自动化
工作流自动化与调度
thue-tncn-vietnam
disliked-romancelanguage5249
Use when user asks about Vietnamese personal income tax (TNCN), tax finalization (quyet toan), dependent deductions (giam tru gia canh), freelancer/KOL/online seller tax, eTax Mobile, or tax deadlines. Covers fiscal year 2026 under Law 109/2025/QH15. Triggers on: thue, TNCN, quyet toan, ke khai, HKD, 500 trieu nguong, expat, KOL, seller.
discover-skills
nesnilnehc
Identify missing skills and recommend installations from AI Cortex or public skill catalogs. Use when discovering capabilities or suggesting skills to fill gaps.
validate-bsv-script
b-open-io
This skill should be used when the user asks to "validate BSV script", "analyze locking script", "parse unlocking script", "check script opcodes", or needs to validate and analyze Bitcoin scripts using @bsv/sdk.
task-output-validator
dozybot001
Validate task output against criteria before calling Finish. Use when the task has a validation spec (criteria, optionalChecks). Load this skill, write output to sandbox, run validate script, fix issues if validation fails, then call Finish.
sdlc-yolo
uinaf
"ALL coding work. Features, fixes, refactors — never hand-code. Delegates to coding-agent, reviews, auto-merges or escalates."
vibecoding-refactor
GCWing
Vibe Coding Engineering Refactoring Methodology. Systematically refactor AI-generated code through architecture-layer and module-layer deep analysis, discovering duplicate implementations, unused resources, inconsistent patterns, and other typical problems. Supports persistent task management for incremental execution. Use when asked to refactor code, clean up patches, improve code quality, analyze architecture, or optimize codebase.
orchestrator
wyattowalsh
Build and deploy parallel execution via subagent waves, agent teams, and multi-wave pipelines. Use when the Decomposition Gate identifies 2+ independent actions or when spawning teams. NOT for single-action tasks or non-parallel work.
vercel-doctor
Aniket-508
Find ways to cut your Vercel bill. Run after making changes to catch cost-heavy patterns early in Next.js projects.
terminal-title
bluzername
Automatically updates terminal window title to reflect the current high-level task. Use at the start of every Claude Code session when the user provides their first prompt, and whenever the user switches to a distinctly new high-level task. Helps developers manage multiple Claude Code terminals by providing clear, at-a-glance identification of what each terminal is working on.
verify
JinFanZheng
Verification + citation workflow. Use whenever the user asks you to look up information, mentions latest/today/real-time, requests news/weather/prices/scores, or whenever you plan to reference external facts. Requires source links and (when relevant) local published/updated time. NEVER fabricate.
fx
JinFanZheng
Exchange rates / FX lookup workflow. Use for currency exchange rate questions (USD/CNY, EUR/CNY, etc.), “today/latest/real-time” rates, conversion requests, or when you need to cite FX numbers. Default to market mid rate unless user asks for official/bank rates. Must include source link + local update time; NEVER fabricate.
data-viz
JinFanZheng
Data visualization for charts and graphs. Use when user needs "画图/图表/可视化". Creates static PNG or interactive HTML charts from data.
flight
JinFanZheng
Flight status lookup workflow. Use for flight status, delays, cancellations, airport departures/arrivals, or “today/real-time” aviation updates. Prefer airline/airport official sources; always include source link + local update time; NEVER fabricate.
PicoClaw Fleet
EricGrill
Optional teardown if requested
plan
corca-ai
"Agent-assisted plan drafting to define a reviewable execution contract before coding. Reuses gather/clarify evidence first, fills unresolved gaps with targeted research, applies BDD success criteria and cwf:review integration, then persists plan+lessons as runtime-independent files for plan→impl→review continuity. Triggers: \"cwf:plan\", \"plan this task\""
retro
corca-ai
"Comprehensive session retrospective that turns one session's outcomes into persistent improvements. Adaptive depth: deep by default, with light mode via --light (and tiny-session auto-light). Triggers: \"cwf:retro\", \"retro\", \"retrospective\", \"회고\""
agent-estimation
ZhangHanDong
Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time. Use when asked to estimate, scope, plan, or evaluate how long a coding task will take. Prevents the common failure mode where agents anchor to human developer timelines and massively overestimate. Outputs a structured breakdown with round counts, risk factors, and a final wallclock conversion.
gpui-troubleshooting
cnwzhu
Common errors and solutions for GPUI development. Use when debugging build errors, runtime panics, borrow checker issues, or unexpected behavior.
team-tasks
win4r
"Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via sessions_send, and result collection. Supports two modes: linear (sequential pipeline) and dag (dependency graph with parallel execution)."
rive-script-builder
sanqiushili
Build and revise Rive Luau scripts across Node, Layout, Converter, Path Effect, Transition Condition, Listener Action, Util, and Test protocols. Use when the user asks to write or modify Rive scripts, choose protocols, wire script inputs or data binding, debug runtime behavior, or plan unit tests for script logic.
ai-strategist
dangeles
Use when evaluating AI tools and agentic workflows against workflow gaps, when conducting quarterly landscape scans, or when assessing integration feasibility of new tools for startup workflows.
lit-pm
dangeles
Use when coordinating comprehensive literature reviews requiring multi-stage pipeline (archival setup, scope refinement, parallel review discovery, outline synthesis, section writing, fact-checking, editorial polish). Orchestrates literature-researcher, lit-synthesizer, fact-checker, and editor skills with adaptive checkpoints based on complexity and stakes.
cn-holiday
deusyu
中国节假日/调休查询 — 查某天是工作日还是休息日、是否调休补班、全年假期安排。 触发词: 节假日, 调休, 补班, 放假, 上班, holiday, workday, 今天上班吗, 明天放假吗, 春节放几天, 国庆放假, 下个工作日, 或任何 "[日期] 是否放假/上班" 格式的输入。
nl2ledger
deusyu
Natural language bookkeeping — parse Chinese/English expense descriptions and append to QianJi CSV. Trigger phrases: 记账, 记一笔, add expense, spent, 花了, 买了, lunch, dinner, 打车, 咖啡, or any input that looks like "[item] [amount]" or "[amount] [item]".