sampx — AI Agent Skills on SkillsAuth

skill-deployer

This skill deploys skills from the workspace's source code directory for skill development to the corresponding agent skills directory. You should use this skill when the user requests to deploy, install, or synchronize a skill. Or, when the skill has undergone code optimization, you should inquire with the user about using this skill for installation and deployment.

development1

mac-reminder

Manage personal todos via macOS Reminders.app. ⚠️ MUST use when user asks to "add a todo", "remind me", "记一下", "加个待办", "待办列表", "完成待办", "查看待办", or any personal task/reminder management. 🔴 Trigger even when user doesn't explicitly say "reminder" if the intent is personal task tracking. Use todowrite for session-level coding steps; use dev-flow for product plans.

development1

opencode-config

Edit opencode.jsonc, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false

tools1

skill-master

⚠️ MUST LOAD BEFORE any skill operation (install/update/deploy). Provides skill lifecycle commands (find/download/scan/install). Triggers on skill search, installation, INBOX management, or skill quality queries.

testing1

ai-ref-creator

Converts lengthy official product documentation into concise, high-density AI references. Use when users request: (1) Documentation compression or condensing, (2) Creating AI-friendly reference materials, (3) Reducing token usage for large documentation, (4) Extracting technical specifications from official docs

testing1

skill-security-scanner

Security scanner for AI agent skills. Scans skills or directories for malicious code including C2 infrastructure, reverse shells, credential exfiltration, malware markers, dynamic code execution, and JS obfuscation. Default JSON output for AI agents. Use after downloading any new skill.

development1

binary-download-test

Test sample with binary download patterns

testing1

git-worktrees

Workspace-level Git worktree management for parallel development across multiple branches. Supports dynamic project validation and automated dependency installation. Use this skill when creating isolated development environments or working on multiple features in parallel.

development1

dev-flow

Issue / Plan 驱动的开发工作流。⚠️ 只有当任务以 GitHub Issue 或 Plan 作为执行载体时才使用本技能。必须使用本技能的场景： - 开发、修复、重构某个 GitHub Issue（如 "#14"、"这个 issue"、"处理 issue 120"） - 创建、修改、推进、验证、归档 Plan - 用户要求“写个方案 / 出个计划 / 开始开发 / 继续开发 / 执行计划”，且任务会通过 Plan 落地执行 - 从 PRD 拆分 Issue 不使用本技能的场景： - spec 驱动流程（Spec / OpenSpec / spec-first / spec-kit） - 单纯研究、讨论、解释、评审 - 不需要 Issue 或 Plan 承载的临时小改动 🔴 判断标准：任务是否要进入 “Issue / Plan → 实施 → 验证 → 归档” 这条开发链路。只有是，才使用本技能。依赖：git-worktrees 技能（可选，用于隔离开发环境）

development1

automating-mail

Automates Apple Mail via JXA with AppleScript dictionary discovery. Use when asked to "automate email", "send mail via script", "JXA Mail automation", or "filter email messages". Covers accounts, mailboxes, batch message filtering, composition, attachments, and UI fallback.

tools1

agent-orchestration

Orchestrate OpenCode agent with OpenSpec-driven workflows and worktree isolation. Use when you need to: (1) Drive OpenCode with OpenSpec artifacts (proposal/design/specs/tasks), (2) Execute tasks in background with process-adapter, (3) Monitor and interact with background agent sessions, (4) Use worktree for isolated development. This skill is for Wopal to coordinate OpenCode as an execution unit.

development1

automating-mail

Automates Apple Mail via JXA with AppleScript dictionary discovery. Use when asked to "automate email", "send mail via script", "JXA Mail automation", or "filter email messages". Covers accounts, mailboxes, batch message filtering, composition, attachments, and UI fallback.

tools1

crafting-rules

创建或修改 OpenCode 规则文件时使用。帮助从对话历史中提取模式、分析项目约定（AGENTS.md、linter、package.json），并生成格式正确的规则。触发条件：用户想创建规则、固化重复指令、跨会话持久化指导、或为特定文件/主题定制 Agent 行为。

development1

git-worktrees

Workspace-level Git worktree management for parallel development across multiple branches. Supports dynamic project validation and automated dependency installation. Use this skill when creating isolated development environments or working on multiple features in parallel.

development1

mac-reminder

Manage personal todos via macOS Reminders.app. ⚠️ MUST use when user asks to "add a todo", "remind me", "记一下", "加个待办", "待办列表", "完成待办", "查看待办", or any personal task/reminder management. 🔴 Trigger even when user doesn't explicitly say "reminder" if the intent is personal task tracking. Use todowrite for session-level coding steps; use dev-flow for product plans.

