スキルを探す

The project's Files under `/drives`: the user's own folder (their desktop, also at `~/Desktop`) and the folders shared with you, synced with the Kortix web app and every other session. Load before you read or save a file the user should keep, look for the user's notes, preferences or context, keep memory across sessions, or when you see a file named `... (conflict <date> <time>)...`.

日本語の概要は準備中です。原文の説明を表示しています。

How to cut a Kortix production release — the versioning philosophy (when patch vs minor vs major) and the exact flow: promote CURRENT main to staging, let the staging PR's checks be the gate, fix forward on main until it is green, then run Promote to Production and deploy + verify prod. Load WHENEVER the user wants to release, promote, cut/ship a version, publish a release, bump the version, or asks why a promotion is stuck. Load it too whenever another skill or doc needs to describe the release/promotion flow — this file is the one place it is written out in full.

日本語の概要は準備中です。原文の説明を表示しています。

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.

日本語の概要は準備中です。原文の説明を表示しています。

How to roll Kortix PRODUCTION back to an older already-released version — the inverse of a release. Covers the one-dispatch rollback-prod.yml engine, the per-surface mechanics (API + gateway = ECS Fargate image-tag swap; frontend = Vercel promote), the all-important Vercel frontend behavior (why a backend-only push can 'clobber' a FE rollback, and the 'don't rebuild the FE for backend-only pushes' skip that fixes it), the DB/migration-drift safety check that is the real blocker, and how a later promote returns prod to latest. Load WHENEVER the user wants to roll back / revert / downgrade / 'go back a version' on prod, asks how the rollback or the frontend clobber/skip behavior works, or needs to run rollback-prod.yml. Pairs with kortix-release (the forward direction).

日本語の概要は準備中です。原文の説明を表示しています。

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

日本語の概要は準備中です。原文の説明を表示しています。

Recipe: write platform-native social content for Kortix (LinkedIn posts, X threads, carousels, Instagram, TikTok, Reels and Shorts video scripts, content calendars) and repurpose one long-form piece into many. Load kortix-brand first for voice, positioning and claims. This skill covers platform mechanics: limits, hooks, cadence, repurposing. Use when the user asks for a LinkedIn post, Twitter or X thread, carousel, social calendar, "what should I post", "repurpose this", a video hook, a reel or short-form video.

日本語の概要は準備中です。原文の説明を表示しています。

Design and acceptance gates for centrally enforcing sandbox outbound network policy.

日本語の概要は準備中です。原文の説明を表示しています。

The project's episodic memory: a timestamped ledger of rules paid for with real outages and near-misses, one entry per incident. Load WHENEVER you write or review a DB migration or schema change, touch deploy/release workflows (.github/workflows/deploy-*, promote.yml, vercel config), plan a promote/release, respond to a prod incident, or when another skill references a learning. ALSO load after resolving any incident or near-miss: it must leave a new ledger entry in the same session.

日本語の概要は準備中です。原文の説明を表示しています。

Recipe: produce a Kortix image (hero, OG card, social card, thumbnail, cover, blog image, illustration, UI asset). Load kortix-brand first. This skill covers sizes, tools, generation, compositing and export. Use when the user asks to create, art-direct or revise an image for Kortix, agents, sandboxes, coding workflows, launch assets, thumbnails or covers.

日本語の概要は準備中です。原文の説明を表示しています。

The hard rules for editing `@kortix/sdk` (packages/sdk) — a PUBLISHED npm package with constraints no other package in this repo has: TDD is mandatory (failing test first, gates run and pasted every turn, explicit shippable YES/NO/NOT YET); exported names INCLUDING types are a public API contract and renaming one is a breaking change; the `version` field is inert and must never be hand-bumped; adding an export requires three synchronized edits; and a static import-graph tripwire enforces the framework-free core. Load WHENEVER you add, edit, rename, move, export, test, or delete anything under packages/sdk, or touch its streaming/transport layer.

日本語の概要は準備中です。原文の説明を表示しています。

How to change the database schema in this repo. Current engine: node-pg-migrate, with SQL generated from Drizzle schema changes when possible. Load whenever you add/alter/drop a table, column, enum, index, constraint, RLS/function/grant, or any file under packages/db/migrations.

日本語の概要は準備中です。原文の説明を表示しています。

Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.

日本語の概要は準備中です。原文の説明を表示しています。

Use for every Kortix test task, behavior change, bug fix, refactor, API route change, CLI change, SDK change, browser journey, test failure, coverage question, local benchmark, or testing infrastructure change. Enforce the single local-first runner, black-box flow contracts, package-local SDK tests, browser-only Playwright tests, and real input/output verification.

