all publishers

mizchi

@mizchi source repo

124 published skills · page 1 of 2

  1. ▌
    Justfile 2 · mizchi bundle
    Reference for just command runner. Provides justfile syntax and GitHub Actions examples.
    419 repo stars
  2. ▌
    Playwright CLI 2 · mizchi bundle
    Use when running Playwright via terminal CLI — `npx playwright test` (test runner), `codegen` (interactive recording), `screenshot` / `pdf` (one-off captures), and CI sharding. NOT for agent-driven real-time browser control (use `claude-in-chrome` MCP tools for that).
    419 repo stars
  3. ▌
    Vlmkit 2 · mizchi bundle
    Automatic frontend quality router. Use automatically whenever the user asks to create, edit, debug, validate, test, compare, migrate, or repair a frontend UI, HTML/CSS, screenshot implementation, responsive or interactive behavior, Playwright/VRT, or a visual regression. The user does not need to mention vlmkit or choose a sub-skill. Classify the request, load the bundled workflow, run the smallest deterministic gates, fix failures, and rerun to green.
    419 repo stars
  4. ▌
    Auto Markup 2 · mizchi
    End-to-end automatic markup — recreate a page or component as HTML/CSS from a target screenshot (or UI Contract IR), driven by deterministic signal tools with an optional VLM assist. Pipeline; scaffold the landmark skeleton (contract scaffold), converge composition (build page - missing/extra components, ordering, stacking gaps), converge each part (build component + report.json), then audit decoration (check palette / tokens / theme). Works with any agent model including Haiku; the tools are pure Playwright + pixel math, no API key required. Use when asked to implement markup from a design image, rebuild a page to match a reference, or prove a screenshot-to-HTML loop converges.
    419 repo stars
  5. ▌
    Mock Markup 2 · mizchi
    Markup from a mock image or screenshot — recreate a page as HTML/CSS when the only input is an exported design image (Figma export, retina screenshot, competitor-site capture) with no reference HTML. Normalizes @2x/@3x exports to CSS pixels (scan mock), then drives the deterministic verify-markup loop to a DONE verdict. Works with any agent model — the agent's own vision is the only VLM required, no API key; Haiku handles structure/spacing cheaply, hard 1px endgames measured to need Sonnet (see Model selection). Use when asked to "implement this mock", "turn this screenshot into HTML", or markup from an image that did not come from this repo's own capture tooling.
    419 repo stars
  6. ▌
    Component Vrt 2 · mizchi bundle
    Focus visual regression testing on ONE component instead of a whole page, so the diff is small enough to read and to hand to a model. Mounts a story from a Playwright component-testing gallery and screenshots only that component (`vlmkit check story`), then loops baseline → diff → fix → re-run to green. Includes copyable gallery reference implementations (vanilla / React / Vue) because Playwright ships no template for the gallery. Use when repairing or restyling a specific component, when a full-page diff is too noisy or cascades, or when a project wants per-component VRT baselines. Not for whole-page comparison (use vrt-visual-diff) or for generating browser tests from a spec (use spec-to-playwright).
    419 repo stars
  7. ▌
    Markup Assist 2 · mizchi
    General-purpose deterministic verification for any HTML/CSS work — no API key, no reference design required, no project setup. Route by task; run the matching vlmkit gate (integrity / copy / layout / breakpoints / scroll / handlers / interactions / verify markup); read the kickback; fix; re-run to green. Use whenever you wrote or edited markup and want to know if it is actually correct — broken-page defects, copy fidelity, responsive boundaries, keyboard operability, design-target match — instead of eyeballing a screenshot. Works standalone in any repo via `npx vlmkit`; this is the drop-in generalist skill, distinct from the full-workflow skills (auto-markup / mock-markup / dynamic-markup).
    419 repo stars
  8. ▌
    Dynamic Markup 2 · mizchi
    Markup with dynamic behavior — recreate a page whose requirements include responsive breakpoints, scrollable panels, and CSS animations from target screenshots plus a short motion brief, then prove the behavior with the deterministic dynamic-gate suite (check breakpoints / scan scroll / check animation / check motion). Static pixel convergence delegates to the auto-markup skill. Works with any agent model — the agent's own vision is the only VLM required, no API key; Haiku handles structure/spacing cheaply, hard 1px endgames measured to need Sonnet (see Model selection). Use when a markup task specifies how the page behaves (resizes, scrolls, animates), not just how one screenshot looks.
    419 repo stars
  9. ▌
    Vrt Visual Diff 2 · mizchi
    Compare two rendered pages (URL pairs or local HTML) and produce a structured Markdown report tailored for coding agents — pixel diff per viewport, per-section diffRatio, computed-style diff split into universal vs. breakpoint-gated, and worst-viewport screenshot paths. Use when the agent just made a UI change and needs to know whether it altered visible output, where it altered it, and which CSS properties drove the change. Works on a single HTML/URL pair without baseline state.
    419 repo stars
  10. ▌
    Markup Decompose 2 · mizchi
    Plan and sequence a whole-screen markup problem by decomposing it into components first, then routing each phase to the loop that fits it — outline extraction from a reference, per-component construction, and the handoff where a converged component is frozen as a story baseline so later edits are checked per component instead of per page. Use when the task is a whole screen or feature rather than one component, when a reference/mock exists and you need to decide the component boundaries before writing markup, or when converged markup needs to become maintainable. Not a build loop itself — it routes to auto-markup / mock-markup / dynamic-markup / component-vrt and defines the handoff between construction and maintenance.