development1

js-obfuscation-test

JavaScript obfuscation patterns for testing detection

development1

malware-sample

Malicious skill sample for testing detection

testing1

clean-skill

A clean skill with no malicious patterns for testing

testing1

wsf-add-backlog

Add an idea to the backlog parking lot (999.x numbering)

tools1

wsf-add-phase

Add phase to end of current milestone in roadmap

tools1

wsf-code-review

Review source files changed during a phase for bugs, security issues, and code quality problems

development1

wsf-discuss-phase

Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (the agent picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).

data-ai1

wsf-docs-update

Generate or update project documentation verified against the codebase

development1

wsf-intel

Query, inspect, or refresh codebase intelligence files in .planning/intel/

development1

wsf-join-discord

Join the WSF Discord community

tools1

wsf-list-workspaces

List active WSF workspaces and their status

tools1

wsf-add-tests

Generate tests for a completed phase based on UAT criteria and implementation

testing1

wsf-new-milestone

Start a new milestone cycle — update PROJECT.md and route to requirements

tools1

wsf-new-project

Initialize a new project with deep context gathering and PROJECT.md

tools1

wsf-new-workspace

Create an isolated workspace with repo copies and independent .planning/

tools1

wsf-next

Automatically advance to the next logical step in the WSF workflow

tools1

wsf-pause-work

Create context handoff when pausing work mid-phase

tools1

wsf-plan-phase

Create detailed phase plan (PLAN.md) with verification loop

data-ai1

wsf-progress

Check project progress, show context, and route to next action (execute or plan)

testing1

wsf-quick

Execute a quick task with WSF guarantees (atomic commits, state tracking) but skip optional agents

data-ai1

wsf-research-phase

Research how to implement a phase (standalone - usually use /wsf-plan-phase instead)

research1

website-doc-scraper

Scrapes website pages to Markdown with state management and deduplication. Supports Fast Path (single page), Layer Mode (incremental crawling), and Site Mode (full discovery).

development1

fae-collab

Wopal 与 Fae 协作的完整生命周期指南。⚠️ **MUST load before ANY delegation to fae** — 委派、检查、监控、验证、收尾全覆盖。🔴 Trigger: "委派"、"delegate"、"让 fae 执行"、"fae 任务"、"检查 fae 状态"、"取消任务"、"fae 协作"、或任何意图将任务交给 fae 执行的场景。**严禁不加载本技能就直接委派任务给 fae，这是严重失职。**

tools1

wsf-audit-fix

Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit

testing1

wsf-add-todo

Capture idea or task as todo from current conversation context

tools1

wsf-autonomous

Run all remaining phases autonomously — discuss→plan→execute per phase

data-ai1

wsf-audit-milestone

Audit milestone completion against original intent before archiving

testing1

wsf-check-todos

List pending todos and select one to work on

testing1

wsf-cleanup

Archive accumulated phase directories from completed milestones

tools1

wsf-insert-phase

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

testing1

wsf-pr-branch

Create a clean PR branch by filtering out .planning/ commits — ready for code review

development1

wsf-code-review-fix

Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.

development1

wsf-analyze-dependencies

Analyze phase dependencies and suggest Depends on entries for ROADMAP.md

testing1

wsf-complete-milestone

Archive completed milestone and prepare for next version

tools1

wsf-audit-uat

Cross-phase audit of all outstanding UAT and verification items

testing1

wsf-debug

Systematic debugging with persistent state across context resets

development1

wsf-execute-phase

Execute all plans in a phase with wave-based parallelization

tools1

wsf-do

Route freeform text to the right WSF command automatically

tools1

wsf-manager

Interactive command center for managing multiple phases from one terminal

tools1

wsf-fast

Execute a trivial task inline — no subagents, no planning overhead

data-ai1

wsf-health

Diagnose planning directory health and optionally repair issues

data-ai1

wsf-list-phase-assumptions

Surface the agent's assumptions about a phase approach before planning

data-ai1

wsf-forensics

Post-mortem investigation for failed WSF workflows — analyzes git history, artifacts, and state to diagnose what went wrong

data-ai1

wsf-import

Ingest external plans with conflict detection against project decisions before writing anything.

testing1

wsf-plan-milestone-gaps

Create phases to close all gaps identified by milestone audit

testing1

wsf-note

Zero-friction idea capture. Append, list, or promote notes to todos.

