rajitsaha

60 mods across 1 repository, 10 stars between them.

a11y-auditor

01

rajitsaha/100xprism

Skill Claude CodeCodex

Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for…

10 3d ago A 88 tokens original MIT

ab-test-setup

02

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion…

10 3d ago A 79 tokens copy · 86% MIT

ad-creative

03

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, full variations — for any paid platform; 'ad copy variations,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads.' For campaign strategy and targeting, see paid-ads. For landing page copy, see…

10 3d ago A 77 tokens copy · 84% MIT

ai-seo

04

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see…

10 3d ago A 90 tokens copy · 78% MIT

analytics-tracking

05

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to set up, improve, or audit analytics tracking and measurement — "GA4," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "attribution," "Mixpanel," "Segment," "are my events firing," or how to measure marketing results. For A/B test measurement, see…

10 3d ago A 86 tokens original MIT

architect

06

rajitsaha/100xprism

Skill Claude CodeCodex

Architectural decision advisor for cloud, data, and SaaS distributed systems. Use when the user asks "should we use X or Y", weighs a tradeoff, or needs a decision matrix, scaling analysis, cost-at-scale review, data-tier design, multi-tenancy model, or API/resilience guidance. For full technical blueprints, use…

10 3d ago A 74 tokens original MIT

branch

07

rajitsaha/100xprism

Skill Claude CodeCodex

Create a feature branch from the default branch with a descriptive, conventional name.

10 3d ago A 17 tokens original MIT

churn-prevention

08

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to reduce churn or build retention systems — 'cancel flow,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'customers are leaving.' For post-cancel win-back sequences, see email-sequence. For in-app upgrade paywalls, see…

10 3d ago A 85 tokens copy · 89% MIT

cloud-security

09

rajitsaha/100xprism

Skill Claude CodeCodex

Rigorous security and data privacy scan for cloud deployments. Covers GCP infrastructure hardening, data privacy (PII/GDPR/CCPA), API security, container security, and compliance. Audits deployed infrastructure and config — not a code-diff review.

10 3d ago A 56 tokens original MIT

cold-email

10

rajitsaha/100xprism

Skill Claude CodeCodex

Write B2B cold emails and follow-up sequences that get replies — "cold outreach," "prospecting email," "outbound email," "SDR emails," "nobody's replying to my emails." Covers subject lines, openers, body copy, CTAs, personalization, and multi-touch follow-ups. For warm/lifecycle sequences, see email-sequence. For…

10 3d ago A 88 tokens original MIT

commit

11

rajitsaha/100xprism

Skill Claude CodeCodex

Quality gate runs FIRST. Do NOT commit if any gate fails.

10 3d ago A 17 tokens original MIT

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants competitor comparison or alternative pages for SEO and sales enablement — 'alternative page,' 'vs page,' '[Product] vs [Product],' 'battle card,' 'competitor teardown.' Covers four formats: singular/plural alternatives, you vs competitor, competitor vs competitor. For sales-specific competitor…

10 3d ago A 74 tokens copy · 81% MIT

connect

13

rajitsaha/100xprism

Skill Claude CodeCodex

Connect, authenticate, and verify any SaaS CLI tool. Reads credentials from .env. Never prints secrets.

10 3d ago B 24 tokens original MIT

content-strategy

14

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to plan content strategy or decide what topics to cover — "what should I write about," "blog strategy," "topic clusters," "editorial calendar," "content pillars," "content roadmap," "I don't know what to write." For writing individual pieces, see copywriting. For SEO audits, see seo-audit. For…

10 3d ago A 81 tokens original MIT

context-dump

15

rajitsaha/100xprism

Skill Claude CodeCodex

Sync 7 days of GitHub activity (commits, PRs, issues, reviews) into a structured context dump. Optionally pull from Slack, GDrive, or Asana if configured. Use at the start of a session to get fully caught up before coding.

10 3d ago A 59 tokens original MIT

copy-editing

16

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to edit, review, or improve existing marketing copy — 'edit this copy,' 'proofread,' 'polish this,' 'tighten this up,' 'too wordy,' 'sharpen the messaging.' Use when copy exists and needs improving, not rewriting from scratch. For writing new copy, see copywriting.

10 3d ago A 73 tokens original MIT

copywriting

17

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to write, rewrite, or improve marketing copy for any page — homepage, landing, pricing, feature, about, or product pages; "headline help," "CTA copy," "value proposition," "tagline," "hero section," "make this more compelling," "conversion copy," or complete Figma-ready full-page copy (see…

10 3d ago A 108 tokens original MIT

data-query

18

rajitsaha/100xprism

Skill Claude CodeCodex

Run analytics queries against any database using plain English — BigQuery (bq CLI), PostgreSQL, MySQL, SQLite, or any DB with a CLI/MCP/API. Use when you need to pull metrics, analyze data, or answer business questions without writing SQL.

10 3d ago A 57 tokens original MIT

data-viz

19

rajitsaha/100xprism

Skill Claude CodeCodex

Act as a Senior Data Visualization Designer for dashboards, analytics pages, and chart-driven UI built in Recharts / visx / D3 / Plotly — chart-type decision tree, dashboard layout heuristics, color-blind safe palettes, empty/loading/error states, library trade-offs. For a one-off chart or plot, prefer a…

10 3d ago A 86 tokens original MIT

db

20

rajitsaha/100xprism

Skill Claude CodeCodex

Connect to any database — Cloud SQL, PostgreSQL, Snowflake, Databricks, Athena, Presto, or Oracle.

10 3d ago A 28 tokens original MIT

docs

21

rajitsaha/100xprism

Skill Claude CodeCodex

You are a documentation engineer. Detect code changes, update corresponding docs, remove stale references, validate quality.

10 3d ago A 23 tokens original MIT

email-sequence

22

rajitsaha/100xprism

Skill Claude CodeCodex

When the user wants to create or optimize an email sequence, drip campaign, or lifecycle email program — "nurture sequence," "onboarding emails," "welcome series," "re-engagement," "email automation," "email cadence," or any multi-email automated flow. For cold outreach, see cold-email. For in-app onboarding, see…

10 3d ago A 77 tokens copy · 86% MIT

enterprise-design

23

rajitsaha/100xprism

Skill Claude CodeCodex

Produce a comprehensive technical blueprint for a web product or SaaS, suitable for implementation in Figma Make, engineering sprints, and cloud deployment.

10 3d ago A 32 tokens original MIT

eval

24

rajitsaha/100xprism

Skill Claude CodeCodex

Run a 100xprism module's evals to check it triggers correctly and produces good output — "do my skills still trigger correctly," "did this change break a skill." Fans eval cases out to parallel subagents with Haiku-graded pass/fail scorecards. For authoring or benchmarking general-purpose skills, prefer a…

10 3d ago A 76 tokens original MIT