Shotgun
Shotgun contiene 36 skills recopiladas de Krishnatejavepa, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
End-to-end technical execution, code, scripts, websites, automations, MVPs. Use for any request to build, fix, code, deploy, or automate anything.
Daily/weekly operating rhythm, standup, planning, review, "what should I work on". Use when the founder starts a work session, asks what's next, or wants a review of progress.
Brand identity and the visual system: brand kit, palette, typography, logo direction, design tokens, "set up my brand", "make it look consistent", visual briefs for landing pages, decks, and social assets. Writing voice is WRITE; marketing strategy is GROW; this skill owns how things LOOK.
Self-integrity checkup of the cofounder system: memory index consistency, loop registry, vault hygiene, git safety, secret leaks, skill health. Use when the founder says "checkup", "health check", "doctor", "something feels off", and monthly during a weekly review.
Distribution and launch execution: channel strategy, launch plans and checklists, growth experiments, "how do I get users", "nobody knows my product exists". Use for any request about marketing, launching, traffic, audience, or customer acquisition.
First-run setup, interview the founder, build their profile, map the venture, capture their writing voice, and organize their scattered data. Run automatically when memory/founder-profile.md does not exist, or when the founder says "onboard", "set up", or "start over".
Intelligently organize scattered files and business data into the vault. Use for any request about files, data cleanup, "where is X", imports of CSVs/sheets/exports, or when new data arrives.
The company-building roadmap: staged milestones from idea to scale. Use for "where am I", "what's next for the company", "show the roadmap", "what should the business do next", marking milestones done, or planning the next company stage. Today's task list is DAILY; this is the months-long path.
Sales execution and the CRM: ICP definition, prospecting, pipeline management, outreach drafting, follow-ups, consult calls, negotiation prep, closing. Use for "find me customers", "who should I sell to", "draft outreach", "update the pipeline", "prep me for this call". Selling to identified humans is SELL; getting broad attention is GROW.
Company infrastructure, guided and founder-owned: hosting and deploys, staging-to-prod publishing, domains and DNS, transactional email, database, Stripe payments, analytics wiring. Use for "set up payments", "get this live", "set up my domain", "add a database", "can people pay me yet". Writing app code is BUILD; this skill gets the company's rails ready.
Import, export, back up, or migrate the cofounder itself. Use when the founder says "back this up", "export everything", "move to my new laptop", "import my Obsidian vault", "import my Notion export", "import my Roam graph", "import my Google Docs", "import my Linear issues", "import my ChatGPT history", "make an advisor bundle", or asks how to take their cofounder somewhere else.
The Panel, a virtual team of specialists that critiques work before it ships, plus Debate Mode where the specialists argue trade-offs against each other. Use when the founder says "review this", "tear this apart", "what would a team say", "is this ready", "debate this", "argue it out", or before anything user-facing goes live.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Automated parsing of Stripe exports, Google Analytics screenshots, or raw CSV/text data dumps into canonical memory metrics. Trigger phrases: 'here is my stripe export', 'parse this csv', 'update my metrics from this', 'here is a screenshot of my dashboard'.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Structured decision support, prioritization, strategy, "should I X or Y", pricing, pivots. Use whenever the founder faces a choice with real consequences.
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
Metric hill-climbing loop (the Karpathy autoresearch pattern): autonomously improve a measurable number through many small keep-or-revert experiments. Use when the founder says "make X faster/better/cheaper", "optimize this", "squeeze more out of", and the quality can be expressed as a number a command can produce.
Used when the founder wants to log expenses, track revenue, calculate runway, or check the financial health of the venture. Trigger phrases: 'i spent', 'we made', 'whats my runway', 'survival mode', 'burn rate'
Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Generate localized compliance checklists, privacy policies, terms of service, and incorporation roadmaps based on the founder's country of operation. Trigger phrases: 'privacy policy', 'terms of service', 'gdpr', 'incorporate', 'legal compliance'.
Autonomous work loop, delegated tasks the agent iterates on alone until verifiably done. Use when the founder says "loop on this", "keep going until it works", "don't stop until", or delegates a bounded task and walks away.
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Answers questions about the world outside the repo: market and competitor analysis, customer discovery prep, tool and vendor comparisons, "what already exists for X", "who else does this". Use when the founder needs external facts, or when a DECIDE is missing a key number.
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
Used when the founder wants to debate an idea, bounce thoughts, get pushback, or explore a strategy without immediately deciding. Trigger phrases: 'what if we', 'im thinking about', 'argue with me on this', 'tear this idea apart', 'spar with me'
Used when the founder needs to triage user feedback, bugs, complaints, or emails without losing focus. Trigger phrases: 'user feedback', 'customer said', 'triage this bug', 'reply to this user'
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
Writes anything humans will read under the founder's name, in the founder's own voice: launch posts, emails, landing page copy, investor updates, social posts, changelogs. Use when the founder asks to write, draft, or punch up any prose. Not for code or technical docs inside a build.