Vaibtan
- 23 skills
- 0 followers
- 4 hours ago last updated
- ▌ How · vaibtan bundleExplain how a subsystem works by tracing executable entrypoints, types, state, dependencies, and tests. Use for $how, code walkthroughs, ownership questions, or architecture grounding before a change. Use $why for historical motivation.
- ▌ Why · vaibtan bundleReconstruct why code or a product decision exists from source history, issues, documents, conversations, observability, and analytics. Use for $why, design rationale, regressions, postmortems, or data-backed thresholds. Use $how for execution behavior.
- ▌ Arena · vaibtan bundleRun several independent attempts at the same artifact, select a base against a rubric, and graft only compatible strengths. Use for $arena or a consequential design or implementation bakeoff.
- ▌ Swarm · vaibtan bundleFan out independent slices, races, or coverage checks to Codex subagents and aggregate one evidence-backed report. Use for $swarm or explicitly parallel work.
- ▌ Recall · vaibtan bundleRebuild current working context for a topic from scoped Codex task history, repository state, and available shared records. Use for $recall, catch-me-up requests, or resuming earlier work.
- ▌ Unslop · vaibtan bundleEdit prose to remove canned AI phrasing, vague abstractions, choppy fragments, and inflated framing while preserving meaning. Use for $unslop or as the final writing pass in $poteto-mode.
- ▌ Prelude · vaibtan bundlePrelude bootstrapping for TypeScript. Use when creating or rebuilding a prelude.ts from ambient generic helpers and types.
- ▌ Reflect · vaibtan bundleReview a completed or long-running task for reusable workflow lessons and propose focused skill improvements. Use only when the user asks to reflect or capture lessons.
- ▌ Architect · vaibtan bundleDesign types, contracts, call flows, and module boundaries before implementation. Use for $architect, architecture work, or an implementation-ready technical specification.
- ▌ Automate Me · vaibtan bundleCreate or refine a personal Codex mode skill from the user's demonstrated working preferences. Use for $automate-me or requests to capture a recurring working style as a skill.
- ▌ Interrogate · vaibtan bundleAdversarially review a diff, design, or implementation with independent lenses and a final evidence audit. Use for $interrogate, multi-model review, stress testing, or finding blind spots.
- ▌ No Comments · vaibtan bundleReview changed code for comments that narrate implementation, preserve dead history, or claim unenforced invariants, then fix only accepted findings. Use for $no-comments before code review.
- ▌ Poteto Mode · vaibtan bundleRun a rigorous pstack engineering workflow in Codex. Use when the user invokes $poteto-mode or asks for pstack-style investigation, implementation, verification, review, shipping, or sustained autonomous work.
- ▌ Blast Radius · vaibtan bundleFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
- ▌ Setup Pstack · vaibtanConfigure pstack model and reasoning profiles for Codex. Use when the user asks to set up pstack, change its budget, or route roles across GPT-5.6 Sol, Terra, Luna, or the parent model.
- ▌ Figure It Out · vaibtan bundleDesign an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for $figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
- ▌ Install Anti Slop · vaibtan bundleInstall, configure, update, or upgrade vendored anti-slop Oxlint plugins. Use when adding anti-slop, picking up upstream rules or fixes, or migrating an existing installation while preserving local customizations.
- ▌ Show Me Your Work · vaibtan bundleKeep a compact decision trail for long-running or unattended work. Use for $show-me-your-work when a reviewer needs evidence for important choices and verification.
- ▌ Technical Writing · vaibtan bundleLayered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for $technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
- ▌ Create Verification Skill · vaibtan bundleGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for $create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
- ▌ Typescript Best Practices · vaibtan bundleApply focused TypeScript type, boundary, module, and test guidance. Use when $poteto-mode reads or edits .ts or .tsx files, or when the user explicitly asks for the integrated TypeScript standards.
- ▌ Cloudflare Composition Root · vaibtan bundleComposition roots for Hono and Cloudflare. Use when adding a binding-backed service or refactoring raw runtime dependencies out of inner code.
- ▌ Maintain Verification Skill · vaibtan bundlePeriodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for $maintain-verification-skill or "audit the verify skill".