    419 repo stars
  11. ▌
    Vrt CSS Fix Loop 2 · mizchi
    Closed-loop CSS auto-repair. Given a fixture with a known regression (one CSS property or one selector block removed), iterate with a VLM that proposes the missing fix from the diff screenshot, apply it, and re-run until the diff falls below a threshold. Currently scoped to the CSS-challenge fixture set in `src/experiments/css-challenge/`; adapting to an arbitrary repo requires writing a fixture entry. Use when measuring whether a VLM model can recover a known regression, not for production self-healing.
    419 repo stars
  12. ▌
    Vrt Markup Synth 2 · mizchi
    Five DOM/pixel-based signal tools for markup work — turn a screenshot + HTML scaffold into a converging pixel diff (build component), crop a page screenshot into per-component PNGs (scan component), audit hard-coded values against a design-token scale (check tokens), verify theme parity (check theme — light vs dark render), and stress-test layout under inflated text (stress i18n). All five are pure DOM + Playwright + pixel processing — **no VLM / no API key required**. The agent supplies the markup reasoning; the tool surfaces the signal. Use when you've authored HTML/CSS and want signal back without paying VLM latency or cost.
    419 repo stars
  13. ▌
    Spec To Playwright 2 · mizchi bundle
    Turn a natural-language spec into Playwright tests with deterministic, reproducible VRT and a self-healing loop. Uses the official init-agents planner/generator to explore the app and generate tests, a determinism layer to keep screenshots byte-stable, and @mizchi/vlmkit-heal to auto-fix failures. Use when authoring Playwright tests from a spec, making visual regression tests deterministic, getting generated tests to reproduce in CI, or healing tests that drift from the UI.
    419 repo stars
  14. ▌
    Vrt Migration Eval 2 · mizchi
    Evaluate whether a framework / CSS-library / build-system swap (Tailwind → vanilla CSS, reset-css switch, bundler swap, etc.) produced a visually-equivalent result. Three modes — compare (deterministic pixel + CSD), blind (agent runs without baseline reference), subagent (dispatched-agent verification) — let the caller pick the rigour level. Use when the diff is large by construction (the markup was rewritten) and a flat pixel diff would drown the actual regressions in noise.
    419 repo stars
  15. ▌
    Vrt Regression Watch 2 · mizchi
    Run vlmkit diff in a stateful loop where each run is compared against the previous run's persisted summary, surfacing a `⚠ REGRESSION` banner when the majority of viewports get worse. Designed for periodic CI gates (per-PR or scheduled) where you want "did this change make things worse" as a binary signal, not a one-shot snapshot. Stores summary at `.vlmkit/last-diff-for-agent.json` by default.
    419 repo stars
  16. ▌
    Agent Validation Loop 2 · mizchi
    Improve a developer-facing tool (CLI, library, agent harness) by running closed-loop validation with disposable subagents, treating their friction as the deliverable, fixing the friction, and re-running. Use when the user wants to evaluate or harden a tool whose value depends on whether an agent can use it — vrt-like signal loops, agent SDKs, CLI ergonomics, prompt scaffolding, IDE integrations. The loop produces both a stronger tool and a written record (per-run reports + tracked issues) of what was learned and why.
    419 repo stars
  17. ▌
    Playwright CLI · mizchi bundle
    Use when running Playwright via terminal CLI — `npx playwright test` (test runner), `codegen` (interactive recording), `screenshot` / `pdf` (one-off captures), and CI sharding. NOT for agent-driven real-time browser control (use `claude-in-chrome` MCP tools for that).
    419 repo stars
  18. ▌
    Gh Fix CI · mizchi bundle
    Use when GitHub Actions PR checks are failing on a pull request and need to be diagnosed or fixed. Inspects checks / logs via `gh`, drafts a fix plan, and implements only after explicit approval. Trigger on red checks, failing workflow runs, `pr is failing CI` reports — even if the user does not name a specific check. Out of scope: external CI (e.g. Buildkite) — report only the details URL.
    419 repo stars
  19. ▌
    Pkspec Maintenance · mizchi
    Use when working on github.com/mizchi/pkspec, especially release readiness, version bumps, GitHub Actions/Nix release checks, adapter DSL work, or the experimental Playwright/Vitest coverage presets. Covers the repo's spec gates, pkfire release flow, pkl CLI dependency gotchas, and what is intentionally still experimental.
    419 repo stars
  20. ▌
    Moonbit Mem Profile · mizchi
    Profile MoonBit memory/allocations with moon-pprof to find and fix allocation hotspots. Use when the user wants to memory-profile a MoonBit package, reduce allocations / GC pressure, investigate a slow hot path on the wasm backend, or mentions moon-pprof / samply / "memory profile" / "allocation profile" in this repo.
    419 repo stars
  21. ▌
    Mooncheat · mizchi bundle
    Moonbit cheatsheet to check syntax and corelibrary usages
    419 repo stars
  22. ▌
    Mmmd · mizchi bundle
    Render Markdown as terminal-friendly text or an HTML fragment. Mermaid fenced blocks become ASCII-art diagrams in TUI output.
