Coding & Dev Tools

kiyoraka Bundle

MUST use when user says 'save topic', 'save to topic diary', 'remember this under', 'review topic', 'list topics', or when a generic 'save' request needs routing between session memory, daily diary, topic diary, or all targets.

kiyoraka Bundle

Auto-triggers when a non-obvious decision is made during conversation. Also triggers on 'log decision', 'why did we choose', 'what was the trade-off', 'should we use A or B' (after resolution), or when user asks about past reasoning behind a choice.

kiyoraka Bundle

Auto-triggers when user says 'create songs', 'new album', 'create album', 'make music', 'muse this', 'write a song', 'create a song', 'compose', 'song from image', 'album from image', 'generate album', 'write songs', or when user shares an image and wants to create music from it.

kiyoraka Bundle

📋 Session Briefing — Skill Plugin

kiyoraka Bundle

Auto-triggers when user says 'new adventure', 'start adventure', 'new fantasy', 'save adventure', 'end adventure', 'load adventure', 'resume adventure', 'continue adventure', 'let's play', 'VN mode', or on numbered choice input (1-5) or free text dialogue during an active adventure.

kiyoraka Bundle

Auto-triggers on 'new project [name]', 'load project [name]', 'save project', 'list projects'. Also triggers on 'create project', 'resume project', 'open project', 'show projects', or when user mentions switching between active projects.

coolxeo Skill

Use this when a draft needs a structural read before line-edit — thesis, arc, and teach test first, style second.

coolxeo Skill

Use this when writing or expanding an article section by section. Never generate a full article in one shot.

coolxeo Skill

Core instructions on every turn: voice, first-run interview, day-two starter menu, sources, digests, anti-jobs.

coolxeo Skill

Use this when turning a seed, interview, or set of facts into a writing plan before drafting an article.

coolxeo Skill

Use this when writing or rewriting an X Article (long-form on x.com/i/article), with images between sections, a first-line hook, and no invented numbers.

coolxeo Skill

ALWAYS use this first when writing or editing any text that will be published (X, ads, LinkedIn, site). Strip AI slop without flattening the writer's voice. Source: petergyang/no-ai-slop.

coolxeo Skill

use this when opening or rewriting a pull request description, or when the user needs a visual explanation of code shape, flow, or structure — keep PR bodies easy to scan with the smallest clear diagram

coolxeo Skill

First-run watch-list interview. Also use when the user wants to reconfigure names, brands, URLs, or sources.

coolxeo Skill

Use this after drafting an article, before publish, to verify every factual claim and statistic against a named source.

coolxeo Skill

Use this when designing or creating a new Grok Bot. Ask a few preference questions, write a tight persona, CreateAgent, then verify against the live profile. Coding bots use pstack / poteto-mode as the quality bar. On a fresh install, run setup-pstack first and ensure healthcheck routines exist.

coolxeo Skill

Use when auditing Grok Bot routines for token waste, offering a fleet checkup after template import, deciding cadence, or running the standing routine-healthcheck wake.

coolxeo Skill

Use this when writing or adapting copy for X or LinkedIn so it matches the platform instead of sounding like a press release.

coolxeo Skill

Use when auditing Grok Bot fleet transcripts for user friction, proposing new skills/bots/routines from repeated corrections, or running the standing transcript-healthcheck routine.

erikuus Bundle

Manage authenticated Rahvusarhiivi virtuaalne uurimissaal (VAU) content through the user's existing Chrome session, including editing Estonian or English articles, translating the latest Estonian news into English, and managing feedback. Invoke this skill explicitly with `$vau` when those workflows are needed.

erikuus Bundle

Structured Codex, Claude, Amp, Pi, or Kimi code review when explicitly requested.

erikuus Bundle

Take a finished Git topic branch through one isolated autoreview, verified in-scope repairs, focused tests, intentional commits, push, draft pull-request creation, and required-CI handoff without merging. Use when the user explicitly invokes review-to-pr after implementation is committed and wants the branch reviewed and published as a concise, human-reviewable PR instead of entering a multi-reviewer polling loop.

erikuus Bundle

Turn a docs-heavy app planning or rewrite session into a reconstruction-grade, stack-neutral CONTEXT.md by grilling the user one question at a time. Use when the user has legacy architecture notes, UI descriptions, rationale, strengths and weaknesses, user feedback, migration intent, or product documents and wants to pressure-test the next version before implementation.

erikuus Bundle

Build project-root DESIGN.md and design-assets from screenshots, visual assets, styles, docs, and current app evidence as a stack-neutral visual source of truth for reimplementation. Use when the user wants to preserve or reconstruct an app's design, visual system, essential screens, responsive layouts, interaction states, or product-defining assets.

