Menu
Skills in this repository
SkillsMP has collected 645 skills from whyzsm/tiny-agents. Open a skill to review its source and details.
whyzsm/tiny-agentsShowing 40 of 645 collected skills.
AIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource health, inspect logs, or run a comprehensive health check across cloud functions, CloudRun services, databases, and other…
Use when building, debugging, or evaluating CloudBase PostgreSQL / CloudBase PG / PG mode apps, including Postgres schema setup, queryPgDatabase/managePgDatabase, JS SDK v3 app.rdb() CRUD/RPC, PG HTTP API fallback, RLS-style permissions, username-password…
This is the required documentation for agents operating on the CloudBase Relational Database through MCP. It defines the canonical SQL management flow with `querySqlDatabase`, `manageSqlDatabase`, `queryPermissions`, and `managePermissions`, including MySQL…
Use when building frontend Web apps that talk to CloudBase Relational Database via @cloudbase/js-sdk – provides the canonical init pattern so you can then use Supabase-style queries from the browser.
Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-heavy requests.
Use when users need visual direction, interface hierarchy, layout decisions, design specifications, or prototypes before implementing a Web or mini program UI.
Use when users need to implement, integrate, debug, build, deploy, or validate a Web frontend after the product direction is already clear, especially for React, Vue, Vite, browser flows, or CloudBase Web integration.
CloudBase WeChat integration guide for Mini Program WeChat Pay, Official Account JSAPI Pay, Native QR-code Pay, Official Account OAuth, openid handling, payment callbacks, and CloudBase Integration Center generated functions. This skill should be used when…
CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, or AI agent development.
Deep codebase analysis workflow for architecture, execution flow, data flow, business rules, external dependencies, data models, DDD patterns, complexity, dependency maps, and technical-debt preparation. Use when the user asks to understand a codebase,…
Source text: Chinese
Code refactoring patterns and techniques for improving code quality without changing behavior. Use when cleaning up legacy code, reducing complexity, extracting methods, removing duplication, improving maintainability, planning refactor steps, or matching…
Chinese code review report assistant for Git diffs, PR diffs, code snippets, and changed files. Use when the user asks in Chinese or English to review code, inspect recent changes, review a PR, analyze a diff, produce Markdown/JSON/HTML review reports, or…
Source text: Chinese
Use when the user asks to turn a local skill bundle into "codex 可以安装的格式", package it cleanly, or install it into ~/.codex/skills. Best for SkillHub-style exports with manifest.json, zipped child skills, or mixed metadata.
Rigorous adversarial code review for finding bugs, edge-case failures, security holes, lazy patterns, performance risks, accessibility gaps, and maintainability problems. Use when the user asks for a strict code review, critical review, critique, PR risk…
Explicit helper for CRUD scaffolding and API endpoint generation. Do NOT load for: UI components, form design, database schema discussion, or general implementation.
Read-only cursor-agent delegate for questions/sanity checks (no writes). Triggers: ask cursor, cursor:ask, second opinion, sanity check. Skip for: implementation (use cursor:do).
Source text: Japanese
Delegate write task to Cursor Composer in isolated worktree, Lead-review + cherry-pick. Triggers: cursor:do, delegate to cursor, composer write, refactor with cursor. Skip for: planning, review-only, multi-task.
Source text: Japanese
Diagnose and recover Cursor backend failures for Harness workflows. Use when user invokes cursor:rescue, Cursor delegation fails, cursor-agent is missing, setup-cursor fails, or backend resolution unexpectedly falls back to claude.
Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain. Use when user invokes cursor:review, asks Cursor to review, or wants composer to sanity-check a diff. Cursor never owns…
Configure and verify Cursor backend for CCH. Triggers: cursor:setup, set Cursor as local default, check Cursor readiness. Distribution default stays opt-in; only local env changes on request.
Optional advanced tool for complex data modeling. For simple MySQL table creation, use relational-database-tool directly; for PostgreSQL / CloudBase PG schema work, use postgresql-development.