    419 repo stars
  23. ▌
    TS Bridge Generator · mizchi
    Use when modifying the TypeScript-to-MoonBit bridge generator in this repo — `src/bridge/`, the `ts2mbt` CLI (generate / vendor / scaffold / package / bridge / ffi / decl), `bridge.mbti` / `bridge.mbt` / `bridge.js` synthesis, or the companion vite-plugin-moonbit integration.
    419 repo stars
  24. ▌
    Moonbit Dts Normalization · mizchi
    Use when modifying `mbt2ts normalize` (the MoonBit-generated `.d.ts` rewriter), `src/bridge/typescript_decl.mbt`, or the experimental normalizedDts integration in vite-plugin-moonbit.
    419 repo stars
  25. ▌
    Compiler Perf Profiling · mizchi
    Performance workflow for the vibe compiler — profiling a real compile with node --cpu-prof, running phase benches (__bench_ exports), reading hotspots, and the fix → fixpoint → regression validation loop. Use when compiles are slow, CI is slow, or a bench regressed.
    419 repo stars
  26. ▌
    Selfhost Miscompile Bisect · mizchi
    backend(gc/linear/RC)でコンパイルしたコンパイラ自身が誤動作するとき、probe entry の追記とフェーズ二分で miscompile を特定する手法。コンパイラの self-compile が hang する・誤った診断を出す・出力が linear と食い違うときに使う。
    419 repo stars
  27. ▌
    Actrun · mizchi
    actrun (ローカル GitHub Actions ランナー) の使い方リファレンスとワークフロー実行支援。actrun コマンドの提案、ワークフロー解析、実行プラン確認を行う。
    419 repo stars
  28. ▌
    Actrun Init · mizchi
    プロジェクトに actrun を導入する。インストール、actrun.toml 設定、ワークフロー調整をガイドする。
    419 repo stars
  29. ▌
    Actrun Debug · mizchi
    actrun の実行失敗を診断する。ログ解析、エラー原因特定、修正提案を行う。
    419 repo stars
  30. ▌
    Flaker Setup · mizchi
    Set up @mizchi/flaker on a new repository. Use when the user asks to introduce flaker, configure flaker.toml, integrate flaker into GitHub Actions, or "start using flaker on this project". Encodes the declarative apply-based onboarding flow for @mizchi/flaker 0.7.0+ (declarative apply model).
    419 repo stars
  31. ▌
    Flaker Management · mizchi bundle
    Operate @mizchi/flaker after setup. Use when the user asks how to run flaker day-to-day, review sampling and flaky metrics, design advisory vs required CI gates, promote or demote Playwright E2E or VRT checks, tune PR time budgets, run nightly triage, or manage quarantine and `@flaky` tags in an OSS repository. Targets @mizchi/flaker 0.7.0+ (declarative apply model).
    419 repo stars
  32. ▌
    Flaker Add Adapter · mizchi
    Add a new test-result adapter to flaker (parses an external report format into TestCaseResult[]). Use when the user asks to "add a flaker adapter for <X>", "make flaker import <some format>", "support <some test runner> in flaker import", or otherwise extends `flaker import --adapter <name>` with a new format. Encodes the file layout, registration step, test pattern, CHANGELOG convention learned from the chaosbringer adapter (#79).
    419 repo stars
  33. ▌
    Flaker Manual Release · mizchi
    Cut a flaker patch/minor release manually — branch → bump 3 version sites → CHANGELOG → PR → merge → tag → GitHub release → publish.yml OIDC publish. Use when the user asks to "release flaker N.N.N", "bump flaker", "publish flaker", or runs the equivalent in 日本語 ("flaker をリリース", "patch bump"). MAINTAINER-ONLY — only the npm OIDC trusted publisher (mizchi) can complete the publish step. Does NOT apply to chaosbringer (release-please) or other repos.
    419 repo stars
  34. ▌
    Bitflow Dependency Analysis Example · mizchi
    Use this skill when adding or updating the dependency-analysis example in this repository, including workflow.star design, changed-path target selection, and executable validation with moon run.
    419 repo stars
  35. ▌
    Check Similarity · mizchi
    Detect duplicate code using AST-based similarity analysis. Auto-selects the right tool based on file types in the project (similarity-ts for TypeScript/JavaScript, similarity-py for Python, similarity-mbt for MoonBit, similarity-rs for Rust, etc).
    419 repo stars
  36. ▌
    Check Similarity Py · mizchi
    Detect duplicate Python code using AST-based similarity analysis. Use when working with .py files and looking for code duplication or refactoring opportunities.
    419 repo stars
  37. ▌
    Check Similarity Rs · mizchi
    Detect duplicate Rust code using AST-based similarity analysis. Use when working with .rs files and looking for code duplication or refactoring opportunities.
    419 repo stars
  38. ▌
    Check Similarity TS · mizchi
    Detect duplicate TypeScript/JavaScript code using AST-based similarity analysis. Use when working with .ts/.tsx/.js/.jsx files and looking for code duplication or refactoring opportunities.
    419 repo stars
  39. ▌
    Check Similarity Mbt · mizchi
    Detect duplicate MoonBit code using AST-based similarity analysis. Use when working with .mbt files and looking for code duplication, refactoring opportunities, or enforcing code quality.
    419 repo stars
  40. ▌
    Luna · mizchi bundle
    Use whenever working with `mizchi/luna` in the luna.mbt repo — writing CSR examples, fixing reactivity bugs (effects re-running on unrelated signal changes), adding new luna features, or onboarding to luna's mental model. This is the unified entry point; pick the right reference page below for the specific situation.
