meshcode-ai
Organization73 open-source Agent Skills for business — SEO/AEO, marketing, copywriting, operations, planning, research, executive. Knowledge-first, 2KB each. Claude Code, Codex, Cursor, meshcode.
Categories
Indexed Skills (140)
dev-architecture
System design before code — classifies a request as spike, bounded, or architectural and produces the right design artifact with an approval gate. Use when the user asks to design a feature or system, compare technical approaches, structure a new project, write an ADR, or when a change crosses module boundaries or alters interfaces others depend on.
docs-docx
Document generation — report/proposal structure, heading hierarchy, styles, and producing verified .docx files via pandoc or docx libraries. Use when user says "write a report", "make a document", "Word file", "docx", "proposal document", or needs a formal long-form document delivered as a file. Slides are docs-pptx; print-ready PDF is docs-pdf.
docs-pdf
PDF production — print vs screen route selection, page layout, font embedding, and export verification for reports, ebooks, and one-pagers. Use when user says "make a PDF", "export to PDF", "print-ready", "ebook", "PDF report", or a deliverable must ship as PDF. Editable documents are docs-docx; slides are docs-pptx.
docs-pptx
Presentation generation — deck storyline, slide-by-slide outline, chart choice, and generating/editing .pptx files with overflow and font QA. Use when user says "make a presentation", "build a deck", "PowerPoint", "pptx", "investor deck slides", or needs slides from notes/data. Written reports are docs-docx; visual identity beyond the deck is design-design-system.
design-design-system
Design system and design tokens — token layering (primitive → semantic → component), minimal token set, dark mode, and legacy migration mapping. Use when user says "design system", "design tokens", "token architecture", "dark mode tokens", "unify our styles", or when inconsistent colors/spacing across a product needs a system fix. Single-page design is design-homepage.
design-homepage
Homepage and landing page design — structure, hero, visual hierarchy, motion restraint, and AI-template tells. Use when user says "design a homepage", "landing page design", "hero section", "website design", or asks to build/redesign a marketing site. Component-level review is design-ui-audit; tokens are design-design-system.
design-ui-audit
UI design review — grades hierarchy, spacing, typography, color, consistency, accessibility of a page or component set, then ranks fixes by impact. Use when user says "design review", "UI audit", "critique this UI", "why does this look off", or shares a URL/screenshot for design feedback. Building from scratch is design-homepage; token architecture is design-design-system.
ops-compliance-checklist
Build a compliance checklist and evidence plan for an audit or policy rollout — control mapping, evidence cadence, and audit-readiness verdict. Use when user says "compliance checklist", "audit readiness", "SOC 2", "ISO 9001", "GDPR checklist". For SOP authoring use ops-sop-builder.
mkt-churn-prevention
Churn reduction — cancellation flows, save offers, dunning/payment recovery, health scoring. Use when user says "reduce churn", "cancellation flow", "save offer", "failed payments", "dunning". Activation problems are mkt-onboarding.
mkt-comparisons
Comparison and alternative pages — builds "{competitor} alternative" pages, versus tables, migration guides for SEO and sales enablement. Use when user says "comparison page", "alternative to", "vs page", "migrate from". Deep competitor research is mkt-competitor-profiling.
mkt-funnel-audit
Funnel journey diagnosis — maps stages, quantifies drop-off, finds the leaking step and prioritizes fixes. Use when user says "funnel analysis", "funnel audit", "funnel diagnosis", "where are users dropping", "conversion funnel". Single-page conversion tests are mkt-cro, not this.
mkt-churn-prevention
Churn reduction — cancellation flows, save offers, dunning/payment recovery, health scoring. Use when user says "reduce churn", "cancellation flow", "save offer", "failed payments", "dunning". Activation problems are mkt-onboarding.
mkt-comparisons
Comparison and alternative pages — builds "{competitor} alternative" pages, versus tables, migration guides for SEO and sales enablement. Use when user says "comparison page", "alternative to", "vs page", "migrate from". Deep competitor research is mkt-competitor-profiling.
mkt-funnel-audit
Funnel journey diagnosis — maps stages, quantifies drop-off, finds the leaking step and prioritizes fixes. Use when user says "funnel analysis", "funnel audit", "funnel diagnosis", "where are users dropping", "conversion funnel". Single-page conversion tests are mkt-cro, not this.
