Free, local-first voice synthesis studio (MIT license) powered by Qwen3-TTS.
Voice cloning from short samples, local REST API, no per-character costs.
4-5x faster on Apple Silicon via MLX.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix 3 wrong character counts in ad copy examples (all off by +1)
- Fix TikTok ad text: 80 recommended / 100 max (was 100 recommended)
- Fix LinkedIn description: add 300 max (was missing)
- Fix Gemini API model name: gemini-2.5-flash-image (was gemini-2.0-flash-exp)
- Fix Cartesia pricing: $0.03/min (was $0.0085/sec)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Covers ElevenLabs (voice cloning, best quality), OpenAI TTS (cheap at scale),
Cartesia Sonic (40ms latency), PlayHT, Resemble AI, WellSaid Labs, Fish Audio,
and cloud providers. Includes comparison table, decision tree, and voice+video
layering workflow with ffmpeg.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ByteDance's video model with native audio, up to 2K resolution, multimodal
inputs (12 references), and OpenAI-compatible API. Estimated 10-100x cheaper
than Sora 2 per clip, making it ideal for high-volume ad production.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Covers image generation (Nano Banana Pro, Flux, Ideogram), video generation
(Veo, Kling, Runway, Sora, Higgsfield), and code-based video (Remotion).
Includes decision tree, cost comparison for 100+ variations, platform image
specs, and recommended hybrid workflow for scaled ad production.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Inspired by Anthropic growth marketing team workflows. Covers generating
headlines, descriptions, and primary text at scale across Google Ads, Meta,
LinkedIn, TikTok, and Twitter/X with platform character limits, performance
based iteration loops, and batch generation workflows.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- amplitude: mask api_key in dry-run body output
- livestorm: add missing Bearer prefix to Authorization header
- mixpanel: mask token/$token in dry-run ingestion body output
- onesignal: change auth from 'Key' to 'Basic' per OneSignal REST API docs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Critical:
- meta-ads: move access_token from URL query string to Authorization
header to prevent credential leakage in server logs and referrers
Medium (URL encoding):
- g2: encode state and date filter values
- trustpilot: use URLSearchParams for reviews list params
- typeform: encode response IDs in delete endpoint
- demio: encode event type filter
- lemlist: encode email addresses in URL path segments
Docs:
- Fix 6 missing env vars in CLI README auth table
- Fix .gitignore typo (extra space in .DS_Store pattern)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
High-quality cold-email skill with benchmarks, frameworks, and follow-up sequences. Complements email-sequence (lifecycle) and the new email outreach CLIs.
- Expand .gitignore with .env, .DS_Store, node_modules, editor files,
and macOS iCloud duplicate patterns
- Add security section to CLI README warning against hardcoded keys
- Update AGENTS.md with CLI tools in repo structure and build commands
- Trash 40 macOS "2.md" duplicate files from working tree
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- meta-ads: use empty array for special_ad_categories (not ['NONE'])
- ahrefs: add --target validation to all 5 site-explorer commands
- wistia: read SRT file contents from disk for captions create
- tiktok-ads: use URLSearchParams for cleaner URL construction
- mixpanel: require --from-date/--to-date for retention, add --event filter for export
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fixes from thorough codex review (o3 high reasoning, 5 parallel batches):
Validation fixes:
- customer-io: add ID validation for customer/campaign commands, event name check
- dub: fix links get to use /links/info endpoint, add --id validation
- google-search-console: fix countries to use ['country'] only, add --url validation
- mention-me: add --customer-id validation on referral/share/reward commands
- tolt: add --id validation for affiliates get/update
Auth & API fixes:
- apollo: move API key from header to JSON body, fix search endpoint path
- rewardful: change from Bearer to Basic auth
- hotjar: split OAuth URL (unversioned) from resource URL (v2)
- amplitude: wrap retention e param in JSON array
- snov: change list prospects from GET to POST with JSON body
- optimizely: change archive from DELETE to PATCH status=archived
- google-ads: fix budget body field from camelCase to snake_case
- resend: change webhook field from endpoint to url, add validation
- linkedin-ads: add required campaignGroup URN, fix numeric amount types
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fixes found by automated codex review of all 47 CLI tools:
- resend: webhook field name endpoint_url -> endpoint
- mailchimp: change from Bearer to Basic auth per API docs
- kit: fail fast when api_secret required but not set
- activecampaign: automation add-contact needs --contact-id not --email
- google-ads: budget updateMask must be snake_case (amount_micros)
- meta-ads: special_ad_categories default to ['NONE'] not empty array
- linkedin-ads: add required X-RestLi-Protocol-Version header
- onesignal: auth prefix should be Key, not Basic
- mixpanel: query dates must be YYYY-MM-DD, not relative strings
- wistia: change from Bearer to Basic auth per API docs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Adobe Analytics: add required x-proxy-global-company-id header
(Adobe Analytics 2.0 API rejects requests without this header)
- Clearbit: change from Bearer to Basic auth (API key as username)
per Clearbit API documentation
Found by codex review of all 47 CLI tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When --dry-run is passed, each CLI prints the HTTP request it would
make (method, URL, headers, body) without actually calling fetch().
