Explore skills

Miki's personal pre-self-review loop. Iteratively runs /review on the current PR and addresses obvious issues until only minor nits remain or 3 iterations have run. Surfaces judgment calls back to the user, makes atomic commits per project convention, pushes once at the end. Invoke when the user says "/miki-review-loop", "loop the review", "iterate on the review", or similar after a PR has been cr

Parallel review of a draft along multiple focuses (voice, structure, slop, hook, closer, optional factual). Spawns N subagents concurrently — each with a single focus and the user's writing-style — then aggregates findings into one severity-grouped report. Use full mode mid-draft or as a pre-publish gate; use delta mode (--since-last / --since <ref>) to review only what changed since the last snap

LinkedIn carousel — multi-slide PDF post (8–10 slides typical). Derives from a long-form piece OR a strong listicle / how-to topic. Use when repurposing a published long-form into LinkedIn's highest-engagement format, or when a user has a step-by-step / numbered insight that benefits from one-idea-per-slide pacing.

Short-form post (X single / LinkedIn / Threads) stating a single observation. No list, no contrast — just one thing noticed clearly and named. Use when the user has a one-line insight, pattern, or quiet contrarian take that doesn't need scaffolding to land.

Short-form (X / LinkedIn) comparison of how something is done today vs how it will be done in 1–5 years. Strong for tech / AI / tooling takes. Use when the user wants to frame a directional bet, a tooling shift, or an obsolescence call — anything where the punchline is "this is the present; here's the future".

Destila una guía de estilo de escritura desde 3-5 muestras de referencia y 1-2 textos propios. Genera `scribetronic/style/writing-style.md` con las 8 secciones (voice, structure, sentence-level, signature moves, anti-patterns, ejemplos +, ejemplos -, revision checklist). Usar cuando el usuario quiera crear o refrescar la guía de estilo de su blog/newsletter.

Propone deltas concretos a `scribetronic/style/writing-style.md` (la guía de voz personalizada del usuario) a partir del historial real de edición del usuario (draft vs publicado). No reescribe automáticamente — genera un documento de propuestas con evidencia textual obligatoria. Invocar tras 3+ piezas publicadas o cuando el usuario sienta drift de voz.

Short-form motivational post within your niche (X / LinkedIn / Threads). WARNING — easiest format to slide into AI slop / coach-speak. Use when you have a personal-stakes statement or hard truth tied to a specific moment in your work — never as generic inspiration. Hard quota: 1-2 per month max.

Use this skill when the user is mid-build and drifting, scope is creeping, or focus is lost. Trigger on "ship focus", "scope check", "refocus", "what should I cut", "am I scope creeping", "this is getting bigger than expected", "I'm losing focus", "I keep finding things to improve", "should I stop and ship what I have", or "new requirements came in". Also trigger when the user expresses frustratio

Use this skill when the user wants a code review before shipping, merging, or deploying. Trigger on "ship review", "review my changes", "code review", "review my diff", "is this ready to ship", "is this ready to merge", "check this over before I push", "brutal review", "kind review", "pre-ship review", or when the user says they've finished building and wants feedback. Also trigger when the user i

Audit a project's Claude Code setup against official Anthropic documentation. Evaluates 9 areas: CLAUDE.md, Rules, Skills, Sub-agents, Hooks, Permissions, Settings, MCP servers, and Feature Selection. Produces a scored AUDIT-REPORT.md with findings that cite documentation sources fetched during the session. Use this skill when the user says 'audit', 'audit my setup', 'review my Claude Code config'

Cross-document and cross-code coherency analysis — finds contradictions, conflicting values, and inconsistencies across multiple files, then researches official sources to resolve factual errors and asks the user only about preference decisions. MUST use this skill whenever the user asks to compare, cross-check, cross-reference, or verify consistency between 2+ files of any type — docs, configs, c