    419 repo stars
  41. ▌
    Astra Ssg · mizchi
    astra-ssg
    419 repo stars
  42. ▌
    Sol Bootstrap · mizchi
    Use when running `sol new` for the first time, when `sol <subcommand>` fails with `failed to resolve path mizchi/sol/cmd/sol_js` / `Run this command inside a MoonBit project that depends on mizchi/sol.`, or when moving from `sol dev` to `sol build` / `sol serve` for the first time. Covers (a) the bootstrap rules — `sol new <name> --user <ns>` works in an empty directory as of sol 0.22.2, but `--cloudflare` / `--doc` / `--dev` still need a host moon project, and every non-new subcommand needs `.mooncakes/mizchi/sol/` locally (= `moon install` after `sol new`) — (b) the sol 0.22.x scaffold layout (`app/server/routes.mbt` holds routes + page handlers; `app/layout/` is a separate package; `/` and `/about` are pre-registered) and (c) the production flow gotchas (`sol build` writes to two directories, `sol serve` does NOT rebuild, dev & prod both default to :7777).
    419 repo stars
  43. ▌
    Creating Luna App · mizchi
    Use when scaffolding a new standalone CSR app that uses luna (@luna_ui/luna) outside the luna.mbt monorepo — running `npx @luna_ui/luna new`, choosing TSX vs MoonBit, or fixing a broken `--mbt` scaffold (moon build `_bench` import error, or vite `failed to resolve import "mbt:..."`).
    419 repo stars
  44. ▌
    Sol Cloudflare Deploy · mizchi
    Use when deploying sol_app (or any sol-built MoonBit SSR worker) to Cloudflare Workers, debugging error 10021, or extending sol/examples/sol_app/scripts/patch-cloudflare-globals.mjs. Captures the global-scope I/O traps in MoonBit core + sol's generated bundle and the wrangler ASSETS binding URL layout.
    419 repo stars
  45. ▌
    Playwright Pnpm Workspace · mizchi
    Use when running Playwright tests in this repo (luna.mbt) and either the test fails to discover specs ("did not expect test.describe()" / "two different versions of @playwright/test") or you're adding a new playwright config under astra/ or sol/. Captures the version-skew between root and per-package @playwright/test pins.
    419 repo stars
  46. ▌
    Auto Markup · mizchi
    End-to-end automatic markup — recreate a page or component as HTML/CSS from a target screenshot (or UI Contract IR), driven by deterministic signal tools with an optional VLM assist. Pipeline; scaffold the landmark skeleton (contract scaffold), converge composition (build page - missing/extra components, ordering, stacking gaps), converge each part (build component + report.json), then audit decoration (check palette / tokens / theme). Works with any agent model including Haiku; the tools are pure Playwright + pixel math, no API key required. Use when asked to implement markup from a design image, rebuild a page to match a reference, or prove a screenshot-to-HTML loop converges.
    419 repo stars
  47. ▌
    Mock Markup · mizchi
    Markup from a mock image or screenshot — recreate a page as HTML/CSS when the only input is an exported design image (Figma export, retina screenshot, competitor-site capture) with no reference HTML. Normalizes @2x/@3x exports to CSS pixels (scan mock), then drives the deterministic verify-markup loop to a DONE verdict. Works with any agent model — the agent's own vision is the only VLM required, no API key; Haiku handles structure/spacing cheaply, hard 1px endgames measured to need Sonnet (see Model selection). Use when asked to "implement this mock", "turn this screenshot into HTML", or markup from an image that did not come from this repo's own capture tooling.
    419 repo stars
  48. ▌
    Component Vrt · mizchi bundle
    Focus visual regression testing on ONE component instead of a whole page, so the diff is small enough to read and to hand to a model. Mounts a story from a Playwright component-testing gallery and screenshots only that component (`vlmkit check story`), then loops baseline → diff → fix → re-run to green. Includes copyable gallery reference implementations (vanilla / React / Vue) because Playwright ships no template for the gallery. Use when repairing or restyling a specific component, when a full-page diff is too noisy or cascades, or when a project wants per-component VRT baselines. Not for whole-page comparison (use vrt-visual-diff) or for generating browser tests from a spec (use spec-to-playwright).
    419 repo stars
  49. ▌
    Markup Assist · mizchi
    General-purpose deterministic verification for any HTML/CSS work — no API key, no reference design required, no project setup. Route by task; run the matching vlmkit gate (integrity / copy / layout / breakpoints / scroll / handlers / interactions / verify markup); read the kickback; fix; re-run to green. Use whenever you wrote or edited markup and want to know if it is actually correct — broken-page defects, copy fidelity, responsive boundaries, keyboard operability, design-target match — instead of eyeballing a screenshot. Works standalone in any repo via `npx vlmkit`; this is the drop-in generalist skill, distinct from the full-workflow skills (auto-markup / mock-markup / dynamic-markup).
    419 repo stars
  50. ▌
    Dynamic Markup · mizchi
    Markup with dynamic behavior — recreate a page whose requirements include responsive breakpoints, scrollable panels, and CSS animations from target screenshots plus a short motion brief, then prove the behavior with the deterministic dynamic-gate suite (check breakpoints / scan scroll / check animation / check motion). Static pixel convergence delegates to the auto-markup skill. Works with any agent model — the agent's own vision is the only VLM required, no API key; Haiku handles structure/spacing cheaply, hard 1px endgames measured to need Sonnet (see Model selection). Use when a markup task specifies how the page behaves (resizes, scrolls, animates), not just how one screenshot looks.