design-design-system
Design system and design tokens — token layering (primitive → semantic → component), minimal token set, dark mode, and legacy migration mapping. Use when user says "design system", "design tokens", "token architecture", "dark mode tokens", "unify our styles", or when inconsistent colors/spacing across a product needs a system fix. Single-page design is design-homepage.
design-homepage
Homepage and landing page design — structure, hero, visual hierarchy, motion restraint, and AI-template tells. Use when user says "design a homepage", "landing page design", "hero section", "website design", or asks to build/redesign a marketing site. Component-level review is design-ui-audit; tokens are design-design-system.
design-ui-audit
UI design review — grades hierarchy, spacing, typography, color, consistency, accessibility of a page or component set, then ranks fixes by impact. Use when user says "design review", "UI audit", "critique this UI", "why does this look off", or shares a URL/screenshot for design feedback. Building from scratch is design-homepage; token architecture is design-design-system.
docs-docx
Document generation — report/proposal structure, heading hierarchy, styles, and producing verified .docx files via pandoc or docx libraries. Use when user says "write a report", "make a document", "Word file", "docx", "proposal document", or needs a formal long-form document delivered as a file. Slides are docs-pptx; print-ready PDF is docs-pdf.
docs-pdf
PDF production — print vs screen route selection, page layout, font embedding, and export verification for reports, ebooks, and one-pagers. Use when user says "make a PDF", "export to PDF", "print-ready", "ebook", "PDF report", or a deliverable must ship as PDF. Editable documents are docs-docx; slides are docs-pptx.
docs-pptx
Presentation generation — deck storyline, slide-by-slide outline, chart choice, and generating/editing .pptx files with overflow and font QA. Use when user says "make a presentation", "build a deck", "PowerPoint", "pptx", "investor deck slides", or needs slides from notes/data. Written reports are docs-docx; visual identity beyond the deck is design-design-system.
ops-compliance-checklist
Build a compliance checklist and evidence plan for an audit or policy rollout — control mapping, evidence cadence, and audit-readiness verdict. Use when user says "compliance checklist", "audit readiness", "SOC 2", "ISO 9001", "규정 준수", "내부 감사", "통제 문서화", "GDPR checklist". For SOP authoring use ops-sop-builder.
res-competitor-research
Competitor research — systematic profiling of rivals' product, pricing, positioning, GTM, and moat with evidence-graded comparison tables. Use when user says "competitor analysis", "competitive research", or .
res-customer-research
Customer and user research — interview guides, JTBD framing, evidence-based insight synthesis, and bias controls. Use when user says "customer research", "user research", or needs to understand why users buy, stay, or churn.
res-deep-research
Multi-source deep research with citation-grade synthesis — frames the question, gathers primary/official sources, resolves conflicts, delivers a sourced verdict. Use when user says "deep research", "research this thoroughly", or asks a broad factual question needing verified web sources.
res-dossier
Structured dossier building — entity briefing packs on companies or people with verified facts, timeline, network map, and open questions. Use when user says "dossier", or needs a one-stop fact pack before a meeting.
res-litreview
Structured literature review — search strategy, inclusion/exclusion screening, quality appraisal, and synthesis map of a research field. Use when user says "literature review", "lit review", or needs to map what is already known about a topic.
res-patent-landscape
Patent landscape and freedom-to-operate analysis — IPC/CPC classification mapping, assignee and citation clustering, white-space and risk screening. Use when user says "patent landscape", "FTO", or before launching a product in a crowded tech field.
res-research-brief
Research brief writing — turns a fuzzy topic into a scoped, decision-oriented brief with questions, success criteria, and an executable plan others can run. Use when user says "research brief", or needs to hand off a research task with clear scope.
res-survey-design
Survey and questionnaire design — sampling plan, sample-size math, question wording, order and non-response bias checks, analysis-ready instrument. Use when user says "survey design", or needs quantitative validation of a hypothesis.
dev-code-review
Code review with severity-graded findings and evidence per claim — reviews the diff against requirements, not files in isolation. Use when the user asks for a code review, PR review, or diff review, before merging a branch, or after completing a major feature. Also covers the protocol for receiving review feedback without performative agreement.
