkgs.sh [CREATED | UPDATED | SKIPPED] .github/workflows/claude.yml [CREATED | UPDATED | SKIPPED] .github/workflows/claude-code-review.yml [CREATED | UPDATED | SKIPPED] Marketplace enrollment: .claude/settings.json → extraKnownMarketplaces.claude-plugins ✓ .github/workflows/claude.yml → plugin_marketplaces ✓ Health check: PASS | WARN (<N> warnings) | FAIL (<N> failures) Next steps: 1. Review the staged diff: git diff --cached 2. Commit: git commit -m "chore(claude): configure repo for Claude Code" 3. Add CLAUDE_CODE_OAUTH_TOKEN to repository secrets 4. Push and test: mention @claude in a PR comment ``` If `--check-only` was set, prefix the summary with "DRY RUN — no files modified". ## Important Notes - This skill is a thin orchestrator — it contains no business logic. All logic lives in its dependencies. - Never auto-commit; always stage and let the user review with `git diff --cached`. - `AskUserQuestion` is required for migration offers — this skill must not run on `haiku` model. - `extraKnownMarketplaces` in `.claude/settings.json` is the key to surviving ephemeral web sessions. - The SessionStart hook uses `CLAUDE_CODE_REMOTE` guard so it is a no-op in local sessions. ## Agentic Optimizations | Context | Command | |---------|---------| | Full setup with health check | `/configure:repo` | | Dry-run, no file changes | `/configure:repo --check-only` | | Setup without migration prompts | `/configure:repo --skip-migrations` | | Quick setup, skip health | `/configure:repo --skip-health --skip-migrations` | | Stage and review | `git diff --cached` | ## Dependencies (driver freshness) This skill orchestrates these dependencies. If any dependency's `modified:` date is newer than this skill's `reviewed:` date, run `scripts/check-driver-freshness.sh` and update this skill accordingly. | Dependency | File | |------------|------| | `/configure:claude-plugins` | `configure-plugin/skills/configure-claude-plugins/SKILL.md` | | `/configure:web-session` | `configure-plugin/skills/configure-web-session/SKILL.md` | | `/hooks:session-start-hook` | `hooks-plugin/skills/hooks-session-start-hook/SKILL.md` | | `/health:check` | `health-plugin/skills/health-check/SKILL.md` | | `/migration-patterns:mypy-to-ty` | `migration-patterns-plugin/skills/mypy-to-ty/SKILL.md` | | `/migration-patterns:black-to-ruff-format` | `migration-patterns-plugin/skills/black-to-ruff-format/SKILL.md` | | `/migration-patterns:flake8-to-ruff` | `migration-patterns-plugin/skills/flake8-to-ruff/SKILL.md` | | `/migration-patterns:eslint-to-biome` | `migration-patterns-plugin/skills/eslint-to-biome/SKILL.md` | ## See Also - `/configure:claude-plugins` — Configure plugins, permissions, and marketplace enrollment - `/configure:web-session` — SessionStart hook
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.