    419 repo stars
  51. ▌
    Vrt Visual Diff · mizchi
    Compare two rendered pages (URL pairs or local HTML) and produce a structured Markdown report tailored for coding agents — pixel diff per viewport, per-section diffRatio, computed-style diff split into universal vs. breakpoint-gated, and worst-viewport screenshot paths. Use when the agent just made a UI change and needs to know whether it altered visible output, where it altered it, and which CSS properties drove the change. Works on a single HTML/URL pair without baseline state.
    419 repo stars
  52. ▌
    Markup Decompose · mizchi
    Plan and sequence a whole-screen markup problem by decomposing it into components first, then routing each phase to the loop that fits it — outline extraction from a reference, per-component construction, and the handoff where a converged component is frozen as a story baseline so later edits are checked per component instead of per page. Use when the task is a whole screen or feature rather than one component, when a reference/mock exists and you need to decide the component boundaries before writing markup, or when converged markup needs to become maintainable. Not a build loop itself — it routes to auto-markup / mock-markup / dynamic-markup / component-vrt and defines the handoff between construction and maintenance.
    419 repo stars
  53. ▌
    Vrt CSS Fix Loop · mizchi
    Closed-loop CSS auto-repair. Given a fixture with a known regression (one CSS property or one selector block removed), iterate with a VLM that proposes the missing fix from the diff screenshot, apply it, and re-run until the diff falls below a threshold. Currently scoped to the CSS-challenge fixture set in `src/experiments/css-challenge/`; adapting to an arbitrary repo requires writing a fixture entry. Use when measuring whether a VLM model can recover a known regression, not for production self-healing.
    419 repo stars
  54. ▌
    Vrt Markup Synth · mizchi
    Five DOM/pixel-based signal tools for markup work — turn a screenshot + HTML scaffold into a converging pixel diff (build component), crop a page screenshot into per-component PNGs (scan component), audit hard-coded values against a design-token scale (check tokens), verify theme parity (check theme — light vs dark render), and stress-test layout under inflated text (stress i18n). All five are pure DOM + Playwright + pixel processing — **no VLM / no API key required**. The agent supplies the markup reasoning; the tool surfaces the signal. Use when you've authored HTML/CSS and want signal back without paying VLM latency or cost.
    419 repo stars
  55. ▌
    Spec To Playwright · mizchi bundle
    Turn a natural-language spec into Playwright tests with deterministic, reproducible VRT and a self-healing loop. Uses the official init-agents planner/generator to explore the app and generate tests, a determinism layer to keep screenshots byte-stable, and @mizchi/vlmkit-heal to auto-fix failures. Use when authoring Playwright tests from a spec, making visual regression tests deterministic, getting generated tests to reproduce in CI, or healing tests that drift from the UI.
    419 repo stars
  56. ▌
    Vrt Migration Eval · mizchi
    Evaluate whether a framework / CSS-library / build-system swap (Tailwind → vanilla CSS, reset-css switch, bundler swap, etc.) produced a visually-equivalent result. Three modes — compare (deterministic pixel + CSD), blind (agent runs without baseline reference), subagent (dispatched-agent verification) — let the caller pick the rigour level. Use when the diff is large by construction (the markup was rewritten) and a flat pixel diff would drown the actual regressions in noise.
    419 repo stars
  57. ▌
    Vrt Regression Watch · mizchi
    Run vlmkit diff in a stateful loop where each run is compared against the previous run's persisted summary, surfacing a `⚠ REGRESSION` banner when the majority of viewports get worse. Designed for periodic CI gates (per-PR or scheduled) where you want "did this change make things worse" as a binary signal, not a one-shot snapshot. Stores summary at `.vlmkit/last-diff-for-agent.json` by default.
    419 repo stars
  58. ▌
    Agent Validation Loop · mizchi
    Improve a developer-facing tool (CLI, library, agent harness) by running closed-loop validation with disposable subagents, treating their friction as the deliverable, fixing the friction, and re-running. Use when the user wants to evaluate or harden a tool whose value depends on whether an agent can use it — vrt-like signal loops, agent SDKs, CLI ergonomics, prompt scaffolding, IDE integrations. The loop produces both a stronger tool and a written record (per-run reports + tracked issues) of what was learned and why.
    419 repo stars
  59. ▌
    SQL Lint · mizchi bundle
    Static lint for sqlc-style SQL catalogs. Catches duplicate query names, missing semicolons, SELECT *, double-wildcard LIKE, and other cheap-but-easy-to-miss mistakes. Optional sqlfluff integration for full style coverage.
    419 repo stars
  60. ▌
    Vlmkit · mizchi bundle
    Entry-point for the `@mizchi/vlmkit` toolkit — VLM-driven frontend kit covering visual regression (snapshot / diff / regression-watch), markup synthesis from screenshots, design-token / theme / a11y / i18n audits, and a 2-stage VLM + LLM CSS auto-repair loop. Use when a coding agent has edited HTML/CSS and needs to know whether the visible output changed, where it changed, and which CSS properties drove the change — or when the task is markup-from-image / token / theme audit / fix-loop driven by VLM. This skill orients you to the 5 detailed sub-skills (vrt-visual-diff / vrt-migration-eval / vrt-markup-synth / vrt-regression-watch / vrt-css-fix-loop) and the verb-group CLI; pick the matching sub-skill once the task shape is clear.