dev-test-design
Test design before implementation — turns requirements into a test-case matrix (happy path, boundary values, invalid input, edge cases) and enforces red-green-refactor. Use when the user asks to design tests, write a test plan, raise coverage, or review test quality. Also use before implementing any feature or bugfix.
video-script
Video script writing — cold-open structure, retention checkpoints, hook formulas, and timed outlines for long-form and shorts. Use when user says "video script", "write a script", "YouTube video outline", "shorts script", "hook ideas", or has a topic and needs a shootable script. Clip editing is video-shorts; titles/thumbnails are video-packaging.
video-shorts
Short-form video (Shorts/Reels/TikTok) creation — clip selection from long-form, 9:16 reframing, burned-in captions, safe zones, render and QA. Use when user says "make shorts", "cut clips from this video", "vertical clips", "9:16", "Reels", "TikTok edit", or wants to repurpose a long video into shorts. Script writing is video-script; titles/thumbnails are video-packaging.
exec-decision-memo
Structures executive decisions — option set, reversibility test, weighted criteria, premortem, and a reviewable decision record. Use when user says "decision memo", "how to decide", or "premortem".
exec-executive-mentor
Executive mentoring for founders and C-level leaders — delegation levels, decision rights, calendar triage, and effective 1:1 cadence. Use when user says "executive mentor", "CEO coaching", "delegation", or .
exec-investor-update
Writes monthly investor updates — highlights, lowlights, metric tables, and specific asks — with consistent metric definitions and runway narrative. Use when user says "investor update", "board report", or .
exec-leadership-comm
Executive communication — all-hands messaging, crisis response principles, and change announcements that reduce rumor and resistance. Use when user says "all-hands", "town hall", "crisis communication", or .
fin-forecast
Forecasts revenue — baseline plus weighted pipeline, commit/best-case categories, forecast accuracy tracking, and 13-week cash flow linkage. Use when user says "sales forecast", "revenue forecast", "forecast accuracy", "quota", or .
fin-negotiation
Prepares negotiations — BATNA and ZOPA analysis, anchoring with justification bands, give-get tradeoffs, and discount governance. Use when user says "negotiation strategy", "BATNA", "ZOPA", or "discount negotiation".
fin-prospecting
Defines ICP from top-customer cohorts, builds scored target lists, mixes outbound channels with experiments, and computes the activity math to hit pipeline goals. Use when user says "prospecting", "ICP", "target list", or .
fin-revops
Aligns sales, marketing, and CS operations — single metric definitions, CRM hygiene rules, funnel number reconciliation, and a weekly reporting rhythm. Use when user says "RevOps", "revenue operations", "CRM data quality", "funnel reconciliation", or .
fin-sales-enablement
Builds sales enablement assets — MEDDICC qualification scoring, discovery question sets, demo-to-value flow, and a one-page proposal structure. Use when user says "sales enablement", "MEDDICC", "discovery call", "demo structure", or "proposal structure".
fin-sales-pipeline
Manages the sales pipeline — buyer-evidence stage criteria, pipeline coverage ratio (3x), sales velocity formula, win rate consistency, and stalled deal cleanup. Use when user says "sales pipeline", "pipeline coverage", "deal stages", "sales velocity", or "stalled deals".
biz-business-plan
Structures a business plan or lean canvas — problem, solution, market, moat, GTM, 3-scenario financials — with an explicit assumption register and milestones. Use when user says "business plan", "lean canvas", "startup plan", or .
biz-competitor-profiling
Profiles direct, indirect, substitute, and potential competitors — feature-pricing matrix, positioning map from customer language, and recent-signal tracking to find exploitable gaps. Use when user says "competitor analysis", "competitive landscape", "rivals", or .
biz-market-sizing
Estimates market size with TAM/SAM/SOM using top-down, bottom-up, and analogous-market methods, then triangulates into a defensible range with sensitivity scenarios. Use when user says "market size", "TAM SAM SOM", "addressable market", or asks whether a market is big enough to enter.
biz-offer-design
Builds a one-line value proposition and stacks offer components — core deliverable, bonuses, guarantee/risk reversal, scarcity — with tiered packaging aligned to pricing. Use when user says "offer design", "value proposition", or "risk reversal guarantee".