tools1

wsf-map-codebase

Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents

development1

wsf-profile-user

Generate developer behavioral profile and create Claude-discoverable artifacts

development1

wsf-help

Show available WSF commands and usage guide

documentation1

wsf-plant-seed

Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone

tools1

wsf-review-backlog

Review and promote backlog items to active milestone

tools1

wsf-ship

Create PR, run review, and prepare for merge after verification passes

tools1

wsf-remove-phase

Remove a future phase from roadmap and renumber subsequent phases

tools1

wsf-review

Request cross-AI peer review of phase plans from external AI CLIs

tools1

wsf-explore

Socratic ideation and idea routing — think through ideas before committing to plans

tools1

wsf-resume-work

Resume work from previous session with full context restoration

tools1

wsf-remove-workspace

Remove a WSF workspace and clean up worktrees

tools1

wsf-reapply-patches

Reapply local modifications after a WSF update

tools1

wsf-milestone-summary

Generate a comprehensive project summary from milestone artifacts for team onboarding and review

tools1

wsf-session-report

Generate a session report with token usage estimates, work summary, and outcomes

business1

wsf-ui-phase

Generate UI design contract (UI-SPEC.md) for frontend phases

development1

wsf-settings

Configure WSF workflow toggles and model profile

data-ai1

wsf-scan

Rapid codebase assessment — lightweight alternative to /wsf-map-codebase

development1

wsf-undo

Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.

testing1

wsf-set-profile

Switch model profile for WSF agents (quality/balanced/budget/inherit)

testing1

wsf-thread

Manage persistent context threads for cross-session work

tools1

wsf-stats

Display project statistics — phases, plans, requirements, git metrics, and timeline

tools1

wsf-workstreams

Manage parallel workstreams — list, create, switch, status, progress, complete, and resume

tools1

wsf-secure-phase

Retroactively verify threat mitigations for a completed phase

testing1

project-worktrees

项目级 Git worktree 管理工具，面向协同 Agent 设计。支持在项目 .worktrees 目录下创建隔离开发环境，自动依赖安装和测试验证。

data-ai1

crafting-rules

创建或修改 OpenCode 规则文件时使用。帮助从对话历史中提取模式、分析项目约定（AGENTS.md、linter、package.json），并生成格式正确的规则。触发条件：用户想创建规则、固化重复指令、跨会话持久化指导、或为特定文件/主题定制 Agent 行为。

development1

fae-collab

Wopal 与 Fae 协作的完整生命周期指南。⚠️ **MUST load before ANY delegation to fae** — 委派、检查、监控、验证、收尾全覆盖。🔴 Trigger: "委派"、"delegate"、"让 fae 执行"、"fae 任务"、"检查 fae 状态"、"取消任务"、"fae 协作"、或任何意图将任务交给 fae 执行的场景。**严禁不加载本技能就直接委派任务给 fae，这是严重失职。**

tools1

git-submodule

管理 Git 子模块的工作流指南。适用于：(1) 在主项目中包含外部仓库，(2) 跨多个项目管理共享库，(3) 将依赖锁定到特定版本，(4) 管理 monorepo 架构的独立组件，(5) 克隆/更新/移除子模块，(6) 处理嵌套子模块。

tools1

base64-legit-test

Legitimate Base64 usage for testing whitelist

testing1

dynamic-code-test

Dynamic code execution patterns for testing detection

development1

skills-research

Search and download AI agent skills from the skills.sh ecosystem. Use when user wants to find skills, download skills to INBOX for evaluation, or explore available skills from GitHub repositories.

data-ai1

url-shortener-test

URL shortener patterns for testing detection

testing1

opencode-config

Edit opencode.jsonc, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false

tools1

skill-master

⚠️ MUST LOAD BEFORE any skill operation (install/update/deploy). Provides skill lifecycle commands (find/download/scan/install). Triggers on skill search, installation, INBOX management, or skill quality queries. When to Use: - User asks to find/search for skills - User wants to install new capabilities - User mentions skills.sh catalog - User wants to develop or optimize a skill - User wants to evaluate skill quality

development1

project-worktrees

项目级 Git worktree 管理工具，面向协同 Agent 设计。支持在项目 .worktrees 目录下创建隔离开发环境，自动依赖安装和测试验证。

data-ai1

wsf-verify-work

Validate built features through conversational UAT

testing1

agents-collab

Foundation rules for how Wopal collaborates with sub-agents such as fae and rook. ⚠️ MUST load before ANY delegation — covers delegation tool APIs, task lifecycle, notifications, status handling, and recovery. 🔴 Trigger: "delegate", "let fae implement", "fae task", "rook review", "check task status", "cancel task", "abort task", "agent collaboration", "委派", "让 fae 执行", "fae 任务", "rook 审查", "检查状态", or any intent to hand work to a sub-agent. 🔴 Never delegate without loading this skill first. Skipping it is serious negligence. Note: this skill does not include workflow-specific prompt templates such as dev-flow templates. Those belong to the corresponding workflow skills.

