30f9b9a729
* feat: v2.0 skill renames and CRO consolidation BREAKING CHANGE: Users must reinstall skills after this update. ## Skill Renames (16) - ab-test-setup → ab-testing - analytics-tracking → analytics - aso-audit → aso - competitor-alternatives → competitors - email-sequence → emails - free-tool-strategy → free-tools - launch-strategy → launch - onboarding-cro → onboarding - paywall-upgrade-cro → paywalls - popup-cro → popups - pricing-strategy → pricing - product-marketing-context → product-marketing - referral-program → referrals - schema-markup → schema - signup-flow-cro → signup - social-content → social ## Consolidations (1) - page-cro + form-cro → cro (form content in references/form.md) ## Why 2.0? - Shorter, cleaner skill names - Consistent naming (no -strategy, -setup, -cro suffixes) - All cross-references updated across 100+ files Total skills: 40 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(v2.0): update evals for renamed skills, fix validate script, clear warnings - Update 32 evals.json files to reference new skill names (page-cro → cro, product-marketing-context → product-marketing, etc.) — these were missed in the initial v2.0 rename pass since only SKILL.md and marketplace.json were updated. - Fix validate-skills.sh: replace GNU-only `head -n -1` with portable awk so frontmatter extraction works on macOS. - Move Copy Editing Checklist (56 lines) to references/checklist.md to bring copy-editing SKILL.md under the 500-line limit (508 → 457). - Add "see X" pointers to marketing-psychology description for skill discovery (cro, pricing, copywriting). - Update skill-request.yml issue template placeholder (page-cro → cro). All 40 skills now pass validation with zero warnings. * fix(v2.0): add evals for 8 missing skills, strip stale frontmatter from cro/form.md Adds 48 new eval cases (6 per skill) for skills that previously had no evals: aso, co-marketing, community-marketing, competitor-profiling, directory-submissions, image, lead-magnets, video. All 40 skills now have eval coverage (251 total cases). Strips leftover frontmatter from skills/cro/references/form.md — it was inherited from the old form-cro SKILL.md before consolidation. Reference files don't need frontmatter. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(v2.0): rename paid-ads → ads One more v2.0 simplification — drops the redundant 'paid-' qualifier. Updates the skill directory, SKILL.md frontmatter, evals.json, README skill table, the v2.0 rename table in VERSIONS.md (now 17 renames), and all cross-references in related skills (ad-creative, aso, competitor-profiling, customer-research, lead-magnets, marketing-ideas) plus the tools/integrations guides. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(v2.0): bump SKILL.md frontmatter version to 2.0.0 for all 40 skills VERSIONS.md was already updated to 2.0.0 but the metadata.version field inside each SKILL.md was still on 1.x. That mismatch would have caused the update-check flow to perpetually report 'update available' since it compares VERSIONS.md against local SKILL.md metadata versions. Caught by codex review (P1). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(v2.0): add legacy product-marketing-context.md filename fallback Before this fix, users upgrading from v1.x who had a `product-marketing-context.md` file would lose automatic context loading — every skill only checked the new `product-marketing.md` filename. Now all 40 skills also accept the legacy filename (in either `.agents/` or `.claude/`), and the README migration command covers both legacy and current filenames. Caught by codex review (P1 + P2). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(v2.0): re-sort README skills table alphabetically, fix ads box width The skills table had a few entries out of alphabetical order from the renames (co-marketing was after cold-email, ads was at the renamed position). Re-sorted alphabetically per sync-skills.js. Also padded the 'ads' cell in the ASCII flow diagram to keep the box width consistent. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * fix(v2.0): document folder cleanup on upgrade, stop sync-skills from re-adding skills array README upgrade guide now includes: - A clear cleanup step for stale v1.x skill folders (renamed + consolidated) so users don't end up with both old and new folders side-by-side after upgrading - The full v1 to v2 rename map for reference - Existing product-marketing-context.md migration steps (preserved) sync-skills.js no longer (re-)introduces a `skills` array on marketplace.json -- Claude Code's plugin schema discovers skills via the `skills/` directory, and the explicit array was failing validation. The script now refreshes the description count and strips the stale array if present. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
85 lines
6.7 KiB
JSON
85 lines
6.7 KiB
JSON
{
|
|
"skill_name": "co-marketing",
|
|
"evals": [
|
|
{
|
|
"id": 1,
|
|
"prompt": "We make a project management tool for design agencies. Who should we look for as co-marketing partners?",
|
|
"expected_output": "Should check for product-marketing.md first. Should apply the Partner Identification Framework with audience overlap analysis. Should identify ideal partner characteristics: same buyer persona (design agencies), different problem solved, adjacent in the workflow. Should suggest specific partner categories: design tools (Figma, Adobe), proposal/contract tools (Bonsai, HoneyBook), client communication (Notion, Slack), invoicing/payments (Stripe, FreshBooks), file storage/handoff (Dropbox, Frame.io). Should recommend audience scoring criteria. Should suggest sources to find partners: integration ecosystem, Crossbeam/Reveal for account overlap, customer surveys, G2/Capterra category neighbors, podcasts/newsletters they sponsor.",