biz-prd
Writes a PRD from an idea, meeting notes, or existing code — problem, goals/non-goals, user stories, FR/NFR, success metrics, MoSCoW priority, and acceptance criteria. Use when user says "PRD", "product requirements document", "code to PRD", or "feature spec".
biz-pricing-strategy
Chooses among cost-plus, value-based, and competitor-based pricing, picks skimming vs penetration vs premium strategy, and sets a three-point price band with A/B test design. Use when user says "pricing strategy", "how much should I charge", "pricing model", "price point", or .
biz-segmentation
Segments a market using Kotler's five criteria (measurable, substantial, accessible, differentiable, actionable), scores segment attractiveness, and picks one target segment with a positioning line. Use when user says "market segmentation", "customer segments", "target customer", or "STP".
biz-unit-economics
Computes LTV, CAC, payback period, and contribution margin, applies the LTV:CAC ≥ 3 and payback ≤ 12 months thresholds, and finds which lever (price, churn, CAC) moves profitability most. Use when user says "unit economics", "LTV", "CAC", "LTV CAC ratio", or .
ops-capacity-planner
Size an ops team (support, CX, IT, finance ops) that handles queued work — utilization bands, demand P90, shrinkage-adjusted FTE, hiring sequence. Use when user says "capacity planning", "headcount plan", "utilization", "SLA understaffed". Not engineering velocity.
copy-brand-voice
Brand voice — voice guidelines, tone-by-channel adaptation, and before/after rewrites that keep identity consistent across pages, emails, and posts. Use when user says "brand voice", "tone of voice", "style guide".
copy-cold-email
Cold email writing — subject lines, one-line personalization, value-first body, single CTA, and follow-up cadence for outbound prospecting. Use when user says "cold email", "outreach email", "first email to a prospect".
copy-content-brief
Content brief creation — SERP gap analysis, search intent, outline with H2/H3, sources, tone, and acceptance criteria for writers and AI drafts. Use when user says "content brief", "blog brief", "writer brief".
copy-content-strategy
Content strategy — pillar selection, channel/format matrix, 80-10-10 mix, distribution-first planning, and a 90-day calendar. Use when user says "content strategy", "content pillars", "content calendar".
copy-copy-editing
Copy editing — three-pass structural/line/final edit, weak-verb replacement, redundancy deletion, and a pre-publish checklist for any drafted text. Use when user says "copy editing", "edit my draft", "proofread", "polish this".
copy-copywriting
Copywriting frameworks — AIDA, PAS, Before-After-Bridge, 4U — with selection criteria, headline formulas, feature-to-benefit translation, and CTA phrasing. Use when user says "copywriting", "write copy", "headline", "sales copy".
copy-email-sequences
Email copywriting — subject lines, preview text, skimmable body structure, and personalization for sequences and newsletters. Use when user says "email copy", "subject line", "preview text", "newsletter copy".
copy-humanize
Remove AI-sounding phrasing — cliché opener deletion, varied sentence rhythm, concrete experience injection, and a human-sounding rewrite pass. Use when user says "humanize", "make it sound human".
copy-landing-copy
Landing page copy — hero, above-the-fold structure, section order, benefit stack, and CTA copy for product pages, with message match from ad to page. Use when user says "landing page copy", "hero copy", "above the fold", "CTA copy".
copy-pr-outreach
PR outreach — newsworthiness test, press release structure, journalist pitch emails, embargo notes, and follow-up rules. Use when user says "press release", "media pitch", "PR outreach".
mkt-ad-creative
Ad creative strategy — angles, hooks, formats, iteration matrix for paid ads at scale. Use when user says "ad creative", "ad copy ideas", "_hooks", "creative testing". Campaign structure/bidding is mkt-google-ads or mkt-meta-ads.
mkt-analytics
Analytics measurement plan — event tracking design, GA4 structure, KPI tree, data quality audit. Use when user says "analytics setup", "event tracking", "measurement plan", "KPI definition", "GA4". Channel attribution logic is mkt-attribution.