日本語の概要は準備中です。原文の説明を表示しています。

How to do feature work in this repo with git worktrees via `pnpm worktree`. Each worktree gets its own branch, its own block of app ports, its own node_modules, and by default shares the primary checkout's standard local Supabase DB for fast setup; pass `--db` only when a separate Supabase project/data plane is needed. Load WHENEVER starting a feature, bugfix, refactor, experiment, or any change you'll want to run/test in isolation; whenever the user mentions worktrees, isolated/parallel dev instances, running multiple branches at once, or 'spin up a worktree'; and whenever you need the exact non-interactive `pnpm worktree` commands and flags. Enforces: one canonical branch per objective, one worktree per branch — join the existing worktree instead of creating another.

日本語の概要は準備中です。原文の説明を表示しています。

Recipe: build, edit, present or record a Kortix deck or film (a Next.js route under /presentations in apps/web, never a file). Load kortix-brand first. This skill covers the slide engine, builds, presenter notes, films and QA. Load WHENEVER the user asks for a deck, slides, a presentation, a walkthrough, a talk track, a guided demo, presenter notes, or a product video; and whenever editing anything under apps/web/src/app/[locale]/presentations.

日本語の概要は準備中です。原文の説明を表示しています。

Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

日本語の概要は準備中です。原文の説明を表示しています。

Scores an inbound application against the role's written rubric with supporting quotes as evidence, writes a structured screen back to {{applications_source}}, and proposes interview slots on {{hiring_manager_calendar}} for strong matches. Never advances or rejects a candidate — every decision stays with the hiring manager.

日本語の概要は準備中です。原文の説明を表示しています。

The pull request loop for this repo: branch → commit → verify in your own box (local tests + local stack) → PR into main → demo video recorded with agent-browser on the local stack → `gh --attach` → self-merge → verify on dev. A PR into main runs no CI unless a person adds the `test` or `preview` label (one run each). Load when opening, updating, or finishing a pull request; when writing a PR body; when asking what CI runs where; when adding or explaining PR labels or the per-PR preview environment; or when attaching an image or video to a PR, issue, or comment.

日本語の概要は準備中です。原文の説明を表示しています。

Runbook for scoring and routing a new HubSpot lead to the right rep for {{projectName}} — territory matching, segment specialists, the stateless round-robin pool, intent scoring, HubSpot property writes, Slack notifications, and when to escalate an ambiguous lead to a human instead of guessing.

日本語の概要は準備中です。原文の説明を表示しています。

Drive Anthropic's Claude Code CLI (`claude -p`) as a non-interactive coding sub-agent from inside Codex. Use when you want to delegate a coding/analysis/refactor task to Claude, get a second opinion / adversarial review from another model, hand off long-context planning, or fan out parallel agents. Covers the exact `claude -p` flags, permission modes, output capture, JSON/stream-json modes, session resume, parallel fan-out, and the mandatory "delegate → capture → independently verify, never trust the self-report" supervision loop.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly win-loss analysis for HubSpot closed deals. Reads deals closed-won and closed-lost in the trailing {{lookback_days}}-day window, breaks outcomes down by segment, competitor, price, and the stage lost deals die in, clusters close reasons into themes, and posts themes plus recommendations to {{alert_channel}}. Read-only and report-only — never writes to a HubSpot deal.

日本語の概要は準備中です。原文の説明を表示しています。

Agentic end-to-end tests with e2e, the e2e runner. Covers scaffolding e2e.config.ts, picking the Playwright browser engine or the agent-device mobile engine, starting the app under test from the config, driving flows with agent.act, judging with agent.assert, agent.waitFor, and agent.extract, pinning values with screen, app, browser, and expect, shaping the agent (context, system prompt, tools, personas), the replay cache, the e2e CLI, reading .e2e/report.json, and bug bashes (parallel explore runs proven with repro tests). Use when a project depends on e2e, when asked for end-to-end, browser, mobile, or agentic UI tests, to bug bash or hunt for bugs, or when an e2e run fails.

日本語の概要は準備中です。原文の説明を表示しています。

Weekly SaaS spend audit loop for {{subscription_sheet}}. Pulls recurring card and bank charges from Plaid, reconciles them against the subscription register, flags duplicate/overlapping tools, unused seats, price hikes, upcoming renewals, and shadow IT, and posts a digest to {{alert_channel}} — recommending cancellations and downgrades only, never acting on them.

日本語の概要は準備中です。原文の説明を表示しています。

Daily runbook for tracking new customer accounts against onboarding milestones in Postgres and HubSpot for {{projectName}}. Covers the milestone framework, stall and overdue detection, nudge drafting, the owning-CSM alert, and the human approval gate before anything sends or changes account state.

日本語の概要は準備中です。原文の説明を表示しています。