All authors
Claude Skills by rajitsaha
github.com/rajitsaha84 skills0 installs0 views
- Referral ProgramWhen the user wants to create, optimize, or analyze a referral, affiliate, or word-of-mouth program — 'ambassador,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'affiliate payout.' For launch-specific virality, see launch-strategy.Votes: 0GitHub stars: 10
- ReleaseYou are a release engineer. Execute each phase in order. Each must fully complete before advancing. Do NOT ask for permission. Do NOT skip phases.Votes: 0GitHub stars: 10
- RevopsWhen the user wants help with revenue operations or the marketing-to-sales handoff — 'RevOps,' 'lead scoring,' 'lead routing,' 'MQL,' 'SQL,' 'pipeline stages,' 'deal desk,' 'CRM automation,' 'data hygiene,' 'leads aren't getting to sales.' For prospecting, see cold-email; drip campaigns, email-sequence; pricing, pricing-strategy.Votes: 0GitHub stars: 10
- Sales EnablementWhen the user wants sales collateral — 'pitch deck,' 'one-pager,' 'objection handling,' 'demo script,' 'talk track,' 'sales playbook,' 'proposal template,' 'buyer persona card,' 'help my sales team' — any asset that helps reps close deals. For comparison pages and battle cards, see competitor-alternatives; website copy, copywriting; prospecting, cold-email.Votes: 0GitHub stars: 10
- Schema MarkupWhen the user wants to add, fix, or optimize schema markup / structured data — "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "star ratings in search." For broader SEO, see seo-audit. For AI search optimization, see ai-seo.Votes: 0GitHub stars: 10
- SecurityYou are a security engineer. Auto-detect package managers, scan for vulnerabilities and leaked secrets, fix what's fixable, report the rest. Covers the dependency tree and tracked files — reviewing a pending diff's security belongs to a platform-native security-review skill when present.Votes: 0GitHub stars: 10
- Seo AuditWhen the user wants to audit or diagnose SEO issues — "technical SEO," "why am I not ranking," "meta tags review," "my traffic dropped," "Google update hit me," "core web vitals," "crawl errors," "indexing issues," or even a vague "my SEO is bad." For pages at scale, see programmatic-seo. For structured data, see schema-markup. For AI search, see ai-seo.Votes: 0GitHub stars: 10
- Signup Flow CroWhen the user wants to optimize signup, registration, account creation, or trial activation flows — "signup conversions," "registration friction," "signup form optimization," "signup abandonment," "reduce signup dropoff," "trial conversion rate," "too many steps to sign up." For post-signup onboarding, see onboarding-cro. For lead capture forms (not account creation), see form-cro.Votes: 0GitHub stars: 10
- Site ArchitectureWhen the user wants to plan, map, or restructure a website's page hierarchy, navigation, URL structure, or internal linking — "sitemap," "information architecture," "IA," "breadcrumbs," "what pages do I need," "how should I organize my site." NOT for XML sitemaps (technical SEO — see seo-audit). For structured data, see schema-markup.Votes: 0GitHub stars: 10
- Social ContentWhen the user wants to create, schedule, or optimize social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook — 'LinkedIn post,' 'Twitter thread,' 'content calendar,' 'viral content,' 'what should I post,' 'repurpose this content,' 'grow my following.' For broader strategy, see content-strategy.Votes: 0GitHub stars: 10
- SpecWrite a precise, implementation-ready spec before any code is written. Use when a feature request is vague, ambiguous, or complex — turn fuzzy requirements into an unambiguous spec with acceptance criteria, edge cases, API contracts, and data shapes. Run before /orchestrate or /commit. Produces a written spec document — downstream of any brainstorming/planning skill, not a replacement for one.Votes: 0GitHub stars: 10
- SubagentsUse subagents to throw more compute at hard problems, keep the main context window clean, and auto-approve safe permissions via hooks. Use when a task is complex, exploratory, or can be parallelized across multiple independent workstreams.Votes: 0GitHub stars: 10
- TechdebtFind and eliminate technical debt across the whole codebase — duplicated code, dead code, redundant abstractions. Use at the end of a coding session or when the codebase feels bloated. Reports findings and fixes them with user confirmation. Cleanups limited to the current working changes belong in a native simplify flow instead.Votes: 0GitHub stars: 10