    419 repo stars
  61. ▌
    SQL Security · mizchi bundle
    SQL injection screening for host code (MoonBit / TS / Rust) plus secretlint setup notes. Flags single-line template-literal or string-concat SQL builders, regardless of value source — the scanner is line-based and does NOT trace data flow, so a clean scan is not proof of safety (multi-line template literals are missed) and every hit needs a manual review or an explicit `// sql-security: ok` opt-out.
    419 repo stars
  62. ▌
    Waxa Eval · mizchi bundle
    Use when iterating on a skill's prompt with the waxa CLI (https://github.com/mizchi/skills/tree/main/tools/waxa) — authoring scenarios, choosing graders, interpreting unclear-points, advancing a ledger, and judging convergence. Encodes the four-stage iteration pattern observed in real iter loops (structural fix → grader breadth → surface-form coverage → residual unclear) and the scenario-design pitfalls (blank-slate executor's network limit, prompt expectation explicitness, regex coverage of Japanese/English surface forms). Meta-skill: do NOT auto-invoke for routine skill edits; fires only when the user explicitly runs waxa or asks for a skill-quality eval.
    419 repo stars
  63. ▌
    SQL Plan Audit · mizchi bundle
    Run EXPLAIN QUERY PLAN against every query in a sqlc-style catalog and diff the plans against a baseline. Detects new full-table SCANs and TEMP B-TREE sort scans introduced by PRs. SQLite/D1-only today; engine extension noted below.
    419 repo stars
  64. ▌
    Review Image · mizchi bundle
    Review screenshots or other images with OpenRouter vision models via bundled Deno scripts. Use for quick VRT sanity checks, invalid-image screening, or CI gates. `scripts/review-image.ts` returns freeform feedback; `scripts/review-image-ci.ts` returns strict `pass|fail` JSON and exits non-zero on fail.
    419 repo stars
  65. ▌
    Node Sqlite Vec · mizchi bundle
    Use when setting up Node 24+ built-in `node:sqlite` with the loadable `sqlite-vec` extension for vector / RAG storage in TypeScript without `better-sqlite3`, or when debugging vec0 BigInt rowids, vitest hanging on sqlite-vec, `.ts` import errors under `node:sqlite`, or "sqlite extension not loadable". Covers extension loading, vitest incompatibility (use `node --test`), tsconfig flags, and CLI shebang. Trigger on `node:sqlite`, `sqlite-vec`, vec0 / vector storage even when the user does not name better-sqlite3.
    419 repo stars
  66. ▌
    Dotenvx · mizchi bundle
    Use when working with the `dotenvx` env-var management tool — encrypting .env files, juggling multiple environments (.env.production / .env.staging / .env.ci), committing encrypted secrets to git with `.env.vault` / `.env.keys` / `.env.encrypted`, or wiring dotenvx into GitHub Actions. Trigger on `.env.vault` / `.env.keys` / `dotenvx` commands or symptoms (env-var leak risk, env per-stage management, encrypted secrets workflow) even if the user does not say "dotenvx" by name.
    419 repo stars
  67. ▌
    Otel Node · mizchi bundle
    Node.js OpenTelemetry setup — SDK init, auto-instrumentation packages, and the esbuild ESM silent-failure gotcha (instrumentation-* packages produce no spans when bundled with esbuild --format=esm). Use when adding OTel to a Node.js/Hono/Express service or debugging missing spans after bundling. See devops/opentelemetry for signal design decisions.
    419 repo stars
  68. ▌
    SQL Schema Audit · mizchi bundle
    Index coverage and N+1 review aids for SQLite/D1 schemas with a sqlc catalog. Surfaces unused indexes (with FK CASCADE awareness so cascade-load-bearing indexes are not flagged), queries that scan tables without index help, and `for`-loops calling generated SQL fns.
    419 repo stars
  69. ▌
    Justfile · mizchi bundle
    Reference for the `just` command runner — justfile syntax and GitHub Actions integration. Use when an existing repo already has a `justfile` and tasks must be added, modified, or audited. For new mizchi-owned repos, prefer the `pkfire` skill (`Taskfile.pkl` + `pkf`) instead; justfile is kept only for compatibility with existing repos.
    419 repo stars
  70. ▌
    AWS Vault Mfa Iam · mizchi bundle
    Use when AWS account の IAM API が MFA 必須 policy で弾かれて、 `sts:GetCallerIdentity` は通るのに `iam:*` が `InvalidClientTokenId` で拒否されるとき、 または FIDO2 passkey で MFA が CLI から使えないとき。 aws-vault / aws-cli / MFA / passkey 関連で「アクセス拒否」 「token expired」 「IAM 操作のみ失敗」 等の症状から起動 (user が aws-vault を名指しでなくても OK)。
    419 repo stars
  71. ▌
    Cloudflare Deploy · mizchi bundle
    Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
    419 repo stars
  72. ▌
    Skill Finder · mizchi bundle
    Use ONLY when the user explicitly asks to discover or evaluate a skill from OUTSIDE the curated catalog — e.g., "find a Stripe skill", "is there a skill for X?", "evaluate this candidate before adopting". Meta-skill, complementary to skill-selector: do NOT auto-invoke on routine apm-management, project-init, or catalog-resident requests. Cross-source survey across vetted registries (Anthropic official, claude-skill-registry, VoltAgent/awesome-agent-skills, ComposioHQ, Superpowers, GitHub topic) with a mandatory waxa-eval adoption gate.
