Dek1Skills

Control shell, filesystem, MCP, browser, external APIs, and risky tools. Enforce read-only-before-write, least-privilege, and verification discipline. Trigger on /agent-tool-safety, or when using shell commands, file operations, MCP tools, browser automation, or external APIs.

Final sanity check on AI-generated code before merging. Run the checklist to catch common failure modes. Trigger on /ai-coding-agent-review, or before finalizing any significant AI-generated change.

Review API design — endpoints, types, contracts, error handling, versioning, and consistency. Trigger on /api-design, or when designing or reviewing API specifications.

Implement backend API endpoints — routing, middleware, input validation, error handling, authentication, rate limiting, file upload. Trigger on /api-implementation, or when building endpoints, adding middleware, handling file uploads, or implementing API security.

Record architecture decisions as ADRs — compare options, document trade-offs, and track rationale. Trigger on /architecture-decision, or when choosing libraries, designing modules, splitting systems, or making significant technical decisions.

Make the agent continue work without asking unnecessary questions. Enforce the ask-less policy from CLAUDE.md. Trigger on /ask-less-execution, or when the agent is asking too many clarifying questions instead of discovering answers.

Manage CI/CD pipelines, GitHub Actions, build scripts, changelog, and release workflows. Trigger on /ci-cd-release, or when editing workflows, releasing, fixing CI failures, or creating changelogs.

Review a pull request or diff with a structured checklist — security, error handling, edge cases, test coverage, and code quality. Trigger on /code-review, or when asked to review a PR, diff, or merge request.

Check cross-platform and cross-version compatibility — Windows/Linux/macOS, Node/Bun, ESM/CJS, path separators, shell commands. Trigger on /compatibility-check, or when writing cross-platform code, debugging platform-specific failures, or checking runtime compatibility.

Use Claude Code's computer control capabilities — browser automation, screenshots, UI interaction, and system automation. Trigger on /computer-use, or when automating browser tasks, UI testing, or visual verification.

Database schema changes, migrations, seed data, rollback plans, and data safety. Trigger on /db-migration, or when changing schema, writing migrations, seeding data, or planning rollbacks.

Force real debugging before fixing. Reproduce, trace the failing path, identify the first wrong state, explain root cause before editing. Trigger on /debug-root-cause, when a bug is reported, a test fails, or something is throwing/breaking.

Safe dependency upgrades — review changelogs, check breaking changes, update lockfile, verify compatibility. Trigger on /dependency-upgrade, or when upgrading packages, fixing vulnerabilities, or migrating library versions.

Create and manage Claude Code hooks — auto-trigger scripts on events like PreToolUse, PostToolUse, PreCommit, UserPromptSubmit, and more. Trigger on /hooks-automation, or when setting up automation workflows, pre-commit checks, tool guards, or session lifecycle hooks.

Handle active incidents — failing CI, production issues, runtime breakage, security alerts, agent failures. Stabilize first, diagnose second, fix third. Trigger on /incident-response, or when something is actively broken, CI is red, or emergency fixes are needed.

Use MCP (Model Context Protocol) servers to give Claude Code access to external tools, APIs, databases, and services. Trigger on /mcp-integration, or when setting up external tool connections.

Debug using logs, traces, metrics, and telemetry — runtime behavior analysis, structured logging, and production debugging. Trigger on /observability-debugging, or when debugging from logs, adding tracing, or investigating runtime behavior.

Identify performance bottlenecks — slow queries, N+1 problems, unnecessary work, memory issues, and optimization opportunities. Trigger on /perf-analysis, or when investigating slow code, high latency, or resource usage.

Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Trigger on /post-mortem, when asked for RCA/root cause analysis, or after a debug session lands a validated fix.

Plan and execute safe refactors — map dependencies, identify risks, break into steps, preserve behavior. Trigger on /refactor-plan, or when planning a refactor, restructuring, or migration.

Quickly map an unfamiliar repository — entrypoints, stack, package manager, conventions, architecture. Trigger on /repo-onboarding, or when entering a new repository, reviewing an unfamiliar codebase, or needing a project summary.

Review a plan, diff, PR, or completed change with outsider skepticism. Check code paths, verify behavior, look for edge cases and test gaps. Trigger on /scrutinize-change, or when asked to review/audit/sanity-check changes.

Scan code for security vulnerabilities — OWASP Top 10, credential leaks, injection attacks, path traversal, and insecure configurations. Trigger on /security-audit, or when reviewing code for security issues.

Configure Claude Code behavior via .claude/settings.json — hooks, MCP servers, custom commands, agents, and global options. Trigger on /settings-management, or when tuning Claude Code configuration.

Create a new Claude Code skill — research from web, write SKILL.md, register in plugin.json, add to README.md, create experience log. Trigger on /skill-creator, or when asked to create a new skill.

Delegate large work to subagents safely. Use for codebase mapping, bug tracing, security review, test gap analysis, performance review, and research. Trigger on /subagent-orchestrator, or when a task is too large for a single agent pass.

Analyze testing approach — what to test, how to test, coverage gaps, and test quality. Trigger on /test-strategy, or when planning tests, reviewing test gaps, or debugging flaky tests.

Design and review frontend UI components — props API, state management, loading/error/empty states, accessibility, performance. Trigger on /ui-component, or when building components, reviewing UI code, or debugging rendering issues.

Search multiple websites for techniques, solutions, or best practices — read, compare, synthesize, then test/validate in the actual project before concluding. Trigger on /web-research, or when exploring solutions, researching approaches, learning new techniques, or validating ideas from the web.

Break down complex tasks into actionable steps — define scope, identify dependencies, estimate effort, sequence work, and identify risks. Trigger on /work-plan, or when starting a complex task, planning a sprint, or breaking down ambiguous requirements.