Deploy to Vercel/Netlify. One-way ticket to production arranged. Use when user mentions deployment, Vercel, Netlify, analytics, or health checks. Do NOT load for: implementation work, local development, reviews, or setup.
Source text: Mixed languages
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.
Generate project intro slides with Nano Banana Pro. Internal/manual workflow only; use from an explicit /generate-slide command or a parent media workflow.
Source text: Japanese
Auto-generate product demo videos. Internal/manual workflow only; use from an explicit /generate-video command or a parent media workflow. Requires Remotion setup.
Source text: Japanese
用于 OpenClaw 的技能管理工具，支持从 getskill.work 仓库搜索、下载和更新技能文件。提供 CLI 和编程接口，通过 API 搜索技能、通过 Git 克隆仓库、将技能目录复制到 OpenClaw skills 目录，并提供 Git 安装引导。
Source text: Chinese
gogcli for Google Workspace ops (Drive/Sheets/Docs/Slides). Triggers: list/search/export/read/update Google files, URL/ID parsing, auth selection. Skip for: non-Google storage, generic shell.
Acceptance Demo HTML for ship/wait/reject decision — reads stored acceptance_criteria. Triggers: 受け入れ判断, ship/wait/reject, 検収レビュー, acceptance demo. Skip for: implementation, review, release.
Source text: Japanese
Long-running task loop using /loop (Claude Code dynamic mode) and ScheduleWakeup to re-enter with fresh context on each wake-up. Internally invokes harness-work through Agent. Trigger: long-running, loop, wake-up, autonomous. Do NOT load for: one-shot task…
Source text: Japanese
Backend orchestration scorecard (Claude/Codex/Cursor) — HTML + terminal summary. Triggers: scorecard, backend usage, 自慢. Skip for: implementation, review, planning, release.
Source text: Japanese
Plan Brief HTML for pre-implementation preview (searches harness-mem for past decisions/patterns). Triggers: plan brief, planning preview, 計画概要, 計画レビュー. Skip for: implementation, review, release.
Source text: Japanese
HAR: Research-backed, team-validated task planning, Plans.md management, progress sync. Trigger: create a plan, add tasks, update Plans.md, mark complete, check progress. Do NOT load for: implementation, review, release.
Source text: Japanese
Progress Tracker HTML showing cc:WIP/cc:TODO/cc:完了 counts + drift alerts from Plans.md. Triggers: progress tracker, 進捗確認, 進捗ボード, dashboard. Skip for: implementation, review, release.
Source text: Japanese
Generic release automation for projects using Keep a Changelog + GitHub. Single confirmation gate then end-to-end automation: bump detection, CHANGELOG promotion, PR/main merge, tag, GitHub Release. Trigger: release, version bump, publish. Do NOT load for:…
Source text: Mixed languages
HAR: Multi-angle code, plan, scope review. Security/quality check. Trigger: review, code review, plan review, scope analysis. Do NOT load for: implementation, new features, bugfix, setup, release.
Source text: Mixed languages
HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror. Do NOT load for: implementation, review, release, planning.
Source text: Japanese
HAR: Sync Plans.md with implementation. Drift detect, marker update, retrospective. Trigger: sync-status, where am I, check progress. --snapshot for snapshots. Do NOT load for: planning, implementation, review, release.
Source text: Japanese
HAR: Execute Plans.md tasks from single task to full parallel team run. Trigger: implement, execute, do everything, breezing, team run, parallel, composer, composer 2.5. Do NOT load for: planning, review, release, setup.
Source text: Japanese
CloudBase official HTTP API client guide. This skill should be used when backends, scripts, or non-SDK clients must call CloudBase platform APIs over raw HTTP instead of using a platform SDK or MCP management tool.
Reuse this when the user asks things like "看看clash和atrust 是不是又干架了" or "看一下网终情况" on the Mac. It provides the repeatable low-level checklist for separating Clash proxy health from direct-routing or aTrust route problems.