tools1

df-plan-review

Plan quality verification for dev-flow. Goal-backward analysis ensures plans WILL achieve their stated goal before execution burns context. ⚠️ MUST use when: (1) Reviewing Plan quality before approve (2) Wopal completes Plan writing and needs quality gate (3) User asks to "check plan", "verify plan", "review plan" (4) Plan enters planning status and needs pre-execution validation 🔴 Trigger automatically when Plan is ready for review, even if user doesn't explicitly say "review". Agent: rook (read-only verification subagent) Mode: verification, not execution

development1

youtube-master

YouTube video transcript fetcher + summary/analyzer. ⚠️ MUST use when: (1) User provides YouTube URL + "总结/分析/提取", (2) "总结这个视频"、"视频内容分析"、"这个视频讲了什么", (3) "youtube summary"、"summarize this video"、"video analysis", (4) "YouTube 字幕"、"get transcript", (5) User only provides YouTube URL and context implies processing needed ("看看这个"、"帮我分析"). 🔴 Trigger on ANY YouTube URL when user wants to understand video content.

content-media1

fc-local

Local web scraping & search tool. ⚠️ MUST use when: (1) Scrape/crawl web pages to Markdown, (2) Web search, (3) Batch scrape multiple URLs, (4) Generate LLMs.txt. 🔴 Trigger when user mentions URL scraping, site crawling, web search, or content extraction. 🔄 If anti-crawling blocks fc-local, auto-switch to CDP fallback (scrape-cdp.sh).

tools1

space-master

空间工作规范总纲。⚠️ MUST LOAD FIRST — Wopal 不确定怎么做或任务意图不明确时，第一个加载本技能。 Triggers: 任何意图不明确的任务、"用什么流程"、"该加载什么技能"、技能管理（安装/卸载/搜索）、空间运维（worktree/同步/上游）、多 Space 管理。 🔴 即使用户未明确说"上游同步"，只要涉及 ontology 仓库协作（fork/merge/cherry-pick/PR），就必须加载本技能。

tools1

dev-flow

Issue/Plan 驱动的开发工作流。⚠️ 任务需以 GitHub Issue 或 Plan 为执行载体。 🔴 Trigger: "#14"、"这个 issue"、"出个计划"、"开始开发"、"执行计划"、Plan 生命周期推进（approve/complete/verify/archive）、从 PRD 拆分 Issue。 ❌ Skip: spec 驱动流程、单纯研究/讨论/解释、不需 Issue/Plan 的临时小改动。

development1

df-implement-review

Review implementation results for goal achievement and code quality. Supports both Plan-backed review and planless diff review. ⚠️ MUST use when: (1) Wopal delegates rook to review fae implementation output, (2) Prompt contains "review_type: implementation", (3) Prompt contains changed code file list or Plan path + implementation scope, (4) Any code review request from Wopal. 🔴 Trigger even when user does not explicitly mention "review" if the task involves verifying implementation results. This skill is rook-exclusive (only rook agent can load it).

development1

ellamaka-config

Configure ellamaka, a fork of OpenCode with wopal-space mode. MUST use for any task about ellamaka config, agent frontmatter, permission rules, model/provider selection, formatter settings, config loading order, or why config changes are ignored. Trigger on requests about ellamaka or opencode config files, agent permission overrides, restricting subagents, custom/plugin tool permissions (e.g. wopal_task_*), disabling tools, configuring providers or models, formatter setup, config precedence or layering, or debugging settings that do not take effect. Use this skill even when the user says "opencode" if the actual runtime, config path, or behavior is ellamaka. Prefer this skill whenever the answer depends on the difference between ellamaka and upstream opencode, including wopal-space config loading, plugin tool permissions, or agent frontmatter precedence.

tools1

wsf-validate-phase

Retroactively audit and fill Nyquist validation gaps for a completed phase

testing1

wsf-ui-review

Retroactive 6-pillar visual audit of implemented frontend code

development1