- Terminal SetupGuide for optimal terminal and environment setup for Claude Code — Ghostty, statusline, tmux worktrees, voice dictation, and tab organization. Use when setting up a new machine or optimizing your Claude Code workflow.Votes: 0GitHub stars: 10
- TestYou are a senior test engineer. Auto-detect all test layers (unit, integration, frontend, backend, E2E/system), run them all, write more if coverage is below threshold, and loop until everything passes.Votes: 0GitHub stars: 10
- Update Claude MdAfter any correction from the user, update CLAUDE.md with a rule to prevent the same mistake from recurring. Use when the user corrects your behavior or says "don't do that again". Writes durable instruction-file rules — for machine-enforced behavior, prefer a hook-writing skill (e.g. hookify) or settings changes when available.Votes: 0GitHub stars: 10
- Visual System ArchitectAct as a Global Design Director to produce a complete design system — color palette, typography scale, 8px grid, 30+ components, responsive patterns, animations, and WCAG AA accessibility. Exports design tokens (JSON), CSS variables, and Figma-ready docs. Use when building a brand's visual foundation for Figma Make or a design handoff.Votes: 0GitHub stars: 10
- Plans> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. **Goal:** Ship `/pair-loop` — a coder↔reviewer handoff loop (roles swappable between `claude` and `codex`) that conducts each round through a local `HANDOFF.md`, self-instruments cost via `run_manifest.py`, enforces a per-run budget, and opens a PR carrying the transcript o...Votes: 0GitHub stars: 10
- BranchCreate a feature branch from the default branch with a descriptive, conventional name.Votes: 0GitHub stars: 10
- Cloud SecurityRigorous 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.Votes: 0GitHub stars: 10
- CommitCommit staged work with a conventional message after the quality gate passes. Use when the user asks to commit; never commits on a failing gate.Votes: 0GitHub stars: 10
- DbConnect to any database — Cloud SQL, PostgreSQL, Snowflake, Databricks, Athena, Presto, or Oracle.Votes: 0GitHub stars: 10
- DocsSync documentation with what shipped: refresh READMEs, guides and API references, and prune stale mentions. Use once a feature lands or when asked to refresh docs.Votes: 0GitHub stars: 10
- EvalRun 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 skill-creator plugin when present.Votes: 0GitHub stars: 10
- GateRun the pre-commit quality gate: test coverage, security scan, local build, plus Docker and cloud checks when applicable. Use before any commit or push; a failing gate blocks both.Votes: 0GitHub stars: 10
- LaunchYou are a release engineer. Execute each phase in order. Each must fully complete before advancing. Do NOT ask for permission. Stop only if something is truly unfixable.Votes: 0GitHub stars: 10
- LintDetect the project's linters and formatters, run them, and fix every error. Use when asked to lint or clean up style and type errors.Votes: 0GitHub stars: 10
- PackInstall, list, or uninstall optional vendor skill packs not bundled by default — "add the Databricks pack", "what packs are available", "is there a pack for X", "get me the Databricks skills".Votes: 0GitHub stars: 10
- Pair LoopCoder<->reviewer handoff loop (claude/codex/cursor/pi, roles swappable) with self-instrumented per-round cost tracking. Loops locally via HANDOFF.md until approved, then opens a PR with the full transcript.Votes: 0GitHub stars: 10
- PushPush the current branch after re-running the quality gate. Use when the user asks to push; never pushes on a failing gate.Votes: 0GitHub stars: 10
- ReleaseCut a versioned release: smoke-test the package, bump the version, tag, publish to PyPI/npm/Docker, and verify the published artifact. Use when asked to release or ship a version.Votes: 0GitHub stars: 10
- SecurityScan dependencies and tracked files for known vulnerabilities and leaked secrets; fix what's fixable, report the rest. For reviewing a pending diff, prefer a platform security-review skill.Votes: 0GitHub stars: 10
- SubagentsUse subagents to throw more compute at hard problems, keep the main context window clean, and auto-approve safe permissions via hooks. Use when a task is complex, exploratory, or can be parallelized across multiple independent workstreams.Votes: 0GitHub stars: 10
- TestDetect and run every test layer (unit, integration, E2E), add tests where coverage is below threshold, and loop until green. Use when asked to test or raise coverage.Votes: 0GitHub stars: 10