mkt-attribution
Attribution modeling — figures out which channels and touchpoints actually drive conversions and revenue. Use when user says "attribution", "which channel works", "UTM strategy", "multi-touch", "ROAS truth". Basic event setup is mkt-analytics.
mkt-community
Community-led growth — picks platform, seeds members, sets ritual and moderation, ties community to product metrics. Use when user says "community strategy", "Discord community", "community building". Referral mechanics are mkt-referrals.
mkt-competitor-profiling
Competitor research and profiling — URL-based teardown of positioning, pricing, channels, weaknesses, and strategic gaps. Use when user says "competitor analysis", "competitor profile", "benchmark competitors". Comparison landing pages are mkt-comparisons, pricing strategy is mkt-pricing.
mkt-cro
Conversion rate optimization for a specific page, form, or flow — audits friction, prioritizes fixes, designs experiments. Use when user says "CRO", "increase conversions", "landing page conversion", "optimize this page", "form abandonment". Whole-journey diagnosis is mkt-funnel-audit.
mkt-email-sequences
Email sequence design — welcome, nurture, cart abandonment, re-engagement flows with timing, cadence, and copy structure. Use when user says "email sequence", "drip campaign", "welcome email", "email flow", "abandoned cart email". SMS is out of scope.
mkt-google-ads
Google Ads strategy — campaign structure, keyword intent tiers, match types, bid budgets, Quality Score, Performance Max judgment. Use when user says "Google Ads", "SEA", "PPC", "keyword bidding". Meta/social ads are mkt-meta-ads.
mkt-growth-loops
Growth loops — designs self-reinforcing cycles where output becomes new input (usage → sharing → new users). Use when user says "growth loop", "viral loop", "self-feeding growth", "flywheel". One-off referral campaigns are mkt-referrals.
mkt-launch
Product/feature launch — T-minus timeline, channel sequencing, messaging house, launch tiering. Use when user says "product launch", "launch plan", "feature announcement". Positioning fundamentals are mkt-product-marketing.
mkt-marketing-psychology
Behavioral psychology for marketing — cognitive biases, persuasion principles, ethical application checklist. Use when user says "marketing psychology", "persuasion", "mental models", "bias in marketing". Copywriting itself is a copy-* skill.
mkt-meta-ads
Meta (Facebook/Instagram) ads — campaign structure, creative-first testing, audience layers, signal/CAPI setup, budget scaling. Use when user says "Meta ads", "Facebook ads", "CAC scaling", "lookalike". Google/search ads are mkt-google-ads.
mkt-offers
Offer design — value stacking, risk reversal, guarantee, pricing frame, urgency construction. Use when user says "offer", "make an offer", "value stack", "guarantee", "promo strategy". Whole pricing/packaging strategy is mkt-pricing.
mkt-onboarding
User activation and onboarding optimization — time-to-value, aha moment, first-run flow, checklist design. Use when user says "onboarding", "activation", "first-run experience", "time to value", "Aha moment". Post-churn winback is mkt-churn-prevention.
mkt-pricing
Pricing and packaging — model selection, tier design, WTP research, price change plans. Use when user says "pricing strategy", "pricing model", "packaging", "WTP". Single promo/offer design is mkt-offers.
mkt-product-marketing
Product marketing foundation — positioning, ICP definition, messaging house, competitive narrative. Use when user says "product marketing", "positioning", "ICP", "target audience". All other mkt-* skills should read this first.
mkt-referrals
Referral and affiliate program design — incentive structure, double-sided rewards, fraud prevention, launch plan. Use when user says "referral program", "refer a friend", "affiliate program". Ongoing viral loop mechanics are mkt-growth-loops.
biz-business-plan
Structures a business plan or lean canvas — problem, solution, market, moat, GTM, 3-scenario financials — with an explicit assumption register and milestones. Use when user says "business plan", "lean canvas", "startup plan", or .
biz-competitor-profiling
Profiles direct, indirect, substitute, and potential competitors — feature-pricing matrix, positioning map from customer language, and recent-signal tracking to find exploitable gaps. Use when user says "competitor analysis", "competitive landscape", "rivals", or .
biz-market-sizing
Estimates market size with TAM/SAM/SOM using top-down, bottom-up, and analogous-market methods, then triangulates into a defensible range with sensitivity scenarios. Use when user says "market size", "TAM SAM SOM", "addressable market", or asks whether a market is big enough to enter.
