Loading...
Loading...
Found 39 Skills
Manage and generate .gitignore files using the official GitHub gitignore template library via the `ign` CLI. Use when initializing new project repositories, automatically detecting project stack from files, adding language/framework/IDE ignore rules, inspecting applied templates, or safely modifying existing .gitignore files.
Initialise a git repository with optional agent commit instructions and .gitignore. Use when users say "here be git", "init git", "initialise git", or otherwise indicate they want to set up version control in the current directory.
Use when creating temporary files, drafts, experiments, or any content that should not be committed to version control. Ensures proper placement in .claude/.scratch with gitignore configuration.
Põe no git e num GitHub privado um projeto que ainda não usa git, sem levar junto dado de cliente: confere a pasta (fora de iCloud/OneDrive/Dropbox/Google Drive), lista o que entraria no git sinalizando senha (.env), certificado A1 (.pfx), planilha e arquivo grande, propõe o .gitignore, oferece o alarme de commit da sdd-higiene-dado antes do primeiro commit e só commita e publica com o OK explícito de cada etapa. Fala com quem nunca usou git: uma etapa por vez, com o que foi feito, o que vem agora e as opções de cada decisão. Retoma de onde parou (git sem commit, commit sem GitHub, envio que falhou). Use quando o usuário disser 'pôr no git', 'criar o repositório', 'subir para o GitHub', 'este projeto não tem git', ou quando a sdd-new-session ou a sdd-checar-ambiente disserem que o projeto ainda não usa git. Não limpa histórico que já vazou, não faz login no GitHub pelo usuário e não automatiza outro host (GitLab etc.), só entrega os comandos.
Configure .gitattributes, .editorconfig, .gitignore, and Git LFS filters for a repository: normalize line endings, mark generated, vendored, and documentation paths for GitHub linguist, set per-language editor defaults, and merge .gitignore content from GitHub templates. Use when the user says "add .gitattributes", "fix line endings", "CRLF", "linguist", "mark generated files", "set up .editorconfig", "gitignore template", "git lfs", or invokes /repo-attributes. Do NOT use for prek or pre-commit hook configuration — use /prek. GitHub custom properties (organization-level metadata) are out of scope; this skill only touches per-repository attribute, editor, and ignore files. Community health files (README, LICENSE, CODE_OF_CONDUCT, CONTRIBUTING, SECURITY) belong to /oss-hygiene, not this skill.
Build an iOS / Apple app on remote Xcode with `lim xcode build` instead of local xcodebuild, from any environment (Linux, Windows, macOS, VM, container). Use for non-Bazel projects (an `.xcodeproj` / `.xcworkspace`, an XcodeGen `project.yml` with a gitignored project, React Native / Expo native build) when the user wants to build, compile, reload, produce a preview build, or ship a signed device IPA. To run, tap, screenshot, or otherwise interact with the result on a simulator, use limrun-ios-simulator. For Bazel workspaces, use limrun-xcode-bazel.
Pull AWS Security Agent findings (penetration tests and code reviews) and drive remediation. Use this whenever the user mentions Security Agent, security findings, pentest or penetration test results, code review findings, vulnerabilities found in their AWS account, "what did the security scan find", remediating or triaging security risks, or wants to start fixing reported vulnerabilities — even if they don't name the service explicitly. Trigger it for phrases like "get my security findings", "what vulnerabilities do we have", "let's fix the pentest results", or "triage the security report". The skill discovers scans, exports findings to a gitignored local directory (so sensitive exploit detail is never committed), produces a prioritized triage summary, and offers to start fixing the highest-risk issues.
Use when starting a new app or repo, or making an existing repo agent-ready (say "new app", "new repo", "create a project", "bootstrap this repo"). Sets up git, AGENTS.md + CLAUDE.md, .gitignore, and a per-repo Obsidian knowledge vault, offers the pinned default stack, accounts for deployment (preview + prod), then optionally pressure-tests scope (make-money) and locks in the domain language (grill-with-docs).
Enforce secure secrets management across all platforms. Never hardcode OAuth2 secrets, API keys, tokens, passwords, or credentials in source code. Store all secrets in .env files, load from environment variables, and ensure .env is gitignored. Use this skill when: (1) writing any code that uses API keys, OAuth2 client secrets, tokens, or credentials, (2) setting up authentication or third-party integrations, (3) creating new projects that need environment configuration, (4) reviewing code for security issues related to secrets, (5) configuring CI/CD pipelines or Docker deployments with secrets. Triggers: API key, OAuth, client secret, token, credentials, .env, environment variables, secret, password, authentication setup, third-party integration.
Git workflow standards, commit conventions, hooks, and pull request practices. Use this when users need guidance on Conventional Commits, Git hooks with Lefthook, pull request templates, .gitignore configuration, or Git workflow best practices for team collaboration.
Environment preflight checks and initialization. Probes and installs git, gh, node, vercel, firebase-tools, and gitleaks. Verifies .nvmrc, .gitignore, and Git Flow develop branch setup, and enforces the Secret Vault Policy.
Semantic code search using mgrep for efficient codebase exploration. This skill should be used when searching or exploring codebases with more than 30 non-gitignored files and/or nested directory structures. It provides natural language semantic search that complements traditional grep/ripgrep for finding features, understanding intent, and exploring unfamiliar code.