Claude Skills by KevinZai

Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use for analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards.

When the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also use when the user mentions 'social media strategy,' 'social calendar,' 'community management,' 'social media plan,' 'grow followers,' 'engagement rate,' 'social media audit,' or 'which platforms should I use.' For writing individual social posts, see social-content. For analyzing social performance data, see social-media-analyzer.

Universal links, Android App Links, deep linking configuration, and deferred deep linking for mobile apps.

Flutter/Dart development — widget architecture, state management, platform channels, and cross-platform best practices.

SAML, OIDC, and enterprise identity provider scaffolds · Pro tier only

Failure injection patterns and resilience testing for production services · Pro tier only

Zero-downtime schema versioning, backfills, and safe deploy patterns · Pro tier only

OpenTelemetry, Honeycomb, Datadog, and structured logging wiring · Pro tier only

Multi-tenant SaaS scaffolds: row-level security, billing, invitations · Pro tier only

Answer-first output: fix, then command, then file:line — context last. Based on ayghri/i-have-adhd (MIT). Toggle: $ccc-adhd [on | off | status]. Stacks with caveman.

Bring the CC Commander Orchestrator/Executor doctrine into an EXISTING project. Detects stack, merges a delimited CLAUDE.md section (never clobbers), and tailors a skill/agent pointer list.

Relay CC Commander build, deploy, CI, task, and cost signals to your team's chat or email so non-devs see what shipped — read-only, no secrets in payloads.

Audit the project CLAUDE.md against the codebase — stale paths, dead commands, token waste — fixes applied only after AskUserQuestion approval. Use when: 'audit claude md', 'optimize instructions'.

The Commander Console: one inline panel — agents, usage, safety, memory, history — plus a prompt bar that reaches this session. Publishing a snapshot is separate and consent-gated.

Adversarial multi-agent debate (antfooding): fan out N agents that argue and critique a design or diff from distinct lenses until issues resolve, then synthesize a verdict.

Selective ECC loader: pick one Everything Claude Code skill, agent, or hook and link/copy it into ~/.claude without installing the full ECC harness.

The master switch — arms the full Fable Method: always-on PM loop, verification gates, orchestrator posture; works with any model.

Proactive context reset — write a dense handoff file and tell the user to start a NEW chat now. Context degrades quality as it fills; fix is frequent handoffs, not deeper compaction.

Production hardening audit across 11 pillars (Vercel, GitHub, Sentry, PostHog, Stripe, Cloudflare, Secrets/PII). Read-only; --fix applies safe auto-fixes. Use pre-launch. NO PII.

Agent mission control: live dashboard, delegation flow, snapshots, and plain-English status.

Cross-runtime Orchestrator/Executor — Fable/Opus writes a goal file, GPT-5.6 Sol (codex) or a Sonnet subagent executes it, Fable/Opus verifies against acceptance criteria before reporting done.

Write loops, not prompts — a cheap/fast model drafts the plan or loop, a capable model (Opus/Fable) executes each step. Two-phase routing tied to dispatcher complexity tiers.

Fix and sharpen a prompt. Diagnoses it against the 6 prompt-quality patterns, returns a tightened rewrite with the reasoning, and suggests the right library prompt for your task.

Cross-session loop chaining — chain independent spec/build/review loop SESSIONS that auto-hand-off. Use when the user types $ccc-relay, wants the Finn Loop, or auto-chained loops.

complete research ecosystem — 8 skills in one. Deep multi-source research, spec interviews, cross-model review, competitive analysis, trend analysis, and large…

complete SaaS development ecosystem — 21 skills in one. Scaffold, authenticate, bill, ship, and grow a production SaaS from zero to revenue.

Safety deck: what Commander's hooks caught for you — dangerous actions blocked, auto-fixes applied, and where your tools fail most. A self-contained artifact.

complete application security ecosystem — 8 skills in one. OWASP Top 10, secrets scanning, dependency audits, prompt injection defense, CodeQL, and incident…

complete SEO ecosystem — 20 skills in one. Technical SEO, AI search optimization, content strategy, analytics, and programmatic SEO at scale.

Small-business operations — 6 skills in one: 13-week cash-flow forecast, invoicing + AR chasing, payroll planning, CRM hygiene, expense tracking, and a weekly owner brief.

Click-first spawn hub — spin isolated work into its own session on demand: a spawn_task chip in Cowork, a /spawn peer in the CLI. Also routes to $ccc-fleet or $ccc-relay.

complete testing ecosystem — 15 skills in one. TDD, E2E, verification, QA, regression, visual testing, and load testing. Default isolation mode for test dispatches:…

GitHub issue/PR triage for plugin maintainers — list, label, and summarize issues + PRs via gh CLI. Can delegate deep triage to an agent or Codex.

Audit + safely optimize your local ~/.claude CC Commander setup. Read-only scan by default; backs up + archives (never deletes), asks before fixes. Covers versions, junk, drift, agents, hooks, MCP.

Ultracode mode: xhigh reasoning + automatic dynamic-workflow orchestration for migrations, deep audits, and repo-wide work. Requires Claude Code v2.1.154+.

Click-first plugin update walkthrough. Detects installed vs latest version, runs the marketplace-update sequence, reminds you to restart, and verifies the new version + hooks are live.

Usage & Cost deck: what your agent work costs, and what delegating to cheaper models saved you. A self-contained artifact — burn, savings, cost by app.

One-click safe-YOLO + Plan mode — auto-approve read-only/safe ops via a vetted allowlist, keep Plan mode for risky changes. Use when: 'yolo setup', 'reduce prompts', 'fewer approvals'.

Answer-first output: fix, then command, then file:line — context last. Based on ayghri/i-have-adhd (MIT). Toggle: /ccc-adhd [on | off | status]. Stacks with caveman.

Bring the CC Commander Orchestrator/Executor doctrine into an EXISTING project. Detects stack, merges a delimited CLAUDE.md section (never clobbers), and tailors a skill/agent pointer list.

Teach agents to write with clarity, persuasion, and testability. Use when drafting specs, PRDs, PR descriptions, or documentation. Triggers: 'write a spec', 'PR…

Design-first ideation gate. Forces 3 alternatives before any code is written. Triggers AskUserQuestion to pick the path.

Relay CC Commander build, deploy, CI, task, and cost signals to your team's chat or email so non-devs see what shipped — read-only, no secrets in payloads.

Visual, filterable catalog of every CC Commander skill, agent, and command. Cascades from broad category picker into 4-at-a-time detail cards. Use when the user types…

Build something new — web app, API, CLI, or mobile. Guided spec interview routes to the right template, then scaffolds. Use when: 'build something', 'new project', 'create app'.

Show what changed in the latest CC Commander update. Reads CHANGELOG.md and renders the most-recent version section in a digestible summary. Use when the user types…

CC Commander interactive discovery tool. Renders a live flow diagram of every /ccc-* workflow by reading the plugin directly as single source of truth. Use when the…

CI/CD webhook channel. Receive GitHub Actions, Vercel, Railway deploy events in your session. Auto-triggers /ccc-doctor on failures.

Audit the project CLAUDE.md against the codebase — stale paths, dead commands, token waste — fixes applied only after AskUserQuestion approval. Use when: 'audit claude md', 'optimize instructions'.

Review code changes for security, performance, correctness, and maintainability. Use when: 'review code', 'PR review', 'check changes', 'review my diff', 'is this…