erikuus Bundle

Rebuild project-root SPEC.md from PLAN.md, DEVLOG.md, and current repo truth as a stack-neutral source-of-truth spec for reimplementation. Use when the user wants to synthesize the current implemented specification, rebuild SPEC.md, or reconcile the original plan with what the app actually became.

erikuus Bundle

Harvest a finished coding thread into project-root DEVLOG.md for projects that keep PLAN.md, DEVLOG.md, and SPEC.md. Use when the user wants to finalize a thread into project docs, harvest a finished thread, or backfill a dev log from the current thread or archived Codex session .jsonl files.

erikuus Bundle

Refactor AI-generated or difficult repository code to reduce complexity and human cognitive load while preserving behavior. Use when Codex must inspect real code and simplify excessive files, tiny functions, thin wrappers, pass-through layers, shallow abstractions, caller-specific APIs, speculative patterns, duplicated rules, configuration flags, special cases, unclear ownership, tangled error handling, or broad AI rewrites; then compare designs, implement a focused refactor, and verify it with available tests.

erikuus Bundle

Finalize an implemented GitHub issue by reconstructing the completed work from the current analysis or development thread, verifying the user-visible solution at a supplied application URL in authenticated Chrome, capturing screenshots, and publishing a concise, complete issue comment through the connected GitHub app. Use only when explicitly invoked with an exact GitHub issue URL and application URL after implementation or review work is complete.

erikuus Bundle

Toimeta AI loodud või inglise keelest tõlgitud eestikeelset tarbeteksti nii, et see oleks loomulik, korrektne, sidus, tähendustäpne ja sihtrühmale sobiv. Kasuta, kui palutakse eemaldada tekstist AI-likkus või tõlkekeele jäljed, teha keele- või sisutoimetamist, kontrollida tõlget originaali alusel, ühtlustada stiili ja termineid, parandada veeb-, turundus-, äri- või teabeteksti või kohandada seda Eesti lugejale.

erikuus Bundle

Evaluate how maintainable an AI-generated repository is for a repository-new human by running live maintenance probes in isolated disposable worktrees, withholding location hints, interviewing the developer about navigation and cognitive load, inspecting the resulting change and change reasoning, and producing an evidence-backed complexity diagnosis and refactor handoff. Use when Codex must measure change friction before or after a refactor, diagnose unclear ownership, duplication, coupling, obscurity, change amplification, cognitive load, or unknown-unknown risk, or compare whether one design is easier for developers to modify. Supports any language or framework and live-change, read-only walkthrough, retrospective, and before/after evaluation modes.

igoingdown Bundle

一个每日自我复盘的定时 loop 的设计与参考实现。每天读昨天所有 Claude Code session（可选叠加 IM 素材），用 headless claude 生成「日记 + 自我改进项」云文档，并维护一篇持续累积的自我改进计划。适合想用「定时 + headless AI 做每日复盘、沉淀改进项、追踪自我成长」的人参考。触发词：每日复盘、自动日记、自我改进闭环、headless 定时复盘、session 复盘、cron + claude -p 写日记。

igoingdown Bundle

查询 OpenRouter 账户余额（总额度、已使用、剩余额度）并通过飞书私聊通知。支持定时执行和手动触发。

igoingdown Skill

通用工程协作纪律——开工对齐、讲解风格、交付规范、分工边界、并行加速、反过度设计、决策树范式、测试完整性。使用时：承接任何工程任务（需求/排查/方案/改代码）开工前、写汇报/文档/讲解时、提交交付物时，都应比照本 skill 的硬规则执行。这些规则来自长期协作中被反复强调的要求，违反任何一条都大概率被打回重做。

igoingdown Skill

跨 session 工作考古——从历史 Claude Code session 里找回某项工作的结论、分支、PR 状态，并支持恢复(resume)。使用时：用户说"我之前在哪个 session 做过 X""找一下之前的分析结论""那个 session 是哪个？我怎么找不着了""那个 session 提的 PR 合了吗、合入了吗""我要 resume 那个 session"时触发。核心动作：关键词定位 transcript → 抽取结论与交付物 → 用 git/gh 对账真实状态 → 给出 resume 指引。

igoingdown Bundle

查询 Vultr 账户余额和当月待扣费用。使用时：用户询问 Vultr 账户余额、待扣费用或账户信息时触发。

igoingdown Bundle

按 UID 查用户在 Lindorm(LindormSearch/ES 兼容) 里的聊天原文。使用时：用户想查某个 UID(或反转 UID)在 chat history 索引里的聊天记录、会话原文、消息内容时触发。