|
|
"assertions": [
|
|
"Checks for product-marketing.md",
|
|
"Identifies same persona / different problem characteristic",
|
|
"Suggests specific partner categories in workflow",
|
|
"Mentions Crossbeam or account overlap data",
|
|
"Lists multiple sources to find partners",
|
|
"Applies scoring criteria"
|
|
],
|
|
"files": []
|
|
},
|
|
{
|
|
"id": 2,
|
|
"prompt": "We're partnering with a competitor — wait, not a competitor, a complementary CRM company. Help us brainstorm 5 campaign ideas we could run together.",
|
|
"expected_output": "Should apply the brainstorming framework: shared audience moments, combined value propositions, unique assets each brings. Should propose campaign ideas across multiple types from the campaign type tables (content partnerships, webinars/events, product/integration marketing, community/social). Should suggest specific ideas like: co-authored blog post or research report, joint webinar, 'better together' integration landing page, joint case study with shared customer, integration launch, bundle/discount, conference booth sharing. Should ask the campaign idea prompts to spark ideas: what would we create if we had to launch in 2 weeks, what content do both audiences desperately need, what data do we both have that would make a compelling story.",
|
|
"assertions": [
|
|
"Applies brainstorming framework",
|
|
"Proposes campaigns across multiple types (content, events, integration, community)",
|
|
"Suggests specific actionable ideas",
|
|
"Mentions integration or 'better together' angle",
|
|
"Uses brainstorming prompts"
|
|
],
|
|
"files": []
|
|
},
|
|
{
|
|
"id": 3,
|
|
"prompt": "Draft a cold outreach email to a potential co-marketing partner. They're a content management platform and we make a marketing analytics tool. Both serve B2B marketing teams.",
|
|
"expected_output": "Should use the cold outreach template structure. Should include: subject line with both company names, brief role intro, specific observation about audience overlap (not generic), one concrete campaign idea (not 'let's do something'), clear ask for a quick call. Should keep it short and personal. Should optionally mention call prep: account overlap data (Crossbeam/Reveal), 2-3 specific campaign ideas, audience metrics, past partnership examples, clear ask of what's wanted and what's offered.",
|
|
"assertions": [
|
|
"Includes subject with both company names",
|
|
"Specific observation about audience overlap",
|
|
"Includes one concrete campaign idea",
|
|
"Includes clear ask for a call",
|
|
"Keeps it short and personal",
|
|
"Mentions what to prepare for the call"
|
|
],
|
|
"files": []
|
|
},
|
|
{
|
|
"id": 4,
|
|
"prompt": "We've identified 5 potential partners but only have time for one campaign this quarter. How should we pick?",
|
|
"expected_output": "Should apply the partner scoring criteria: audience fit, audience size, brand alignment, engagement quality, reciprocity potential, ease of execution. Should recommend scoring each partner 1-5 across these criteria. Should weight by current goal (e.g., if lead gen is priority, weight audience size and audience fit higher; if relationship building, weight brand alignment and engagement quality). Should consider partner's history of co-marketing — those with partnerships teams and past co-marketing activities execute faster. Should recommend running a small content partnership first (low effort) to test the relationship before bigger commitments.",
|
|
"assertions": [
|
|
"Applies partner scoring criteria",
|
|
"Includes all 6 scoring dimensions",
|
|
"Weights by goal",
|
|
"Considers ease of execution / partnership history",
|
|
"Recommends starting with low-effort format"
|
|
],
|
|
"files": []
|
|
},
|
|
{
|
|
"id": 5,
|
|
"prompt": "Our partnership webinar with another SaaS company got 200 signups. How do we split the leads?",
|
|
"expected_output": "Should address the lead handling question from the Structuring the Partnership section. Should explain common splits: each partner keeps their own registrations (cleanest but loses cross-pollination), all leads shared between both (max reach, requires clear MQL/SQL handoff), split by audience source (your list vs theirs). Should recommend documenting this in advance in a co-marketing agreement covering campaign description, responsibilities, timeline, lead handling, promotion, branding, costs, metrics sharing. Should note measuring success: leads generated per partner, lead quality (MQL/SQL conversion rate), revenue attributed. Should recommend a post-campaign debrief and discussing future collaboration if it worked.",
|
|
"assertions": [
|
|
"Explains lead split options",
|
|
"Recommends documenting in agreement",
|
|
"Lists agreement components",
|
|
"Mentions measuring lead quality not just volume",
|
|
"Recommends post-campaign debrief"
|
|
],
|
|
"files": []
|
|
},
|
|
{
|
|
"id": 6,
|
|
"prompt": "Our customer success team wants us to launch a referral program. Can you help us design one?",
|
|
"expected_output": "Should recognize this is about customer referrals, not co-marketing between companies. Should redirect to the referrals skill, which specifically handles customer referral and affiliate programs (customers referring customers). Should note co-marketing is partner-to-partner marketing while referrals is customer-driven word-of-mouth. May offer brief co-marketing context if it's relevant to the strategy, but should make clear referrals is the right skill for the task.",
|
|
"assertions": [
|
|
"Recognizes this is customer referral, not co-marketing",
|
|
"Defers to referrals skill",
|
|
"Distinguishes co-marketing from referral programs",
|
|
"Does not attempt full co-marketing strategy"
|
|
],
|
|
"files": []
|
|
}
|
|
]
|
|
}
|