Explore skills

Weekly newsletter — the parent piece of the week. ~600-1200 words. Drafted Sunday. Spawns 5-7 derivative short-form pieces for X / LinkedIn / Threads via /write Phase 5. The recurring Sunday default.

Structured diagnostic runbook for broken AI media pipelines. Walks through symptom → root cause → fix for generator auth failures, stale worker locks, review-app crashes, MCP auth errors, rate limits, and corrupted state files. Use whenever generation jobs fail, workers stop picking up tasks, generated output looks wrong, review tools break, MCP servers error, or any multi-component failure happen

Run CLIP-based quality scoring on AI-generated image frames against configurable thresholds. Returns a GOOD / PASS / FAIL verdict with per-metric breakdown (prompt match, character similarity, palette match, composite). Use whenever the user generates an AI frame and needs objective quality feedback, says "verify", "check quality", "CLIP score", "does this pass", "score this frame", "is this good

Comprehensive Claude Code plugin for yFiles for HTML development - includes skills for initialization, graph building, layouts, custom styling, and interactive features

Comprehensive Claude Code plugin for yFiles for HTML development - includes skills for initialization, graph building, layouts, custom styling, and interactive features

Comprehensive Claude Code plugin for yFiles for HTML development - includes skills for initialization, graph building, layouts, custom styling, and interactive features

Miki's rebase-and-reflect skill. Rebases the current branch onto the latest default branch, then reflects on the nature of what landed in the default branch and what it might mean for this branch. If the rebase gets complex (non-trivial conflicts, unexpected git state), flags and hands off to the user or model. Invoke when the user says "/miki-rebase-reflect", "rebase against main", "pull main and

Miki's session wrap-up check. Surveys the current conversation and working tree for anything outstanding before ending the session — open todos, uncommitted changes, unpushed commits, open PRs that haven't merged, background agents still running, follow-ups the conversation flagged but never closed, and stale references noticed but not fixed. Produces a short punch list, or confirms there's nothin

Persistent decision log that creates a read-write feedback loop: read previous decisions before starting work, respect or supersede them, and write new Y-statement records as you go. Activates during any task involving architectural, structural, or design decisions - choosing libraries, designing schemas, creating modules, making tradeoffs, selecting patterns. Also activates when DECISIONS.md alre

Complete best practices for using react-i18next and i18next in React Native / React projects. Trigger this skill when the user mentions internationalization, multilingual, i18n, i18next, react-i18next, translation files, namespace, language switching, locale, AI translation, or auto-translation. Applicable scenarios: setting up i18n architecture from scratch, namespace design for large-scale proje

Search indexed documents (PDF, Word, Excel, PPT, TXT) using BM25 keyword search. Use for EDA tools, company docs, bug reports, and technical documentation.

Comprehensive Claude Code plugin for yFiles for HTML development - includes skills for initialization, graph building, layouts, custom styling, and interactive features