Auth credentials are masked as "***" in the output.
Useful for verifying request shape and API endpoints without needing
real API keys or making actual API calls.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add two new SEO tool integrations with zero-dependency CLI tools and
detailed API documentation for agent use.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Single-file Node.js scripts for every tool in the registry that lacked
a CLI. All follow the same pattern: env var auth, JSON output, consistent
`{tool} <resource> <action>` command structure, zero npm dependencies.
CLIs added: resend, sendgrid, mailchimp, kit, customer-io, ahrefs,
semrush, google-search-console, ga4, mixpanel, amplitude, segment,
adobe-analytics, rewardful, tolt, mention-me, dub, google-ads,
meta-ads, linkedin-ads, tiktok-ads, zapier.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
web_fetch strips <script> tags during HTML→markdown conversion, which
silently discards JSON-LD schema blocks. Additionally, many CMS plugins
(AIOSEO, Yoast, RankMath) inject schema via client-side JavaScript,
making it invisible to both web_fetch and curl.
This has led to false audit findings in production (reporting 'zero
structured data' on sites with extensive schema implementation).
Adds a prominent warning in the Audit Framework section and a note
in the Tools section recommending browser rendering, Rich Results Test,
or Screaming Frog for accurate schema detection.
Created validate-skills.sh to audit all skills against the Agent Skills
specification. Validates name format, frontmatter fields, description length,
and trigger phrases. All 25 skills currently pass validation.
https://claude.ai/code/session_01DboBqyncsUPg5Z5qpLJx4x
Per the Agent Skills spec, `version` is not a valid top-level frontmatter
field. It belongs under `metadata` as a key-value pair. This fixes all 25
skills to use the correct structure.
https://claude.ai/code/session_01DboBqyncsUPg5Z5qpLJx4x
Per Anthropic's Agent Skills best practices, reference files over
100 lines should include a TOC so Claude can see full scope when
previewing with partial reads. Added ## Contents section to all
32 reference files.
Add section to content-architecture.md explaining how to leverage
site footer for internal linking to comparison/alternative pages.
Covers minimum approach (index links) and recommended approach
(dedicated columns with top 8 competitors per format).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add version: 1.0.0 to all 25 skill YAML frontmatters
- Create VERSIONS.md manifest listing all skill versions
- Add update check instructions to AGENTS.md
This enables users to be notified of skill updates and easily
pull the latest changes when 2+ skills are updated or there is
a major version bump.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create centralized tools/ directory with REGISTRY.md index and 29
integration guides covering analytics, SEO, CRM, payments, referral,
email, ads, automation, and commerce platforms.
Each guide includes API endpoints, authentication, common operations,
and links to relevant skills. Updated AGENTS.md and key skills
(referral-program, analytics-tracking, email-sequence, paid-ads)
with tool integration references.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
