claude-code-skills

37 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator (with semantic version bumper and hotfix/rollback procedures), API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker (task context tracker with lifecycle and handoff format), feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate (pre-production 8-category audit with deploy-intent intercept), slo-architect (SLO designer, error-budget calculator with multi-window burn-rate alerts, SLO reviewer per Google SRE Workbook), and tech-debt-tracker. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

32 production-ready engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright, self-improving agent, security suite (adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection), Stripe integration, TDD guide, Google Workspace CLI, a11y audit, Snowflake development, and more. v2.8.1 augments senior-fullstack / senior-frontend / senior-backend with karpathy-coder + Matt Pocock discipline: each ships a 7-question forcing-question library, 4 customization profiles (JSON, swappable), a deterministic decision engine, a composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) invokable by other agents via /cs:fullstack-review, /cs:frontend-review, /cs:backend-review, /cs:engineer-grill. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

Production-grade Playwright testing toolkit. Generate tests from specs, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55+ ready-to-use templates, 3 specialized agents, smart reporting that plugs into your existing workflow.

Self-Improving Agent: curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills. Provides /si:review, /si:promote, /si:extract, /si:status, and /si:remember slash commands.

Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).

Google Workspace administration via the gws CLI (github.com/googleworkspace/cli, install: npm i -g @googleworkspace/cli). Authenticate and automate Gmail, Drive, Sheets, Calendar, Docs, Chat, and Tasks. 5 Python tools, 3 reference guides, a local catalog of 43 recipe command templates, and 10 persona bundles. Verify generated commands against gws --help.

Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.

WCAG 2.2 accessibility audit and fix skill for React, Next.js, Vue, Angular, Svelte, and HTML. Static scanner detecting 20+ violation types, contrast checker with suggest mode, framework-specific fix patterns, CI-friendly exit codes.

Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening. Covers build performance, layer caching, and production-ready container patterns.

Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing.

Terraform infrastructure-as-code agent skill and plugin for module design patterns, state management strategies, provider configuration, security hardening, and CI/CD plan/apply workflows. Covers mono-repo vs multi-repo, workspaces, policy-as-code, and drift detection.

Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Supports 10 developer personas (vibecoder, new joiner, architect, security reviewer, etc.), all CodeTour step types, and SMIG description formula.

Create polished demo videos from screenshots and scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts to produce product walkthroughs, feature showcases, and marketing teasers with story structure, scene design system, and narration guidance.

Audit datasets for completeness, consistency, accuracy, and validity. 3 stdlib-only Python tools: data profiler with DQS scoring, missing value analyzer with MCAR/MAR/MNAR classification, and multi-method outlier detector.

Hypothesis testing, A/B experiment analysis, sample size calculation, and confidence intervals. 3 stdlib-only Python tools with Z-test, t-test, chi-square, effect sizes, power analysis, and Wilson score intervals.

Turn Claude Code + Obsidian into a second brain. The LLM incrementally ingests sources into a persistent, interlinked markdown wiki — building entity/concept/source pages, flagging contradictions, maintaining an index and log. Knowledge compounds instead of being re-derived by RAG on every query. Inspired by Karpathy's LLM Wiki gist. Ships SKILL, 3 sub-agents, 5 slash commands, 8 Python tools (stdlib only), full vault templates, and cross-tool compatibility (Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, Gemini CLI).

Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.

End-to-end feature-flag discipline: classify, ship, ramp, retire. Detects stale flags as debt, generates phased rollout plans (ring/linear/log/cohort), and audits every flag for a documented kill switch. 3 stdlib Python tools, 4 references on flag taxonomy + provider trade-offs (LaunchDarkly/GrowthBook/Statsig/Unleash/Flipt/DIY) + rollout strategies + lifecycle. /flag-cleanup slash command. Cross-tool compatible.

End-to-end Kubernetes Operator discipline: CRD design, reconcile-loop patterns, and OperatorHub Capability Levels. Ships CRD validator, reconcile-loop linter, and capability auditor (3 stdlib Python tools), 4 references on the operator pattern + CRD design + reconcile patterns + framework comparison (controller-runtime/kubebuilder/operator-sdk/metacontroller/KOPF), CRD + Go controller skeletons, and /operator-audit slash command. NOT a generic k8s skill — specifically the Operator pattern.

End-to-end chaos engineering discipline: design experiments with hypothesis + steady-state metric + blast radius + abort criteria, calculate risk score against error budget, and generate blameless postmortems. 3 stdlib Python tools (experiment_designer, blast_radius_calculator, experiment_postmortem), 4 references on chaos principles + experiment design + 7-attack taxonomy + tooling landscape (Chaos Toolkit/Mesh/Litmus/Gremlin/AWS FIS/DIY), templates for plans + postmortems, and a /chaos-experiment slash command. Composes with feature-flags-architect (kill switches as abort triggers) and kubernetes-operator (chaos targets).

End-to-end SLO/SLI/error-budget discipline per Google SRE Workbook. Ships SLO designer (refuses to render without required fields), error-budget calculator with multi-window burn-rate alert thresholds (PromQL-shaped), and SLO reviewer that catches the 7 common bugs (target too high, window too short, no SLI definition, CPU-as-SLI, etc.). 4 references on principles + SLI design + error budget math + composition with feature-flags-architect/chaos-engineering/kubernetes-operator. Asset templates for SLO YAML and error budget policy. /slo-design slash command. NOT a generic observability skill.