    419 repo stars
  73. ▌
    Apm Usage · mizchi bundle
    Reference for APM (Agent Package Manager) — apm.yml syntax, install / uninstall / update commands, target detection, lockfile workflow. Read when you need exact field names, but do NOT auto-invoke on every apm-related task; user prompts about projects with installed skills can be handled with general APM knowledge. Invoke explicitly when the user mentions APM by name, asks to author or audit an apm.yml, or runs into an unfamiliar APM command / error.
    419 repo stars
  74. ▌
    Nix Setup · mizchi bundle
    Set up reproducible dev environments via devbox (Nix-backed) or pure Nix flakes. Templates for MoonBit, Rust, TypeScript+pnpm, Python+uv, Haskell, OCaml, OxCaml preloaded with just / ast-grep / apm. Covers devbox.json, buildNpmPackage, direnv, GitHub Actions, and bootstrapping in sandboxed envs (Claude Code web). Use when starting, adding, or troubleshooting a Nix or devbox setup.
    419 repo stars
  75. ▌
    Frontend Review CI · mizchi bundle
    Use when CI is slow (>10 min), flaky, or the user asks to optimize GitHub Actions for a frontend project. Analyzes `gh run list` history, identifies bottleneck steps, proposes sharding / cache / concurrency improvements. Runs `scripts/audit-ci.sh`.
    419 repo stars
  76. ▌
    Gleam Practice · mizchi bundle
    Use when writing or reviewing Gleam code on the Erlang target — especially Wisp + Mist HTTP services, OTP-based processes (gen_server / supervisor analogues), justfile workflows, gleeunit testing, `gleam format`, GitHub Actions CI, and performance measurement. Trigger on `gleam.toml`, `.gleam` files, or Erlang/BEAM-related symptoms even if the user does not say "Gleam" by name.
    419 repo stars
  77. ▌
    Skill Selector · mizchi bundle
    Meta-skill for picking project skills via APM. Invoke ONLY when the user explicitly asks to set up apm.yml, choose which skills a project needs, or evaluate a catalog match — do NOT auto-invoke on routine project-init or apm-management tasks. Two-phase: pick from a curated catalog first; only escalate to broader search/evaluation when the catalog has no fit. Avoids the failure mode of impulse-installing skills you never use or hand-searching GitHub when a vetted answer already exists.
    419 repo stars
  78. ▌
    Opentelemetry · mizchi bundle
    Platform-agnostic OpenTelemetry reference — signal selection (traces/metrics/logs), span design, context propagation (W3C TraceContext), sampling strategies, and OTLP exporter config. Use before writing any OTel instrumentation to get design decisions right. Platform-specific skills (devops/otel-node, cloudflare/workers-otel-utels) layer on top of this.
    419 repo stars
  79. ▌
    Frontend Review Deps · mizchi bundle
    Use when auditing dependency health — outdated packages, CVE triage with attack-vector weighting, deprecated/declining library detection (trend-watch). Runs `audit-deps.sh` and `audit-trend-watch.sh`. Pairs with `frontend-review-security` for the full security picture.
    419 repo stars
  80. ▌
    Pi Coding Agent · mizchi bundle
    Use when embedding `@mariozechner/pi-coding-agent` as a coding-agent runtime in Node scripts, writing pi extensions (plugins) with `pi.registerTool` / `pi.registerCommand` / `pi.on`, packaging and `pi install` from npm/git, or picking between the SDK and `pi --mode rpc` for non-Node hosts. Covers session setup, the cwd × tools factory trap, TypeBox tool schemas, and the `peerDependencies` rule. Trigger on `pi-coding-agent`, `pi.registerTool`, `pi install`, or "embed a coding agent into Node" descriptions even when pi is not named.
    419 repo stars
  81. ▌
    Frontend Review State · mizchi bundle
    Use when reviewing state management architecture — classifying state types (server/URL/form/UI), checking for over-globalization, Jotai/Zustand/Redux patterns, derived state, and logout/cache invalidation. Covers checklist 23-state-management.md.
    419 repo stars
  82. ▌
    Moonbit Practice · mizchi bundle
    MoonBit code generation and packaging best practices. Use when writing MoonBit code to avoid common AI mistakes with syntax, tests, and benchmarks, or when defining and publishing a Wasm executable with SKILL.md for the MoonBit Skills Marketplace.
    419 repo stars
  83. ▌
    Extract Glossary · mizchi bundle
    指定されたリポジトリ、複数リポジトリ、または GitHub organization から、ドメイン固有の専門用語、業界用語、社内・プロダクト用語、リポジトリ実装マップ、技術構成、オンボーディング向け Mermaid 構成図を抽出・生成するときに使う。ユーザーが「用語集を作る」「ドメイン辞書を作る」「オンボーディング資料にする」「repo/org を見て専門用語をまとめる」「AI が再確認しなくてよい知識ベースを作る」と依頼したら起動する。
    419 repo stars
  84. ▌
    Frontend Review Triage · mizchi bundle
    Use when starting a frontend review engagement or when the user asks for an initial assessment ("triage", "day 0", "what's the state of this repo"). Reads package.json, README, gh issues, and produces a scorecard covering lockfiles, TypeScript strictness, testing, CI, and known issues. Runs `scripts/audit-triage.sh`.