biz-offer-design
Builds a one-line value proposition and stacks offer components — core deliverable, bonuses, guarantee/risk reversal, scarcity — with tiered packaging aligned to pricing. Use when user says "offer design", "value proposition", or "risk reversal guarantee".
biz-prd
Writes a PRD from an idea, meeting notes, or existing code — problem, goals/non-goals, user stories, FR/NFR, success metrics, MoSCoW priority, and acceptance criteria. Use when user says "PRD", "product requirements document", "code to PRD", or "feature spec".
biz-pricing-strategy
Chooses among cost-plus, value-based, and competitor-based pricing, picks skimming vs penetration vs premium strategy, and sets a three-point price band with A/B test design. Use when user says "pricing strategy", "how much should I charge", "pricing model", "price point", or .
biz-segmentation
Segments a market using Kotler's five criteria (measurable, substantial, accessible, differentiable, actionable), scores segment attractiveness, and picks one target segment with a positioning line. Use when user says "market segmentation", "customer segments", "target customer", or "STP".
biz-unit-economics
Computes LTV, CAC, payback period, and contribution margin, applies the LTV:CAC ≥ 3 and payback ≤ 12 months thresholds, and finds which lever (price, churn, CAC) moves profitability most. Use when user says "unit economics", "LTV", "CAC", "LTV CAC ratio", or .
copy-brand-voice
Brand voice — voice guidelines, tone-by-channel adaptation, and before/after rewrites that keep identity consistent across pages, emails, and posts. Use when user says "brand voice", "tone of voice", "style guide".
copy-cold-email
Cold email writing — subject lines, one-line personalization, value-first body, single CTA, and follow-up cadence for outbound prospecting. Use when user says "cold email", "outreach email", "first email to a prospect".
copy-content-brief
Content brief creation — SERP gap analysis, search intent, outline with H2/H3, sources, tone, and acceptance criteria for writers and AI drafts. Use when user says "content brief", "blog brief", "writer brief".
copy-content-strategy
Content strategy — pillar selection, channel/format matrix, 80-10-10 mix, distribution-first planning, and a 90-day calendar. Use when user says "content strategy", "content pillars", "content calendar".
copy-copy-editing
Copy editing — three-pass structural/line/final edit, weak-verb replacement, redundancy deletion, and a pre-publish checklist for any drafted text. Use when user says "copy editing", "edit my draft", "proofread", "polish this".
copy-copywriting
Copywriting frameworks — AIDA, PAS, Before-After-Bridge, 4U — with selection criteria, headline formulas, feature-to-benefit translation, and CTA phrasing. Use when user says "copywriting", "write copy", "headline", "sales copy".
copy-email-sequences
Email copywriting — subject lines, preview text, skimmable body structure, and personalization for sequences and newsletters. Use when user says "email copy", "subject line", "preview text", "newsletter copy".
copy-humanize
Remove AI-sounding phrasing — cliché opener deletion, varied sentence rhythm, concrete experience injection, and a human-sounding rewrite pass. Use when user says "humanize", "make it sound human".
copy-landing-copy
Landing page copy — hero, above-the-fold structure, section order, benefit stack, and CTA copy for product pages, with message match from ad to page. Use when user says "landing page copy", "hero copy", "above the fold", "CTA copy".
copy-pr-outreach
PR outreach — newsworthiness test, press release structure, journalist pitch emails, embargo notes, and follow-up rules. Use when user says "press release", "media pitch", "PR outreach".
exec-decision-memo
Structures executive decisions — option set, reversibility test, weighted criteria, premortem, and a reviewable decision record. Use when user says "decision memo", "how to decide", or "premortem".
exec-executive-mentor
Executive mentoring for founders and C-level leaders — delegation levels, decision rights, calendar triage, and effective 1:1 cadence. Use when user says "executive mentor", "CEO coaching", "delegation", or .
exec-investor-update
Writes monthly investor updates — highlights, lowlights, metric tables, and specific asks — with consistent metric definitions and runway narrative. Use when user says "investor update", "board report", or .
Showing top 100 of 140 skills by quality score. Browse the full catalog at /browse.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.