Skill-author skill: create new agent skills with proper structure, progressive disclosure, and bundled resources. Enhanced from Matt Pocock's MIT-licensed write-a-skill (https://github.com/mattpocock/skills) with: (1) stdlib Python validation tools (description validator, structure validator, review-checklist runner), (2) 3 reference docs citing 5+ authoritative sources each (progressive disclosure principles, description design patterns, quality gates), (3) cs-skill-author persona agent + /cs:write-a-skill slash command. Matt's voice and 3-phase workflow (Gather → Draft → Review) preserved verbatim per his MIT license. Use when user wants to create, write, build, or author a new agent skill.

Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing the pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (full API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs:workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Enhanced from Matt Pocock's MIT-licensed caveman skill (https://github.com/mattpocock/skills) with: (1) stdlib Python tools (text compressor, token-savings estimator, caveman-style linter), (2) 3 reference docs citing 5+ authoritative sources each (compression principles, technical communication patterns, when caveman backfires), (3) cs-caveman-mode persona agent + /cs:caveman slash command. Matt's voice and persistence rules preserved verbatim per MIT. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Relentless plan-and-design interrogator. Walks the decision tree of a plan one branch at a time, asking forcing questions sequentially with recommended answers. Explores codebase to resolve answers where possible. Enhanced from Matt Pocock's MIT-licensed grill-me skill (https://github.com/mattpocock/skills) with: (1) stdlib Python tools (decision-tree extractor, question generator, session-state tracker), (2) 3 reference docs citing 5+ authoritative sources each (forcing-question patterns, decision-tree completeness, when to stop grilling), (3) cs-grill-master persona agent + /cs:grill-me slash command. Matt's relentless one-at-a-time interview discipline preserved verbatim per MIT. Use when user wants to stress-test a plan, get grilled on their design, or says "grill me".

Conversation-handoff document generator. Compacts the current conversation into a markdown handoff so a fresh agent can continue. References existing artifacts (PRDs, plans, ADRs, issues, commits) by path/URL — does not duplicate them. Enhanced from Matt Pocock's MIT-licensed handoff skill (https://github.com/mattpocock/skills) with: (1) stdlib Python tools (template generator, artifact deduplicator, skill recommender), (2) 3 reference docs citing 5+ authoritative sources each (handoff structure, deduplication discipline, next-session skill matching), (3) cs-handoff-author persona agent + /cs:handoff slash command. Matt's no-duplication discipline preserved verbatim per MIT. Use when user wants to hand off the current conversation to a fresh agent or starts a new session that picks up prior work.

PreToolUse security reminder hook for Claude Code. Catches 12 common security anti-patterns in Edit/Write/MultiEdit operations BEFORE they happen — command injection (exec, os.system, subprocess shell=True), XSS (innerHTML, dangerouslySetInnerHTML, document.write), SQL injection (f-string queries, .format), unsafe deserialization (pickle, yaml.unsafe_load), code injection (eval, new Function), and GitHub Actions workflow injection. Session-state caching prevents duplicate warnings; 30-day auto-cleanup of stale state files. Disable per-session with ENABLE_SECURITY_REMINDER=0. Ported from David Dworken's MIT-licensed plugin at github.com/alirezarezvani/aeo-box.

A universal scraping skill with intelligent routing, token budget tracking, and quota awareness. Supports Firecrawl and local Python extraction (firecrawl, pandas, requests, beautifulsoup4). Free-tier compatible, BYOK.

Snowflake SQL, data pipelines (Dynamic Tables, Streams+Tasks), Cortex AI functions, Snowpark Python, and dbt integration. Includes query helper script, 3 reference guides, and troubleshooting.

Self-Mirror consciousness loop for human-like AI responses. Adds inner dialogue (Self → Mirror → Conscious Response) to make AI output feel authentic, not robotic. Zero dependencies — pure prompt technique.

Personal Claude power-user coach. On first activation, delivers a personalized, ranked cheat-code glossary filtered to the user's use cases. On every subsequent turn, scans for missed power-user opportunities and surfaces at most ONE ⚡ tip when a tip would genuinely 10x the next attempt. Silence is the default. Ships SKILL.md, cheat-codes glossary, coaching-rules decision tree, and three stdlib Python tools (cheat-code filter, prompt rater, 5-gate tip classifier). Includes cs-claude-coach agent persona and /cs:claude-coach slash command.

Docs-anchored grilling session — interrogates a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/), updating those files inline as terminology and decisions crystallise. Derived from Matt Pocock's MIT-licensed grill-with-docs skill (https://github.com/mattpocock/skills) with: (1) 3 stdlib Python tools (CONTEXT.md linter, ADR scanner, glossary-to-code consistency check), (2) 3 reference docs each citing 7+ authoritative sources on ubiquitous language, ADR practice, and CONTEXT.md as a living artifact, (3) cs-grill-with-docs persona agent + /cs:grill-with-docs slash command. Matt's interview discipline + domain-awareness rules + ADR-when-3-criteria-are-met gate preserved verbatim per MIT.

Use when you need to reduce LLM API spend, control token usage, route between models by cost/quality, implement prompt caching, or build cost observability for AI features. Triggers: 'my AI costs are

Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines for production

Assisted retrospective: after a session, calibrates what Claude contributed vs what the developer drove. LLM-assessed 4-frame analysis, zero dependencies.