    419 repo stars
  85. ▌
    Frontend Review Weekly · mizchi bundle
    Use for the weekly AI review. Orchestrates all frontend-review-* skills in order, dispatches the 5 perspective sub-skills in parallel, diffs against last week's KPIs, and produces a weekly report that feeds the ratchet.
    419 repo stars
  86. ▌
    Mizchi Blog Style · mizchi bundle
    Japanese-language style guide and AI-tone detection rubric for mizchi-authored blog posts (zenn / dev.to). Includes a subagent dispatch procedure that scores a draft on two axes — looks-like-mizchi vs sounds-AI-generated. Use after drafting an article during the style-matching revision loop.
    419 repo stars
  87. ▌
    Dep Lib Review · mizchi bundle
    Periodic dependency review for Node.js/pnpm projects — outdated package triage, security audit, update batching strategy (patch/minor/major), validation checklist. Run monthly or before major releases. Use when asked to review or update dependencies in a repo.
    419 repo stars
  88. ▌
    Frontend Review Hygiene · mizchi bundle
    Use when assessing code quality hygiene — TypeScript strictness, lint violations, dead code, and duplication. Runs `audit-typescript.sh`, `audit-lint.sh`, `audit-similarity.sh`. Does NOT cover dependency freshness or CVE audit — use `frontend-review-deps` for that.
    419 repo stars
  89. ▌
    Frontend Review Testing · mizchi bundle
    Use when auditing test infrastructure — vitest coverage, playwright configuration, VRT setup, coverage merging. Produces recommendations for Week 2 testing phase. Runs `scripts/audit-coverage.sh`.
    419 repo stars
  90. ▌
    Moonbit JS Binding · mizchi bundle
    Write MoonBit bindings to JavaScript with `extern "js"`. Use for FFI declarations against browser/Node/Deno APIs or npm packages, wrapping JS objects in opaque types, bridging Promises (`async fn` / `Promise::wait()`), `moon.pkg` exports (esm/cjs/iife), and null/undefined at the JS boundary.
    419 repo stars
  91. ▌
    Playwright Test · mizchi bundle
    Best practices and reference for Playwright Test (E2E). Covers how to write tests, avoiding fixed waits, network triggers, DnD, shard/retry setup on GitHub Actions, and more. Use when writing, reviewing, or configuring CI for Playwright tests.
    419 repo stars
  92. ▌
    Actions CI Tuning · mizchi bundle
    Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.
    419 repo stars
  93. ▌
    Frontend Review Security · mizchi bundle
    Use when conducting a frontend security review — static analysis (risky HTML patterns, env var exposure), authentication/authorization audit (token storage, route guards, logout), and AI self-penetration testing. Runs `scripts/audit-security.sh`. For CVE triage and deprecated library detection, use `frontend-review-deps`.
    419 repo stars
  94. ▌
    Tech Trend Watch · mizchi bundle
    Long-term technology stack review using State of JS, State of CSS, and Thoughtworks Technology Radar — satisfaction×usage matrix, ADOPT/TRIAL/ASSESS/HOLD mapping, P0–P3 migration priority. Use for annual stack audits, planning major migrations (jest→vitest, webpack→Vite, etc.), or on-demand replacement decisions. Not for general architecture design.
    419 repo stars
  95. ▌
    Formal Methods Reconciler · mizchi bundle
    Use when reconciling software specs, docs, tests, configs, code, logs, or incidents with formal methods. Helps Codex extract claims, decide whether docs or implementation are the source of truth, choose an appropriate tool such as Z3, Alloy, TLA+, P, Dafny, MoonBit prove, Lean, Rocq, Why3, Verus, CBMC, Tamarin, or ProVerif, build the smallest useful model, run or plan verifier checks, and translate SAT/UNSAT, traces, proof failures, or proof obligations into domain-language questions and regression guards.
    419 repo stars
  96. ▌
    K8S Crd From Typed Schema · mizchi bundle
    Use when generating Kubernetes CustomResourceDefinitions from a typed schema source (zod / TypeBox / Valibot / json-schema). Covers the Structural Schema dialect's restrictions, the /status subresource trap, the metadata-prohibition rule, and plural inflection — the four pitfalls that bite on first attempt.
    419 repo stars
  97. ▌
    Ts2moonbit Migration · mizchi bundle
    Migrate a TypeScript codebase to MoonBit on the `js` target while keeping the same JavaScript API contract, using mizchi/js (JS/Web/Node bindings), mizchi/x (cross-target async backend: process/fs/http/ws), and mizchi/npm_typed (npm bindings). Use when porting a TS library, Node service, npm package, or Cloudflare Worker to MoonBit and the existing JS/TS consumers, `.d.ts`, and tests must keep working unchanged.
    419 repo stars
  98. ▌
    Retrospective Codify · mizchi bundle
    Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.
    419 repo stars
  99. ▌
    Ast Grep Practice · mizchi bundle
    Operate ast-grep as a project lint tool. Covers sgconfig.yml, fix/rewrite rules, constraints, transform, testing, and CI. Use when writing rules ast-grep can express but general-purpose linters cannot.
    419 repo stars
  100. ▌
    Cloudflare Workers CD Rollback · mizchi bundle
    GitHub Actions CD for a Cloudflare Worker with auto-rollback on smoke failure. Use when you want push-to-deploy with safety: capture pre-deploy version, deploy, smoke, rollback if smoke fails.
    419 repo stars