- marketing-psychology eval 4: BJ Fogg assertion did not match expected_output
which lists Goal-Gradient Effect. Fixed.
- sales-enablement eval 2: all 6 categories assertion contradicted expected_output
which only categorizes the 3 given objections. Fixed.
- ad-creative eval 5: TikTok hard limit corrected to recommended (80 chars
recommended, 100 max) per SKILL.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- sales-enablement: "ROI calculator" → "deal-specific ROI analysis" to avoid
conflict with free-tool-strategy which also claims "ROI calculator"
- sales-enablement: clarified scope boundary to competitor-alternatives for
battle cards (competitor-alternatives owns battle card creation)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- sales-enablement: "Never demo without discovery" → "Demo after discovery, not before"
- site-architecture: "No exceptions" → explains why (backlink equity, broken pages)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fixes 5 issues identified by independent Codex review:
- product-marketing-context: match auto-draft workflow, section flexibility
- marketing-psychology: replace phantom models with actual SKILL.md models
- ad-creative: correct RSA pinning guidance to match skill
- free-tool-strategy: boundary test now defers to related skill (page-cro)
- paywall-upgrade-cro: boundary test references only related skills
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Each skill now has 5-8 evals covering:
- Core framework usage with realistic prompts
- Casual trigger phrase variants
- Sub-type and section-specific coverage
- Boundary tests (skill deferral to related skills)
- Structured assertions for grading
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Changes per skill:
page-cro (5 -> 7 evals):
- Added structured assertions array to all evals
- Added Blog Post CRO eval (was missing)
- Added boundary eval: signup form should defer to signup-flow-cro
- Replaced feature page A/B test eval with fuller feature page eval
copywriting (5 -> 7 evals):
- Added structured assertions array to all evals
- Added About Page eval with voice/tone adaptation test
- Added boundary eval: email sequence should defer to email-sequence
- Added Quick Quality Check eval (buzzword/jargon/exclamation detection)
- Added meta content assertion to homepage eval
seo-audit (5 -> 8 evals):
- Added structured assertions array to all evals
- Added Local Business eval (NAP, GBP, location pages)
- Added Core Web Vitals / site speed eval
- Added boundary eval: FAQ schema should defer to schema-markup
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Following Anthropic skill-creator guidance that Claude undertriggers
skills, make descriptions pushier across all 32 skills:
- Add casual/frustrated user phrases
- Add implicit need triggers where users need the skill but dont name it
- Add catch-all sentences explaining when to use
- Add missing cross-references between related skills
- Ensure consistent format across all descriptions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The .agents/skills/ directory is the emerging cross-agent standard adopted by
OpenAI Codex, Cursor, Windsurf, and npx skills. All 32 skills now check
.agents/product-marketing-context.md first with .claude/ fallback for older
setups. Install paths in README updated accordingly. Bumps all skills to 1.1.0.
Closes#50
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fill the revenue operations and internal sales collateral gaps in the
marketing skills collection. revops covers lead lifecycle, scoring,
routing, pipeline management, and CRM automation. sales-enablement
covers pitch decks, one-pagers, objection handling, demo scripts, and
sales playbooks. Cross-references added to 6 existing skills.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fills the gap between content strategy and SEO skills — covers page
hierarchy, navigation design, URL structure, and internal linking.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Both ai-seo and churn-prevention updated marketplace.json and
VERSIONS.md. Merged both entries, bumped skill count to 29.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rewrote platform-ranking-factors.md from scratch with our own
organizational approach. Replaced table-heavy format with narrative
prose, different section structure, and synthesized analysis.
Updated SKILL.md robots.txt section to match.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Split AEO/GEO content patterns out of seo-audit into a standalone ai-seo
skill. Covers AI visibility auditing, content extractability, authority
signals, third-party presence strategy, schema markup for AI, monitoring
tools (Otterly, Peec AI, ZipTie), and optimization by content type.
Moves aeo-geo-patterns.md from seo-audit/references to ai-seo/references
(renamed to content-patterns.md). Updates seo-audit to cross-reference
the new skill.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
High-quality cold-email skill with benchmarks, frameworks, and follow-up sequences. Complements email-sequence (lifecycle) and the new email outreach CLIs.
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.
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>
Add Mention Me (AI-powered referral marketing platform) to the
referral program tools list.
Closes#2
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Cherry-picked the genuinely unique content from PR #10 and integrated
into existing skills:
seo-audit/references:
- ai-writing-detection.md: AI writing patterns to avoid (em dashes,
overused phrases, filler words)
- aeo-geo-patterns.md: Answer Engine & Generative Engine Optimization
content patterns
copy-editing/references:
- plain-english-alternatives.md: Complex to simple word replacements
copywriting/references:
- natural-transitions.md: Transitional phrases for better content flow
Updated SKILL.md files to link to new references.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Since product-marketing-context now captures foundational info (product, audience,
competitors, voice), removed redundant questions from these sections and renamed
them to clarify they are for task-specific context only.
Removed redundant questions from:
- competitor-alternatives (competitors, differentiator)
- copy-editing (audience, brand voice)
- email-sequence (audience)
- free-tool-strategy (product, audience problems)
- marketing-ideas (product, target customer)
Renamed section in all 23 skills with this pattern.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The ideas were reorganized from an ebook but kept their original numbers,
resulting in out-of-order numbering (3, 7, 39, 40...). Now renumbered 1-139
based on current order in the file.
Also updated:
- Description and header from 140 to 139 (actual count)
- Related Skills references to correct new numbers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Users repeat the same foundational questions (product, audience, competitors,
voice) across 24 skills. This adds a centralized context document that other
skills can reference.
New skill:
- product-marketing-context: Creates .claude/product-marketing-context.md
- Covers 12 sections based on positioning canvas framework
- Can auto-draft V1 from codebase or gather info conversationally
Updated all 24 existing skills to check for product marketing context first,
reducing repetitive questions when context already exists.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Based on PR #1 submission but rebuilt with:
- Searchable vs Shareable framework as core philosophy
- Content types organized by goal (searchable/shareable)
- Keyword research by buyer stage (awareness/consideration/decision/implementation)
- Content ideation from keywords, transcripts, surveys, forums, competitors
- Prioritization scoring system (customer impact, content-market fit, search, resources)
Removes distribution, repurposing, editorial calendar, performance measurement
(covered by other skills or not needed for strategy planning).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
